diff options
author | Dave Airlie <airlied@redhat.com> | 2013-02-08 11:08:10 +1000 |
---|---|---|
committer | Dave Airlie <airlied@redhat.com> | 2013-02-08 11:08:10 +1000 |
commit | cd17ef4114ad5c514b17e6a0bb02a309ab90b692 (patch) | |
tree | 9c162eaa96931597b83e165702e3483ba5c6bb1e /drivers/gpu/drm/i915 | |
parent | 67c964000236497e00c646472cd6b70b5c5109c8 (diff) | |
parent | 7d37beaaf3dbc6ff16f4d32a4dd6f8c557c6ab50 (diff) | |
download | lwn-cd17ef4114ad5c514b17e6a0bb02a309ab90b692.tar.gz lwn-cd17ef4114ad5c514b17e6a0bb02a309ab90b692.zip |
Merge tag 'drm-intel-next-2013-02-01' of git://people.freedesktop.org/~danvet/drm-intel into drm-next
Daniel writes:
"Probably the last feature pull for 3.9, there's some fixes outstanding
thought that I'd like to sneak in. And maybe 3.8 takes a bit longer ...
Anyway, highlights of this pull:
- Kill the horrible IS_DISPLAYREG hack to handle the mmio offset movements
on vlv, big thanks to Ville.
- Dynamic power well support for Haswell, shaves away a bit when only
using the eDP port on pipe A (Paulo). Plus unclaimed register fixes
uncovered by this.
- Clarifications of the gpu hang/reset state transitions, hopefully fixing
a few spurious -EIO deaths in userspace.
- Haswell ELD fixes.
- Some more (pp)gtt cleanups from Ben.
- A few smaller things all over.
Plus all the stuff from the previous rather small pull request:
- Broadcast RBG improvements and reduced color range fixes from Ville.
- Ben is on a "kill legacy gtt code for good" spree, first pile of patches
included.
- No-relocs and bo lut improvements for faster execbuf from Chris.
- Some refactorings from Imre."
* tag 'drm-intel-next-2013-02-01' of git://people.freedesktop.org/~danvet/drm-intel: (101 commits)
GPU/i915: Fix acpi_bus_get_device() check in drivers/gpu/drm/i915/intel_opregion.c
drm/i915: Set the SR01 "screen off" bit in i915_redisable_vga() too
drm/i915: Kill IS_DISPLAYREG()
drm/i915: Introduce i915_vgacntrl_reg()
drm/i915: gen6_gmch_remove can be static
drm/i915: dynamic Haswell display power well support
drm/i915: check the power down well on assert_pipe()
drm/i915: don't send DP "idle" pattern before "normal" on HSW PORT_A
drm/i915: don't run hsw power well code on !hsw
drm/i915: kill cargo-culted locking from power well code
drm/i915: Only run idle processing from i915_gem_retire_requests_worker
drm/i915: Fix CAGF for HSW
drm/i915: Reclaim GTT space for failed PPGTT
drm/i915: remove intel_gtt structure
drm/i915: Add probe and remove to the gtt ops
drm/i915: extract hw ppgtt setup/cleanup code
drm/i915: pte_encode is gen6+
drm/i915: vfuncs for ppgtt
drm/i915: vfuncs for gtt_clear_range/insert_entries
drm/i915: Error state should print /sys/kernel/debug
...
Diffstat (limited to 'drivers/gpu/drm/i915')
29 files changed, 2165 insertions, 1662 deletions
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 0f2c5493242b..91f3ac6cef35 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -16,6 +16,7 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o \ i915_gem_tiling.o \ i915_sysfs.o \ i915_trace_points.o \ + i915_ums.o \ intel_display.o \ intel_crt.o \ intel_lvds.o \ diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 7576e7874698..aa9833babad1 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -258,8 +258,9 @@ static int i915_gem_object_info(struct seq_file *m, void* data) seq_printf(m, "%u fault mappable objects, %zu bytes\n", count, size); - seq_printf(m, "%zu [%zu] gtt total\n", - dev_priv->mm.gtt_total, dev_priv->mm.mappable_gtt_total); + seq_printf(m, "%zu [%lu] gtt total\n", + dev_priv->gtt.total, + dev_priv->gtt.mappable_end - dev_priv->gtt.start); mutex_unlock(&dev->struct_mutex); @@ -813,11 +814,11 @@ static int i915_error_state_open(struct inode *inode, struct file *file) error_priv->dev = dev; - spin_lock_irqsave(&dev_priv->error_lock, flags); - error_priv->error = dev_priv->first_error; + spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); + error_priv->error = dev_priv->gpu_error.first_error; if (error_priv->error) kref_get(&error_priv->error->ref); - spin_unlock_irqrestore(&dev_priv->error_lock, flags); + spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); return single_open(file, i915_error_state, error_priv); } @@ -956,7 +957,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS); u32 rp_state_limits = I915_READ(GEN6_RP_STATE_LIMITS); u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP); - u32 rpstat; + u32 rpstat, cagf; u32 rpupei, rpcurup, rpprevup; u32 rpdownei, rpcurdown, rpprevdown; int max_freq; @@ -975,6 +976,11 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI); rpcurdown = I915_READ(GEN6_RP_CUR_DOWN); rpprevdown = I915_READ(GEN6_RP_PREV_DOWN); + if (IS_HASWELL(dev)) + cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT; + else + cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT; + cagf *= GT_FREQUENCY_MULTIPLIER; gen6_gt_force_wake_put(dev_priv); mutex_unlock(&dev->struct_mutex); @@ -987,8 +993,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) gt_perf_status & 0xff); seq_printf(m, "Render p-state limit: %d\n", rp_state_limits & 0xff); - seq_printf(m, "CAGF: %dMHz\n", ((rpstat & GEN6_CAGF_MASK) >> - GEN6_CAGF_SHIFT) * GT_FREQUENCY_MULTIPLIER); + seq_printf(m, "CAGF: %dMHz\n", cagf); seq_printf(m, "RP CUR UP EI: %dus\n", rpupei & GEN6_CURICONT_MASK); seq_printf(m, "RP CUR UP: %dus\n", rpcurup & @@ -1674,7 +1679,7 @@ i915_wedged_read(struct file *filp, len = snprintf(buf, sizeof(buf), "wedged : %d\n", - atomic_read(&dev_priv->mm.wedged)); + atomic_read(&dev_priv->gpu_error.reset_counter)); if (len > sizeof(buf)) len = sizeof(buf); @@ -1729,7 +1734,7 @@ i915_ring_stop_read(struct file *filp, int len; len = snprintf(buf, sizeof(buf), - "0x%08x\n", dev_priv->stop_rings); + "0x%08x\n", dev_priv->gpu_error.stop_rings); if (len > sizeof(buf)) len = sizeof(buf); @@ -1765,7 +1770,7 @@ i915_ring_stop_write(struct file *filp, if (ret) return ret; - dev_priv->stop_rings = val; + dev_priv->gpu_error.stop_rings = val; mutex_unlock(&dev->struct_mutex); return cnt; @@ -1779,6 +1784,102 @@ static const struct file_operations i915_ring_stop_fops = { .llseek = default_llseek, }; +#define DROP_UNBOUND 0x1 +#define DROP_BOUND 0x2 +#define DROP_RETIRE 0x4 +#define DROP_ACTIVE 0x8 +#define DROP_ALL (DROP_UNBOUND | \ + DROP_BOUND | \ + DROP_RETIRE | \ + DROP_ACTIVE) +static ssize_t +i915_drop_caches_read(struct file *filp, + char __user *ubuf, + size_t max, + loff_t *ppos) +{ + char buf[20]; + int len; + + len = snprintf(buf, sizeof(buf), "0x%08x\n", DROP_ALL); + if (len > sizeof(buf)) + len = sizeof(buf); + + return simple_read_from_buffer(ubuf, max, ppos, buf, len); +} + +static ssize_t +i915_drop_caches_write(struct file *filp, + const char __user *ubuf, + size_t cnt, + loff_t *ppos) +{ + struct drm_device *dev = filp->private_data; + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_object *obj, *next; + char buf[20]; + int val = 0, ret; + + if (cnt > 0) { + if (cnt > sizeof(buf) - 1) + return -EINVAL; + + if (copy_from_user(buf, ubuf, cnt)) + return -EFAULT; + buf[cnt] = 0; + + val = simple_strtoul(buf, NULL, 0); + } + + DRM_DEBUG_DRIVER("Dropping caches: 0x%08x\n", val); + + /* No need to check and wait for gpu resets, only libdrm auto-restarts + * on ioctls on -EAGAIN. */ + ret = mutex_lock_interruptible(&dev->struct_mutex); + if (ret) + return ret; + + if (val & DROP_ACTIVE) { + ret = i915_gpu_idle(dev); + if (ret) + goto unlock; + } + + if (val & (DROP_RETIRE | DROP_ACTIVE)) + i915_gem_retire_requests(dev); + + if (val & DROP_BOUND) { + list_for_each_entry_safe(obj, next, &dev_priv->mm.inactive_list, mm_list) + if (obj->pin_count == 0) { + ret = i915_gem_object_unbind(obj); + if (ret) + goto unlock; + } + } + + if (val & DROP_UNBOUND) { + list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list) + if (obj->pages_pin_count == 0) { + ret = i915_gem_object_put_pages(obj); + if (ret) + goto unlock; + } + } + +unlock: + mutex_unlock(&dev->struct_mutex); + + return ret ?: cnt; +} + +static const struct file_operations i915_drop_caches_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = i915_drop_caches_read, + .write = i915_drop_caches_write, + .llseek = default_llseek, +}; + static ssize_t i915_max_freq_read(struct file *filp, char __user *ubuf, @@ -2176,6 +2277,12 @@ int i915_debugfs_init(struct drm_minor *minor) return ret; ret = i915_debugfs_create(minor->debugfs_root, minor, + "i915_gem_drop_caches", + &i915_drop_caches_fops); + if (ret) + return ret; + + ret = i915_debugfs_create(minor->debugfs_root, minor, "i915_error_state", &i915_error_state_fops); if (ret) @@ -2206,6 +2313,8 @@ void i915_debugfs_cleanup(struct drm_minor *minor) 1, minor); drm_debugfs_remove_files((struct drm_info_list *) &i915_cache_sharing_fops, 1, minor); + drm_debugfs_remove_files((struct drm_info_list *) &i915_drop_caches_fops, + 1, minor); drm_debugfs_remove_files((struct drm_info_list *) &i915_ring_stop_fops, 1, minor); drm_debugfs_remove_files((struct drm_info_list *) &i915_error_state_fops, diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 6d8a1dc74934..cf0610330135 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -992,6 +992,12 @@ static int i915_getparam(struct drm_device *dev, void *data, case I915_PARAM_HAS_PINNED_BATCHES: value = 1; break; + case I915_PARAM_HAS_EXEC_NO_RELOC: + value = 1; + break; + case I915_PARAM_HAS_EXEC_HANDLE_LUT: + value = 1; + break; default: DRM_DEBUG_DRIVER("Unknown parameter %d\n", param->param); @@ -1070,7 +1076,7 @@ static int i915_set_status_page(struct drm_device *dev, void *data, ring->status_page.gfx_addr = hws->addr & (0x1ffff<<12); dev_priv->dri1.gfx_hws_cpu_addr = - ioremap_wc(dev_priv->mm.gtt_base_addr + hws->addr, 4096); + ioremap_wc(dev_priv->gtt.mappable_base + hws->addr, 4096); if (dev_priv->dri1.gfx_hws_cpu_addr == NULL) { i915_dma_cleanup(dev); ring->status_page.gfx_addr = 0; @@ -1420,9 +1426,9 @@ static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv) if (!ap) return; - ap->ranges[0].base = dev_priv->mm.gtt->gma_bus_addr; - ap->ranges[0].size = - dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; + ap->ranges[0].base = dev_priv->gtt.mappable_base; + ap->ranges[0].size = dev_priv->gtt.mappable_end - dev_priv->gtt.start; + primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; @@ -1536,18 +1542,17 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto put_gmch; } - aperture_size = dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; - dev_priv->mm.gtt_base_addr = dev_priv->mm.gtt->gma_bus_addr; + aperture_size = dev_priv->gtt.mappable_end; - dev_priv->mm.gtt_mapping = - io_mapping_create_wc(dev_priv->mm.gtt_base_addr, + dev_priv->gtt.mappable = + io_mapping_create_wc(dev_priv->gtt.mappable_base, aperture_size); - if (dev_priv->mm.gtt_mapping == NULL) { + if (dev_priv->gtt.mappable == NULL) { ret = -EIO; goto out_rmmap; } - i915_mtrr_setup(dev_priv, dev_priv->mm.gtt_base_addr, + i915_mtrr_setup(dev_priv, dev_priv->gtt.mappable_base, aperture_size); /* The i915 workqueue is primarily used for batched retirement of @@ -1600,7 +1605,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) pci_enable_msi(dev->pdev); spin_lock_init(&dev_priv->irq_lock); - spin_lock_init(&dev_priv->error_lock); + spin_lock_init(&dev_priv->gpu_error.lock); spin_lock_init(&dev_priv->rps.lock); mutex_init(&dev_priv->dpio_lock); @@ -1652,15 +1657,15 @@ out_gem_unload: out_mtrrfree: if (dev_priv->mm.gtt_mtrr >= 0) { mtrr_del(dev_priv->mm.gtt_mtrr, - dev_priv->mm.gtt_base_addr, + dev_priv->gtt.mappable_base, aperture_size); dev_priv->mm.gtt_mtrr = -1; } - io_mapping_free(dev_priv->mm.gtt_mapping); + io_mapping_free(dev_priv->gtt.mappable); out_rmmap: pci_iounmap(dev->pdev, dev_priv->regs); put_gmch: - i915_gem_gtt_fini(dev); + dev_priv->gtt.gtt_remove(dev); put_bridge: pci_dev_put(dev_priv->bridge_dev); free_priv: @@ -1690,11 +1695,11 @@ int i915_driver_unload(struct drm_device *dev) /* Cancel the retire work handler, which should be idle now. */ cancel_delayed_work_sync(&dev_priv->mm.retire_work); - io_mapping_free(dev_priv->mm.gtt_mapping); + io_mapping_free(dev_priv->gtt.mappable); if (dev_priv->mm.gtt_mtrr >= 0) { mtrr_del(dev_priv->mm.gtt_mtrr, - dev_priv->mm.gtt_base_addr, - dev_priv->mm.gtt->gtt_mappable_entries * PAGE_SIZE); + dev_priv->gtt.mappable_base, + dev_priv->gtt.mappable_end); dev_priv->mm.gtt_mtrr = -1; } @@ -1720,8 +1725,8 @@ int i915_driver_unload(struct drm_device *dev) } /* Free error state after interrupts are fully disabled. */ - del_timer_sync(&dev_priv->hangcheck_timer); - cancel_work_sync(&dev_priv->error_work); + del_timer_sync(&dev_priv->gpu_error.hangcheck_timer); + cancel_work_sync(&dev_priv->gpu_error.work); i915_destroy_error_state(dev); if (dev->pdev->msi_enabled) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index c8cbc32fe8db..d159d7a402e9 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -276,6 +276,7 @@ static const struct intel_device_info intel_valleyview_m_info = { .has_bsd_ring = 1, .has_blt_ring = 1, .is_valleyview = 1, + .display_mmio_offset = VLV_DISPLAY_BASE, }; static const struct intel_device_info intel_valleyview_d_info = { @@ -285,6 +286,7 @@ static const struct intel_device_info intel_valleyview_d_info = { .has_bsd_ring = 1, .has_blt_ring = 1, .is_valleyview = 1, + .display_mmio_offset = VLV_DISPLAY_BASE, }; static const struct intel_device_info intel_haswell_d_info = { @@ -468,6 +470,8 @@ static int i915_drm_freeze(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + intel_set_power_well(dev, true); + drm_kms_helper_poll_disable(dev); pci_save_state(dev->pdev); @@ -779,9 +783,9 @@ int intel_gpu_reset(struct drm_device *dev) } /* Also reset the gpu hangman. */ - if (dev_priv->stop_rings) { + if (dev_priv->gpu_error.stop_rings) { DRM_DEBUG("Simulated gpu hang, resetting stop_rings\n"); - dev_priv->stop_rings = 0; + dev_priv->gpu_error.stop_rings = 0; if (ret == -ENODEV) { DRM_ERROR("Reset not implemented, but ignoring " "error for simulated gpu hangs\n"); @@ -820,12 +824,12 @@ int i915_reset(struct drm_device *dev) i915_gem_reset(dev); ret = -ENODEV; - if (get_seconds() - dev_priv->last_gpu_reset < 5) + if (get_seconds() - dev_priv->gpu_error.last_reset < 5) DRM_ERROR("GPU hanging too fast, declaring wedged!\n"); else ret = intel_gpu_reset(dev); - dev_priv->last_gpu_reset = get_seconds(); + dev_priv->gpu_error.last_reset = get_seconds(); if (ret) { DRM_ERROR("Failed to reset chip.\n"); mutex_unlock(&dev->struct_mutex); @@ -1115,102 +1119,6 @@ MODULE_LICENSE("GPL and additional rights"); ((HAS_FORCE_WAKE((dev_priv)->dev)) && \ ((reg) < 0x40000) && \ ((reg) != FORCEWAKE)) - -static bool IS_DISPLAYREG(u32 reg) -{ - /* - * This should make it easier to transition modules over to the - * new register block scheme, since we can do it incrementally. - */ - if (reg >= VLV_DISPLAY_BASE) - return false; - - if (reg >= RENDER_RING_BASE && - reg < RENDER_RING_BASE + 0xff) - return false; - if (reg >= GEN6_BSD_RING_BASE && - reg < GEN6_BSD_RING_BASE + 0xff) - return false; - if (reg >= BLT_RING_BASE && - reg < BLT_RING_BASE + 0xff) - return false; - - if (reg == PGTBL_ER) - return false; - - if (reg >= IPEIR_I965 && - reg < HWSTAM) - return false; - - if (reg == MI_MODE) - return false; - - if (reg == GFX_MODE_GEN7) - return false; - - if (reg == RENDER_HWS_PGA_GEN7 || - reg == BSD_HWS_PGA_GEN7 || - reg == BLT_HWS_PGA_GEN7) - return false; - - if (reg == GEN6_BSD_SLEEP_PSMI_CONTROL || - reg == GEN6_BSD_RNCID) - return false; - - if (reg == GEN6_BLITTER_ECOSKPD) - return false; - - if (reg >= 0x4000c && - reg <= 0x4002c) - return false; - - if (reg >= 0x4f000 && - reg <= 0x4f08f) - return false; - - if (reg >= 0x4f100 && - reg <= 0x4f11f) - return false; - - if (reg >= VLV_MASTER_IER && - reg <= GEN6_PMIER) - return false; - - if (reg >= FENCE_REG_SANDYBRIDGE_0 && - reg < (FENCE_REG_SANDYBRIDGE_0 + (16*8))) - return false; - - if (reg >= VLV_IIR_RW && - reg <= VLV_ISR) - return false; - - if (reg == FORCEWAKE_VLV || - reg == FORCEWAKE_ACK_VLV) - return false; - - if (reg == GEN6_GDRST) - return false; - - switch (reg) { - case _3D_CHICKEN3: - case IVB_CHICKEN3: - case GEN7_COMMON_SLICE_CHICKEN1: - case GEN7_L3CNTLREG1: - case GEN7_L3_CHICKEN_MODE_REGISTER: - case GEN7_ROW_CHICKEN2: - case GEN7_L3SQCREG4: - case GEN7_SQ_CHICKEN_MBCUNIT_CONFIG: - case GEN7_HALF_SLICE_CHICKEN1: - case GEN6_MBCTL: - case GEN6_UCGCTL2: - return false; - default: - break; - } - - return true; -} - static void ilk_dummy_write(struct drm_i915_private *dev_priv) { @@ -1234,8 +1142,6 @@ u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \ if (dev_priv->forcewake_count == 0) \ dev_priv->gt.force_wake_put(dev_priv); \ spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); \ - } else if (IS_VALLEYVIEW(dev_priv->dev) && IS_DISPLAYREG(reg)) { \ - val = read##y(dev_priv->regs + reg + 0x180000); \ } else { \ val = read##y(dev_priv->regs + reg); \ } \ @@ -1262,11 +1168,7 @@ void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \ DRM_ERROR("Unknown unclaimed register before writing to %x\n", reg); \ I915_WRITE_NOTRACE(GEN7_ERR_INT, ERR_INT_MMIO_UNCLAIMED); \ } \ - if (IS_VALLEYVIEW(dev_priv->dev) && IS_DISPLAYREG(reg)) { \ - write##y(val, dev_priv->regs + reg + 0x180000); \ - } else { \ - write##y(val, dev_priv->regs + reg); \ - } \ + write##y(val, dev_priv->regs + reg); \ if (unlikely(__fifo_ret)) { \ gen6_gt_check_fifodbg(dev_priv); \ } \ diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index b1b1b7350ca4..984523d809a8 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -337,6 +337,7 @@ struct drm_i915_gt_funcs { DEV_INFO_FLAG(has_llc) struct intel_device_info { + u32 display_mmio_offset; u8 gen; u8 is_mobile:1; u8 is_i85x:1; @@ -364,6 +365,49 @@ struct intel_device_info { u8 has_llc:1; }; +enum i915_cache_level { + I915_CACHE_NONE = 0, + I915_CACHE_LLC, + I915_CACHE_LLC_MLC, /* gen6+, in docs at least! */ +}; + +/* The Graphics Translation Table is the way in which GEN hardware translates a + * Graphics Virtual Address into a Physical Address. In addition to the normal + * collateral associated with any va->pa translations GEN hardware also has a + * portion of the GTT which can be mapped by the CPU and remain both coherent + * and correct (in cases like swizzling). That region is referred to as GMADR in + * the spec. + */ +struct i915_gtt { + unsigned long start; /* Start offset of used GTT */ + size_t total; /* Total size GTT can map */ + size_t stolen_size; /* Total size of stolen memory */ + + unsigned long mappable_end; /* End offset that we can CPU map */ + struct io_mapping *mappable; /* Mapping to our CPU mappable region */ + phys_addr_t mappable_base; /* PA of our GMADR */ + + /** "Graphics Stolen Memory" holds the global PTEs */ + void __iomem *gsm; + + bool do_idle_maps; + dma_addr_t scratch_page_dma; + struct page *scratch_page; + + /* global gtt ops */ + int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total, + size_t *stolen); + void (*gtt_remove)(struct drm_device *dev); + void (*gtt_clear_range)(struct drm_device *dev, + unsigned int first_entry, + unsigned int num_entries); + void (*gtt_insert_entries)(struct drm_device *dev, + struct sg_table *st, + unsigned int pg_start, + enum i915_cache_level cache_level); +}; +#define gtt_total_entries(gtt) ((gtt).total >> PAGE_SHIFT) + #define I915_PPGTT_PD_ENTRIES 512 #define I915_PPGTT_PT_ENTRIES 1024 struct i915_hw_ppgtt { @@ -373,6 +417,16 @@ struct i915_hw_ppgtt { uint32_t pd_offset; dma_addr_t *pt_dma_addr; dma_addr_t scratch_page_dma_addr; + + /* pte functions, mirroring the interface of the global gtt. */ + void (*clear_range)(struct i915_hw_ppgtt *ppgtt, + unsigned int first_entry, + unsigned int num_entries); + void (*insert_entries)(struct i915_hw_ppgtt *ppgtt, + struct sg_table *st, + unsigned int pg_start, + enum i915_cache_level cache_level); + void (*cleanup)(struct i915_hw_ppgtt *ppgtt); }; @@ -642,6 +696,153 @@ struct intel_l3_parity { struct work_struct error_work; }; +struct i915_gem_mm { + /** Memory allocator for GTT stolen memory */ + struct drm_mm stolen; + /** Memory allocator for GTT */ + struct drm_mm gtt_space; + /** List of all objects in gtt_space. Used to restore gtt + * mappings on resume */ + struct list_head bound_list; + /** + * List of objects which are not bound to the GTT (thus + * are idle and not used by the GPU) but still have + * (presumably uncached) pages still attached. + */ + struct list_head unbound_list; + + /** Usable portion of the GTT for GEM */ + unsigned long stolen_base; /* limited to low memory (32-bit) */ + + int gtt_mtrr; + + /** PPGTT used for aliasing the PPGTT with the GTT */ + struct i915_hw_ppgtt *aliasing_ppgtt; + + struct shrinker inactive_shrinker; + bool shrinker_no_lock_stealing; + + /** + * List of objects currently involved in rendering. + * + * Includes buffers having the contents of their GPU caches + * flushed, not necessarily primitives. last_rendering_seqno + * represents when the rendering involved will be completed. + * + * A reference is held on the buffer while on this list. + */ + struct list_head active_list; + + /** + * LRU list of objects which are not in the ringbuffer and + * are ready to unbind, but are still in the GTT. + * + * last_rendering_seqno is 0 while an object is in this list. + * + * A reference is not held on the buffer while on this list, + * as merely being GTT-bound shouldn't prevent its being + * freed, and we'll pull it off the list in the free path. + */ + struct list_head inactive_list; + + /** LRU list of objects with fence regs on them. */ + struct list_head fence_list; + + /** + * We leave the user IRQ off as much as possible, + * but this means that requests will finish and never + * be retired once the system goes idle. Set a timer to + * fire periodically while the ring is running. When it + * fires, go retire requests. + */ + struct delayed_work retire_work; + + /** + * Are we in a non-interruptible section of code like + * modesetting? + */ + bool interruptible; + + /** + * Flag if the X Server, and thus DRM, is not currently in + * control of the device. + * + * This is set between LeaveVT and EnterVT. It needs to be + * replaced with a semaphore. It also needs to be + * transitioned away from for kernel modesetting. + */ + int suspended; + + /** Bit 6 swizzling required for X tiling */ + uint32_t bit_6_swizzle_x; + /** Bit 6 swizzling required for Y tiling */ + uint32_t bit_6_swizzle_y; + + /* storage for physical objects */ + struct drm_i915_gem_phys_object *phys_objs[I915_MAX_PHYS_OBJECT]; + + /* accounting, useful for userland debugging */ + size_t object_memory; + u32 object_count; +}; + +struct i915_gpu_error { + /* For hangcheck timer */ +#define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */ +#define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD) + struct timer_list hangcheck_timer; + int hangcheck_count; + uint32_t last_acthd[I915_NUM_RINGS]; + uint32_t prev_instdone[I915_NUM_INSTDONE_REG]; + + /* For reset and error_state handling. */ + spinlock_t lock; + /* Protected by the above dev->gpu_error.lock. */ + struct drm_i915_error_state *first_error; + struct work_struct work; + + unsigned long last_reset; + + /** + * State variable and reset counter controlling the reset flow + * + * Upper bits are for the reset counter. This counter is used by the + * wait_seqno code to race-free noticed that a reset event happened and + * that it needs to restart the entire ioctl (since most likely the + * seqno it waited for won't ever signal anytime soon). + * + * This is important for lock-free wait paths, where no contended lock + * naturally enforces the correct ordering between the bail-out of the + * waiter and the gpu reset work code. + * + * Lowest bit controls the reset state machine: Set means a reset is in + * progress. This state will (presuming we don't have any bugs) decay + * into either unset (successful reset) or the special WEDGED value (hw + * terminally sour). All waiters on the reset_queue will be woken when + * that happens. + */ + atomic_t reset_counter; + + /** + * Special values/flags for reset_counter + * + * Note that the code relies on + * I915_WEDGED & I915_RESET_IN_PROGRESS_FLAG + * being true. + */ +#define I915_RESET_IN_PROGRESS_FLAG 1 +#define I915_WEDGED 0xffffffff + + /** + * Waitqueue to signal when the reset has completed. Used by clients + * that wait for dev_priv->mm.wedged to settle. + */ + wait_queue_head_t reset_queue; + + /* For gpu hang simulation. */ + unsigned int stop_rings; +}; + typedef struct drm_i915_private { struct drm_device *dev; struct kmem_cache *slab; @@ -697,7 +898,6 @@ typedef struct drm_i915_private { u32 pipestat[2]; u32 irq_mask; u32 gt_irq_mask; - u32 pch_irq_mask; u32 hotplug_supported_mask; struct work_struct hotplug_work; @@ -706,16 +906,6 @@ typedef struct drm_i915_private { int num_pipe; int num_pch_pll; - /* For hangcheck timer */ -#define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */ -#define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD) - struct timer_list hangcheck_timer; - int hangcheck_count; - uint32_t last_acthd[I915_NUM_RINGS]; - uint32_t prev_instdone[I915_NUM_INSTDONE_REG]; - - unsigned int stop_rings; - unsigned long cfb_size; unsigned int cfb_fb; enum plane cfb_plane; @@ -763,11 +953,6 @@ typedef struct drm_i915_private { unsigned int fsb_freq, mem_freq, is_ddr3; - spinlock_t error_lock; - /* Protected by dev->error_lock. */ - struct drm_i915_error_state *first_error; - struct work_struct error_work; - struct completion error_completion; struct workqueue_struct *wq; /* Display functions */ @@ -782,116 +967,9 @@ typedef struct drm_i915_private { /* Register state */ bool modeset_on_lid; - struct { - /** Bridge to intel-gtt-ko */ - struct intel_gtt *gtt; - /** Memory allocator for GTT stolen memory */ - struct drm_mm stolen; - /** Memory allocator for GTT */ - struct drm_mm gtt_space; - /** List of all objects in gtt_space. Used to restore gtt - * mappings on resume */ - struct list_head bound_list; - /** - * List of objects which are not bound to the GTT (thus - * are idle and not used by the GPU) but still have - * (presumably uncached) pages still attached. - */ - struct list_head unbound_list; - - /** Usable portion of the GTT for GEM */ - unsigned long gtt_start; - unsigned long gtt_mappable_end; - unsigned long gtt_end; - unsigned long stolen_base; /* limited to low memory (32-bit) */ - - /** "Graphics Stolen Memory" holds the global PTEs */ - void __iomem *gsm; - - struct io_mapping *gtt_mapping; - phys_addr_t gtt_base_addr; - int gtt_mtrr; - - /** PPGTT used for aliasing the PPGTT with the GTT */ - struct i915_hw_ppgtt *aliasing_ppgtt; - - struct shrinker inactive_shrinker; - bool shrinker_no_lock_stealing; - - /** - * List of objects currently involved in rendering. - * - * Includes buffers having the contents of their GPU caches - * flushed, not necessarily primitives. last_rendering_seqno - * represents when the rendering involved will be completed. - * - * A reference is held on the buffer while on this list. - */ - struct list_head active_list; - - /** - * LRU list of objects which are not in the ringbuffer and - * are ready to unbind, but are still in the GTT. - * - * last_rendering_seqno is 0 while an object is in this list. - * - * A reference is not held on the buffer while on this list, - * as merely being GTT-bound shouldn't prevent its being - * freed, and we'll pull it off the list in the free path. - */ - struct list_head inactive_list; - - /** LRU list of objects with fence regs on them. */ - struct list_head fence_list; - - /** - * We leave the user IRQ off as much as possible, - * but this means that requests will finish and never - * be retired once the system goes idle. Set a timer to - * fire periodically while the ring is running. When it - * fires, go retire requests. - */ - struct delayed_work retire_work; - - /** - * Are we in a non-interruptible section of code like - * modesetting? - */ - bool interruptible; - - /** - * Flag if the X Server, and thus DRM, is not currently in - * control of the device. - * - * This is set between LeaveVT and EnterVT. It needs to be - * replaced with a semaphore. It also needs to be - * transitioned away from for kernel modesetting. - */ - int suspended; - - /** - * Flag if the hardware appears to be wedged. - * - * This is set when attempts to idle the device timeout. - * It prevents command submission from occurring and makes - * every pending request fail - */ - atomic_t wedged; - - /** Bit 6 swizzling required for X tiling */ - uint32_t bit_6_swizzle_x; - /** Bit 6 swizzling required for Y tiling */ - uint32_t bit_6_swizzle_y; - - /* storage for physical objects */ - struct drm_i915_gem_phys_object *phys_objs[I915_MAX_PHYS_OBJECT]; - - /* accounting, useful for userland debugging */ - size_t gtt_total; - size_t mappable_gtt_total; - size_t object_memory; - u32 object_count; - } mm; + struct i915_gtt gtt; + + struct i915_gem_mm mm; /* Kernel Modesetting */ @@ -933,7 +1011,7 @@ typedef struct drm_i915_private { struct drm_mm_node *compressed_fb; struct drm_mm_node *compressed_llb; - unsigned long last_gpu_reset; + struct i915_gpu_error gpu_error; /* list of fbdev register on this device */ struct intel_fbdev *fbdev; @@ -973,12 +1051,6 @@ enum hdmi_force_audio { HDMI_AUDIO_ON, /* force turn on HDMI audio */ }; -enum i915_cache_level { - I915_CACHE_NONE = 0, - I915_CACHE_LLC, - I915_CACHE_LLC_MLC, /* gen6+, in docs at least! */ -}; - #define I915_GTT_RESERVED ((struct drm_mm_node *)0x1) struct drm_i915_gem_object_ops { @@ -1446,6 +1518,7 @@ int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj, bool nonblocking); void i915_gem_object_unpin(struct drm_i915_gem_object *obj); int __must_check i915_gem_object_unbind(struct drm_i915_gem_object *obj); +int i915_gem_object_put_pages(struct drm_i915_gem_object *obj); void i915_gem_release_mmap(struct drm_i915_gem_object *obj); void i915_gem_lastclose(struct drm_device *dev); @@ -1524,8 +1597,18 @@ 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); -int __must_check i915_gem_check_wedge(struct drm_i915_private *dev_priv, +int __must_check i915_gem_check_wedge(struct i915_gpu_error *error, bool interruptible); +static inline bool i915_reset_in_progress(struct i915_gpu_error *error) +{ + return unlikely(atomic_read(&error->reset_counter) + & I915_RESET_IN_PROGRESS_FLAG); +} + +static inline bool i915_terminally_wedged(struct i915_gpu_error *error) +{ + return atomic_read(&error->reset_counter) == I915_WEDGED; +} void i915_gem_reset(struct drm_device *dev); void i915_gem_clflush_object(struct drm_i915_gem_object *obj); @@ -1566,9 +1649,10 @@ void i915_gem_free_all_phys_object(struct drm_device *dev); void i915_gem_release(struct drm_device *dev, struct drm_file *file); uint32_t -i915_gem_get_unfenced_gtt_alignment(struct drm_device *dev, - uint32_t size, - int tiling_mode); +i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode); +uint32_t +i915_gem_get_gtt_alignment(struct drm_device *dev, uint32_t size, + int tiling_mode, bool fenced); int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level); @@ -1591,7 +1675,6 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file); /* 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, @@ -1609,7 +1692,6 @@ void i915_gem_init_global_gtt(struct drm_device *dev); void i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start, unsigned long mappable_end, unsigned long end); int i915_gem_gtt_init(struct drm_device *dev); -void i915_gem_gtt_fini(struct drm_device *dev); static inline void i915_gem_chipset_flush(struct drm_device *dev) { if (INTEL_INFO(dev)->gen < 6) @@ -1668,9 +1750,9 @@ void i915_debugfs_cleanup(struct drm_minor *minor); extern int i915_save_state(struct drm_device *dev); extern int i915_restore_state(struct drm_device *dev); -/* i915_suspend.c */ -extern int i915_save_state(struct drm_device *dev); -extern int i915_restore_state(struct drm_device *dev); +/* i915_ums.c */ +void i915_save_display_reg(struct drm_device *dev); +void i915_restore_display_reg(struct drm_device *dev); /* i915_sysfs.c */ void i915_setup_sysfs(struct drm_device *dev_priv); @@ -1727,6 +1809,7 @@ extern void intel_modeset_cleanup(struct drm_device *dev); extern int intel_modeset_vga_set_state(struct drm_device *dev, bool state); extern void intel_modeset_setup_hw_state(struct drm_device *dev, bool force_restore); +extern void i915_redisable_vga(struct drm_device *dev); extern bool intel_fbc_enabled(struct drm_device *dev); extern void intel_disable_fbc(struct drm_device *dev); extern bool ironlake_set_drps(struct drm_device *dev, u8 val); @@ -1799,5 +1882,19 @@ __i915_write(64, q) #define POSTING_READ(reg) (void)I915_READ_NOTRACE(reg) #define POSTING_READ16(reg) (void)I915_READ16_NOTRACE(reg) +/* "Broadcast RGB" property */ +#define INTEL_BROADCAST_RGB_AUTO 0 +#define INTEL_BROADCAST_RGB_FULL 1 +#define INTEL_BROADCAST_RGB_LIMITED 2 + +static inline uint32_t i915_vgacntrl_reg(struct drm_device *dev) +{ + if (HAS_PCH_SPLIT(dev)) + return CPU_VGACNTRL; + else if (IS_VALLEYVIEW(dev)) + return VLV_VGACNTRL; + else + return VGACNTRL; +} #endif diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 4418e14e3d69..62be74899c2b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -87,47 +87,43 @@ static void i915_gem_info_remove_obj(struct drm_i915_private *dev_priv, } static int -i915_gem_wait_for_error(struct drm_device *dev) +i915_gem_wait_for_error(struct i915_gpu_error *error) { - struct drm_i915_private *dev_priv = dev->dev_private; - struct completion *x = &dev_priv->error_completion; - unsigned long flags; int ret; - if (!atomic_read(&dev_priv->mm.wedged)) +#define EXIT_COND (!i915_reset_in_progress(error)) + if (EXIT_COND) return 0; + /* GPU is already declared terminally dead, give up. */ + if (i915_terminally_wedged(error)) + return -EIO; + /* * Only wait 10 seconds for the gpu reset to complete to avoid hanging * userspace. If it takes that long something really bad is going on and * we should simply try to bail out and fail as gracefully as possible. */ - ret = wait_for_completion_interruptible_timeout(x, 10*HZ); + ret = wait_event_interruptible_timeout(error->reset_queue, + EXIT_COND, + 10*HZ); if (ret == 0) { DRM_ERROR("Timed out waiting for the gpu reset to complete\n"); return -EIO; } else if (ret < 0) { return ret; } +#undef EXIT_COND - if (atomic_read(&dev_priv->mm.wedged)) { - /* GPU is hung, bump the completion count to account for - * the token we just consumed so that we never hit zero and - * end up waiting upon a subsequent completion event that - * will never happen. - */ - spin_lock_irqsave(&x->wait.lock, flags); - x->done++; - spin_unlock_irqrestore(&x->wait.lock, flags); - } return 0; } int i915_mutex_lock_interruptible(struct drm_device *dev) { + struct drm_i915_private *dev_priv = dev->dev_private; int ret; - ret = i915_gem_wait_for_error(dev); + ret = i915_gem_wait_for_error(&dev_priv->gpu_error); if (ret) return ret; @@ -149,6 +145,7 @@ int i915_gem_init_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { + struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_init *args = data; if (drm_core_check_feature(dev, DRIVER_MODESET)) @@ -165,6 +162,7 @@ i915_gem_init_ioctl(struct drm_device *dev, void *data, mutex_lock(&dev->struct_mutex); i915_gem_setup_global_gtt(dev, args->gtt_start, args->gtt_end, args->gtt_end); + dev_priv->gtt.mappable_end = args->gtt_end; mutex_unlock(&dev->struct_mutex); return 0; @@ -186,7 +184,7 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, pinned += obj->gtt_space->size; mutex_unlock(&dev->struct_mutex); - args->aper_size = dev_priv->mm.gtt_total; + args->aper_size = dev_priv->gtt.total; args->aper_available_size = args->aper_size - pinned; return 0; @@ -637,7 +635,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev, * source page isn't available. Return the error and we'll * retry in the slow path. */ - if (fast_user_write(dev_priv->mm.gtt_mapping, page_base, + if (fast_user_write(dev_priv->gtt.mappable, page_base, page_offset, user_data, page_length)) { ret = -EFAULT; goto out_unpin; @@ -937,26 +935,17 @@ unlock: } int -i915_gem_check_wedge(struct drm_i915_private *dev_priv, +i915_gem_check_wedge(struct i915_gpu_error *error, bool interruptible) { - if (atomic_read(&dev_priv->mm.wedged)) { - struct completion *x = &dev_priv->error_completion; - bool recovery_complete; - unsigned long flags; - - /* Give the error handler a chance to run. */ - spin_lock_irqsave(&x->wait.lock, flags); - recovery_complete = x->done > 0; - spin_unlock_irqrestore(&x->wait.lock, flags); - + if (i915_reset_in_progress(error)) { /* Non-interruptible callers can't handle -EAGAIN, hence return * -EIO unconditionally for these. */ if (!interruptible) return -EIO; - /* Recovery complete, but still wedged means reset failure. */ - if (recovery_complete) + /* Recovery complete, but the reset failed ... */ + if (i915_terminally_wedged(error)) return -EIO; return -EAGAIN; @@ -987,13 +976,22 @@ i915_gem_check_olr(struct intel_ring_buffer *ring, u32 seqno) * __wait_seqno - wait until execution of seqno has finished * @ring: the ring expected to report seqno * @seqno: duh! + * @reset_counter: reset sequence associated with the given seqno * @interruptible: do an interruptible wait (normally yes) * @timeout: in - how long to wait (NULL forever); out - how much time remaining * + * 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 + * locks are involved, it is sufficient to read the reset_counter before + * unlocking the lock that protects the seqno. For lockless tricks, the + * reset_counter _must_ be read before, and an appropriate smp_rmb must be + * inserted. + * * Returns 0 if the seqno was found within the alloted time. Else returns the * errno with remaining time filled in timeout argument. */ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, + unsigned reset_counter, bool interruptible, struct timespec *timeout) { drm_i915_private_t *dev_priv = ring->dev->dev_private; @@ -1023,7 +1021,8 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, #define EXIT_COND \ (i915_seqno_passed(ring->get_seqno(ring, false), seqno) || \ - atomic_read(&dev_priv->mm.wedged)) + i915_reset_in_progress(&dev_priv->gpu_error) || \ + reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter)) do { if (interruptible) end = wait_event_interruptible_timeout(ring->irq_queue, @@ -1033,7 +1032,14 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, end = wait_event_timeout(ring->irq_queue, EXIT_COND, timeout_jiffies); - ret = i915_gem_check_wedge(dev_priv, interruptible); + /* We need to check whether any gpu reset happened in between + * the caller grabbing the seqno and now ... */ + if (reset_counter != atomic_read(&dev_priv->gpu_error.reset_counter)) + end = -EAGAIN; + + /* ... but upgrade the -EGAIN to an -EIO if the gpu is truely + * gone. */ + ret = i915_gem_check_wedge(&dev_priv->gpu_error, interruptible); if (ret) end = ret; } while (end == 0 && wait_forever); @@ -1079,7 +1085,7 @@ i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno) BUG_ON(!mutex_is_locked(&dev->struct_mutex)); BUG_ON(seqno == 0); - ret = i915_gem_check_wedge(dev_priv, interruptible); + ret = i915_gem_check_wedge(&dev_priv->gpu_error, interruptible); if (ret) return ret; @@ -1087,7 +1093,9 @@ i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno) if (ret) return ret; - return __wait_seqno(ring, seqno, interruptible, NULL); + return __wait_seqno(ring, seqno, + atomic_read(&dev_priv->gpu_error.reset_counter), + interruptible, NULL); } /** @@ -1134,6 +1142,7 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj, struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_ring_buffer *ring = obj->ring; + unsigned reset_counter; u32 seqno; int ret; @@ -1144,7 +1153,7 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj, if (seqno == 0) return 0; - ret = i915_gem_check_wedge(dev_priv, true); + ret = i915_gem_check_wedge(&dev_priv->gpu_error, true); if (ret) return ret; @@ -1152,8 +1161,9 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj, if (ret) return ret; + reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter); mutex_unlock(&dev->struct_mutex); - ret = __wait_seqno(ring, seqno, true, NULL); + ret = __wait_seqno(ring, seqno, reset_counter, true, NULL); mutex_lock(&dev->struct_mutex); i915_gem_retire_requests_ring(ring); @@ -1362,7 +1372,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) obj->fault_mappable = true; - pfn = ((dev_priv->mm.gtt_base_addr + obj->gtt_offset) >> PAGE_SHIFT) + + pfn = ((dev_priv->gtt.mappable_base + obj->gtt_offset) >> PAGE_SHIFT) + page_offset; /* Finally, remap it using the new GTT offset */ @@ -1377,7 +1387,7 @@ out: /* If this -EIO is due to a gpu hang, give the reset code a * chance to clean up the mess. Otherwise return the proper * SIGBUS. */ - if (!atomic_read(&dev_priv->mm.wedged)) + if (i915_terminally_wedged(&dev_priv->gpu_error)) return VM_FAULT_SIGBUS; case -EAGAIN: /* Give the error handler a chance to run and move the @@ -1435,7 +1445,7 @@ i915_gem_release_mmap(struct drm_i915_gem_object *obj) obj->fault_mappable = false; } -static uint32_t +uint32_t i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode) { uint32_t gtt_size; @@ -1463,16 +1473,15 @@ i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode) * Return the required GTT alignment for an object, taking into account * potential fence register mapping. */ -static uint32_t -i915_gem_get_gtt_alignment(struct drm_device *dev, - uint32_t size, - int tiling_mode) +uint32_t +i915_gem_get_gtt_alignment(struct drm_device *dev, uint32_t size, + int tiling_mode, bool fenced) { /* * Minimum alignment is 4k (GTT page size), but might be greater * if a fence register is needed for the object. */ - if (INTEL_INFO(dev)->gen >= 4 || + if (INTEL_INFO(dev)->gen >= 4 || (!fenced && IS_G33(dev)) || tiling_mode == I915_TILING_NONE) return 4096; @@ -1483,35 +1492,6 @@ i915_gem_get_gtt_alignment(struct drm_device *dev, return i915_gem_get_gtt_size(dev, size, tiling_mode); } -/** - * i915_gem_get_unfenced_gtt_alignment - return required GTT alignment for an - * unfenced object - * @dev: the device - * @size: size of the object - * @tiling_mode: tiling mode of the object - * - * Return the required GTT alignment for an object, only taking into account - * unfenced tiled surface requirements. - */ -uint32_t -i915_gem_get_unfenced_gtt_alignment(struct drm_device *dev, - uint32_t size, - int tiling_mode) -{ - /* - * Minimum alignment is 4k (GTT page size) for sane hw. - */ - if (INTEL_INFO(dev)->gen >= 4 || IS_G33(dev) || - tiling_mode == I915_TILING_NONE) - return 4096; - - /* Previous hardware however needs to be aligned to a power-of-two - * tile height. The simplest method for determining this is to reuse - * the power-of-tile object size. - */ - return i915_gem_get_gtt_size(dev, size, tiling_mode); -} - static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj) { struct drm_i915_private *dev_priv = obj->base.dev->dev_private; @@ -1574,7 +1554,7 @@ i915_gem_mmap_gtt(struct drm_file *file, goto unlock; } - if (obj->base.size > dev_priv->mm.gtt_mappable_end) { + if (obj->base.size > dev_priv->gtt.mappable_end) { ret = -E2BIG; goto out; } @@ -1692,7 +1672,7 @@ i915_gem_object_put_pages_gtt(struct drm_i915_gem_object *obj) kfree(obj->pages); } -static int +int i915_gem_object_put_pages(struct drm_i915_gem_object *obj) { const struct drm_i915_gem_object_ops *ops = obj->ops; @@ -1865,6 +1845,11 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj) if (obj->pages) return 0; + if (obj->madv != I915_MADV_WILLNEED) { + DRM_ERROR("Attempting to obtain a purgeable object\n"); + return -EINVAL; + } + BUG_ON(obj->pages_pin_count); ret = ops->get_pages(obj); @@ -1921,9 +1906,6 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj) BUG_ON(obj->base.write_domain & ~I915_GEM_GPU_DOMAINS); BUG_ON(!obj->active); - if (obj->pin_count) /* are we a framebuffer? */ - intel_mark_fb_idle(obj); - list_move_tail(&obj->mm_list, &dev_priv->mm.inactive_list); list_del_init(&obj->ring_list); @@ -2075,7 +2057,7 @@ i915_add_request(struct intel_ring_buffer *ring, if (!dev_priv->mm.suspended) { if (i915_enable_hangcheck) { - mod_timer(&dev_priv->hangcheck_timer, + mod_timer(&dev_priv->gpu_error.hangcheck_timer, round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES)); } if (was_empty) { @@ -2340,10 +2322,12 @@ i915_gem_object_flush_active(struct drm_i915_gem_object *obj) int i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { + drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_gem_wait *args = data; struct drm_i915_gem_object *obj; struct intel_ring_buffer *ring = NULL; struct timespec timeout_stack, *timeout = NULL; + unsigned reset_counter; u32 seqno = 0; int ret = 0; @@ -2384,9 +2368,10 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) } drm_gem_object_unreference(&obj->base); + reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter); mutex_unlock(&dev->struct_mutex); - ret = __wait_seqno(ring, seqno, true, timeout); + ret = __wait_seqno(ring, seqno, reset_counter, true, timeout); if (timeout) { WARN_ON(!timespec_valid(timeout)); args->timeout_ns = timespec_to_ns(timeout); @@ -2450,15 +2435,15 @@ static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj) { u32 old_write_domain, old_read_domains; - /* Act a barrier for all accesses through the GTT */ - mb(); - /* Force a pagefault for domain tracking on next user access */ i915_gem_release_mmap(obj); if ((obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0) return; + /* Wait for any direct GTT access to complete */ + mb(); + old_read_domains = obj->base.read_domains; old_write_domain = obj->base.write_domain; @@ -2477,7 +2462,7 @@ 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; + int ret; if (obj->gtt_space == NULL) return 0; @@ -2544,52 +2529,38 @@ int i915_gpu_idle(struct drm_device *dev) return 0; } -static void sandybridge_write_fence_reg(struct drm_device *dev, int reg, - struct drm_i915_gem_object *obj) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - uint64_t val; - - if (obj) { - u32 size = obj->gtt_space->size; - - val = (uint64_t)((obj->gtt_offset + size - 4096) & - 0xfffff000) << 32; - val |= obj->gtt_offset & 0xfffff000; - val |= (uint64_t)((obj->stride / 128) - 1) << - SANDYBRIDGE_FENCE_PITCH_SHIFT; - - if (obj->tiling_mode == I915_TILING_Y) - val |= 1 << I965_FENCE_TILING_Y_SHIFT; - val |= I965_FENCE_REG_VALID; - } else - val = 0; - - I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + reg * 8, val); - POSTING_READ(FENCE_REG_SANDYBRIDGE_0 + reg * 8); -} - static void i965_write_fence_reg(struct drm_device *dev, int reg, struct drm_i915_gem_object *obj) { drm_i915_private_t *dev_priv = dev->dev_private; + int fence_reg; + int fence_pitch_shift; uint64_t val; + if (INTEL_INFO(dev)->gen >= 6) { + fence_reg = FENCE_REG_SANDYBRIDGE_0; + fence_pitch_shift = SANDYBRIDGE_FENCE_PITCH_SHIFT; + } else { + fence_reg = FENCE_REG_965_0; + fence_pitch_shift = I965_FENCE_PITCH_SHIFT; + } + if (obj) { u32 size = obj->gtt_space->size; val = (uint64_t)((obj->gtt_offset + size - 4096) & 0xfffff000) << 32; val |= obj->gtt_offset & 0xfffff000; - val |= ((obj->stride / 128) - 1) << I965_FENCE_PITCH_SHIFT; + val |= (uint64_t)((obj->stride / 128) - 1) << fence_pitch_shift; if (obj->tiling_mode == I915_TILING_Y) val |= 1 << I965_FENCE_TILING_Y_SHIFT; val |= I965_FENCE_REG_VALID; } else val = 0; - I915_WRITE64(FENCE_REG_965_0 + reg * 8, val); - POSTING_READ(FENCE_REG_965_0 + reg * 8); + fence_reg += reg * 8; + I915_WRITE64(fence_reg, val); + POSTING_READ(fence_reg); } static void i915_write_fence_reg(struct drm_device *dev, int reg, @@ -2668,18 +2639,37 @@ static void i830_write_fence_reg(struct drm_device *dev, int reg, POSTING_READ(FENCE_REG_830_0 + reg * 4); } +inline static bool i915_gem_object_needs_mb(struct drm_i915_gem_object *obj) +{ + return obj && obj->base.read_domains & I915_GEM_DOMAIN_GTT; +} + static void i915_gem_write_fence(struct drm_device *dev, int reg, struct drm_i915_gem_object *obj) { + struct drm_i915_private *dev_priv = dev->dev_private; + + /* Ensure that all CPU reads are completed before installing a fence + * and all writes before removing the fence. + */ + if (i915_gem_object_needs_mb(dev_priv->fence_regs[reg].obj)) + mb(); + switch (INTEL_INFO(dev)->gen) { case 7: - case 6: sandybridge_write_fence_reg(dev, reg, obj); break; + case 6: case 5: case 4: i965_write_fence_reg(dev, reg, obj); break; case 3: i915_write_fence_reg(dev, reg, obj); break; case 2: i830_write_fence_reg(dev, reg, obj); break; default: BUG(); } + + /* And similarly be paranoid that no direct access to this region + * is reordered to before the fence is installed. + */ + if (i915_gem_object_needs_mb(obj)) + mb(); } static inline int fence_number(struct drm_i915_private *dev_priv, @@ -2709,7 +2699,7 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj, } static int -i915_gem_object_flush_fence(struct drm_i915_gem_object *obj) +i915_gem_object_wait_fence(struct drm_i915_gem_object *obj) { if (obj->last_fenced_seqno) { int ret = i915_wait_seqno(obj->ring, obj->last_fenced_seqno); @@ -2719,12 +2709,6 @@ i915_gem_object_flush_fence(struct drm_i915_gem_object *obj) obj->last_fenced_seqno = 0; } - /* Ensure that all CPU reads are completed before installing a fence - * and all writes before removing the fence. - */ - if (obj->base.read_domains & I915_GEM_DOMAIN_GTT) - mb(); - obj->fenced_gpu_access = false; return 0; } @@ -2735,7 +2719,7 @@ i915_gem_object_put_fence(struct drm_i915_gem_object *obj) struct drm_i915_private *dev_priv = obj->base.dev->dev_private; int ret; - ret = i915_gem_object_flush_fence(obj); + ret = i915_gem_object_wait_fence(obj); if (ret) return ret; @@ -2809,7 +2793,7 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj) * will need to serialise the write to the associated fence register? */ if (obj->fence_dirty) { - ret = i915_gem_object_flush_fence(obj); + ret = i915_gem_object_wait_fence(obj); if (ret) return ret; } @@ -2830,7 +2814,7 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj) if (reg->obj) { struct drm_i915_gem_object *old = reg->obj; - ret = i915_gem_object_flush_fence(old); + ret = i915_gem_object_wait_fence(old); if (ret) return ret; @@ -2931,21 +2915,16 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, bool mappable, fenceable; int ret; - if (obj->madv != I915_MADV_WILLNEED) { - DRM_ERROR("Attempting to bind a purgeable object\n"); - return -EINVAL; - } - fence_size = i915_gem_get_gtt_size(dev, obj->base.size, obj->tiling_mode); fence_alignment = i915_gem_get_gtt_alignment(dev, obj->base.size, - obj->tiling_mode); + obj->tiling_mode, true); unfenced_alignment = - i915_gem_get_unfenced_gtt_alignment(dev, + i915_gem_get_gtt_alignment(dev, obj->base.size, - obj->tiling_mode); + obj->tiling_mode, false); if (alignment == 0) alignment = map_and_fenceable ? fence_alignment : @@ -2961,7 +2940,7 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, * before evicting everything in a vain attempt to find space. */ if (obj->base.size > - (map_and_fenceable ? dev_priv->mm.gtt_mappable_end : dev_priv->mm.gtt_total)) { + (map_and_fenceable ? dev_priv->gtt.mappable_end : dev_priv->gtt.total)) { DRM_ERROR("Attempting to bind an object larger than the aperture\n"); return -E2BIG; } @@ -2982,7 +2961,7 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, if (map_and_fenceable) ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node, size, alignment, obj->cache_level, - 0, dev_priv->mm.gtt_mappable_end); + 0, dev_priv->gtt.mappable_end); else ret = drm_mm_insert_node_generic(&dev_priv->mm.gtt_space, node, size, alignment, obj->cache_level); @@ -3022,7 +3001,7 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, (node->start & (fence_alignment - 1)) == 0; mappable = - obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end; + obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end; obj->map_and_fenceable = mappable && fenceable; @@ -3130,6 +3109,13 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) i915_gem_object_flush_cpu_write_domain(obj); + /* Serialise direct access to this object with the barriers for + * coherent writes from the GPU, by effectively invalidating the + * GTT domain upon first access. + */ + if ((obj->base.read_domains & I915_GEM_DOMAIN_GTT) == 0) + mb(); + old_write_domain = obj->base.write_domain; old_read_domains = obj->base.read_domains; @@ -3436,11 +3422,17 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file) unsigned long recent_enough = jiffies - msecs_to_jiffies(20); struct drm_i915_gem_request *request; struct intel_ring_buffer *ring = NULL; + unsigned reset_counter; u32 seqno = 0; int ret; - if (atomic_read(&dev_priv->mm.wedged)) - return -EIO; + ret = i915_gem_wait_for_error(&dev_priv->gpu_error); + if (ret) + return ret; + + ret = i915_gem_check_wedge(&dev_priv->gpu_error, false); + if (ret) + return ret; spin_lock(&file_priv->mm.lock); list_for_each_entry(request, &file_priv->mm.request_list, client_list) { @@ -3450,12 +3442,13 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file) ring = request->ring; seqno = request->seqno; } + reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter); spin_unlock(&file_priv->mm.lock); if (seqno == 0) return 0; - ret = __wait_seqno(ring, seqno, true, NULL); + ret = __wait_seqno(ring, seqno, reset_counter, true, NULL); if (ret == 0) queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, 0); @@ -3853,7 +3846,7 @@ i915_gem_idle(struct drm_device *dev) * And not confound mm.suspended! */ dev_priv->mm.suspended = 1; - del_timer_sync(&dev_priv->hangcheck_timer); + del_timer_sync(&dev_priv->gpu_error.hangcheck_timer); i915_kernel_lost_context(dev); i915_gem_cleanup_ringbuffer(dev); @@ -3953,8 +3946,6 @@ i915_gem_init_hw(struct drm_device *dev) i915_gem_init_swizzling(dev); - dev_priv->next_seqno = dev_priv->last_seqno = (u32)~0 - 0x1000; - ret = intel_init_render_ring_buffer(dev); if (ret) return ret; @@ -3971,6 +3962,10 @@ i915_gem_init_hw(struct drm_device *dev) goto cleanup_bsd_ring; } + ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000)); + if (ret) + return ret; + /* * XXX: There was some w/a described somewhere suggesting loading * contexts before PPGTT. @@ -4028,9 +4023,9 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, if (drm_core_check_feature(dev, DRIVER_MODESET)) return 0; - if (atomic_read(&dev_priv->mm.wedged)) { + if (i915_reset_in_progress(&dev_priv->gpu_error)) { DRM_ERROR("Reenabling wedged hardware, good luck\n"); - atomic_set(&dev_priv->mm.wedged, 0); + atomic_set(&dev_priv->gpu_error.reset_counter, 0); } mutex_lock(&dev->struct_mutex); @@ -4114,7 +4109,7 @@ i915_gem_load(struct drm_device *dev) INIT_LIST_HEAD(&dev_priv->fence_regs[i].lru_list); INIT_DELAYED_WORK(&dev_priv->mm.retire_work, i915_gem_retire_work_handler); - init_completion(&dev_priv->error_completion); + init_waitqueue_head(&dev_priv->gpu_error.reset_queue); /* On GEN3 we really need to make sure the ARB C3 LP bit is set */ if (IS_GEN3(dev)) { diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 776a3225184c..c86d5d9356fd 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -80,7 +80,7 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, if (mappable) drm_mm_init_scan_with_range(&dev_priv->mm.gtt_space, min_size, alignment, cache_level, - 0, dev_priv->mm.gtt_mappable_end); + 0, dev_priv->gtt.mappable_end); else drm_mm_init_scan(&dev_priv->mm.gtt_space, min_size, alignment, cache_level); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 163bb52bd3b3..27269103b621 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -34,61 +34,133 @@ #include <linux/dma_remapping.h> struct eb_objects { + struct list_head objects; int and; - struct hlist_head buckets[0]; + union { + struct drm_i915_gem_object *lut[0]; + struct hlist_head buckets[0]; + }; }; static struct eb_objects * -eb_create(int size) +eb_create(struct drm_i915_gem_execbuffer2 *args) { - struct eb_objects *eb; - int count = PAGE_SIZE / sizeof(struct hlist_head) / 2; - BUILD_BUG_ON(!is_power_of_2(PAGE_SIZE / sizeof(struct hlist_head))); - while (count > size) - count >>= 1; - eb = kzalloc(count*sizeof(struct hlist_head) + - sizeof(struct eb_objects), - GFP_KERNEL); - if (eb == NULL) - return eb; - - eb->and = count - 1; + struct eb_objects *eb = NULL; + + if (args->flags & I915_EXEC_HANDLE_LUT) { + int size = args->buffer_count; + size *= sizeof(struct drm_i915_gem_object *); + size += sizeof(struct eb_objects); + eb = kmalloc(size, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); + } + + if (eb == NULL) { + int size = args->buffer_count; + int count = PAGE_SIZE / sizeof(struct hlist_head) / 2; + BUILD_BUG_ON(!is_power_of_2(PAGE_SIZE / sizeof(struct hlist_head))); + while (count > 2*size) + count >>= 1; + eb = kzalloc(count*sizeof(struct hlist_head) + + sizeof(struct eb_objects), + GFP_TEMPORARY); + if (eb == NULL) + return eb; + + eb->and = count - 1; + } else + eb->and = -args->buffer_count; + + INIT_LIST_HEAD(&eb->objects); return eb; } static void eb_reset(struct eb_objects *eb) { - memset(eb->buckets, 0, (eb->and+1)*sizeof(struct hlist_head)); + if (eb->and >= 0) + memset(eb->buckets, 0, (eb->and+1)*sizeof(struct hlist_head)); } -static void -eb_add_object(struct eb_objects *eb, struct drm_i915_gem_object *obj) +static int +eb_lookup_objects(struct eb_objects *eb, + struct drm_i915_gem_exec_object2 *exec, + const struct drm_i915_gem_execbuffer2 *args, + struct drm_file *file) { - hlist_add_head(&obj->exec_node, - &eb->buckets[obj->exec_handle & eb->and]); + int i; + + spin_lock(&file->table_lock); + for (i = 0; i < args->buffer_count; i++) { + struct drm_i915_gem_object *obj; + + obj = to_intel_bo(idr_find(&file->object_idr, exec[i].handle)); + if (obj == NULL) { + spin_unlock(&file->table_lock); + DRM_DEBUG("Invalid object handle %d at index %d\n", + exec[i].handle, i); + return -ENOENT; + } + + if (!list_empty(&obj->exec_list)) { + spin_unlock(&file->table_lock); + DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n", + obj, exec[i].handle, i); + return -EINVAL; + } + + drm_gem_object_reference(&obj->base); + list_add_tail(&obj->exec_list, &eb->objects); + + obj->exec_entry = &exec[i]; + if (eb->and < 0) { + eb->lut[i] = obj; + } else { + uint32_t handle = args->flags & I915_EXEC_HANDLE_LUT ? i : exec[i].handle; + obj->exec_handle = handle; + hlist_add_head(&obj->exec_node, + &eb->buckets[handle & eb->and]); + } + } + spin_unlock(&file->table_lock); + + return 0; } static struct drm_i915_gem_object * eb_get_object(struct eb_objects *eb, unsigned long handle) { - struct hlist_head *head; - struct hlist_node *node; - struct drm_i915_gem_object *obj; + if (eb->and < 0) { + if (handle >= -eb->and) + return NULL; + return eb->lut[handle]; + } else { + struct hlist_head *head; + struct hlist_node *node; - head = &eb->buckets[handle & eb->and]; - hlist_for_each(node, head) { - obj = hlist_entry(node, struct drm_i915_gem_object, exec_node); - if (obj->exec_handle == handle) - return obj; - } + head = &eb->buckets[handle & eb->and]; + hlist_for_each(node, head) { + struct drm_i915_gem_object *obj; - return NULL; + obj = hlist_entry(node, struct drm_i915_gem_object, exec_node); + if (obj->exec_handle == handle) + return obj; + } + return NULL; + } } static void eb_destroy(struct eb_objects *eb) { + while (!list_empty(&eb->objects)) { + struct drm_i915_gem_object *obj; + + obj = list_first_entry(&eb->objects, + struct drm_i915_gem_object, + exec_list); + list_del_init(&obj->exec_list); + drm_gem_object_unreference(&obj->base); + } kfree(eb); } @@ -209,7 +281,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, /* Map the page containing the relocation we're going to perform. */ reloc->offset += obj->gtt_offset; - reloc_page = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, + reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable, reloc->offset & PAGE_MASK); reloc_entry = (uint32_t __iomem *) (reloc_page + (reloc->offset & ~PAGE_MASK)); @@ -288,8 +360,7 @@ i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj, static int i915_gem_execbuffer_relocate(struct drm_device *dev, - struct eb_objects *eb, - struct list_head *objects) + struct eb_objects *eb) { struct drm_i915_gem_object *obj; int ret = 0; @@ -302,7 +373,7 @@ i915_gem_execbuffer_relocate(struct drm_device *dev, * lockdep complains vehemently. */ pagefault_disable(); - list_for_each_entry(obj, objects, exec_list) { + list_for_each_entry(obj, &eb->objects, exec_list) { ret = i915_gem_execbuffer_relocate_object(obj, eb); if (ret) break; @@ -324,7 +395,8 @@ need_reloc_mappable(struct drm_i915_gem_object *obj) static int i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring) + struct intel_ring_buffer *ring, + bool *need_reloc) { struct drm_i915_private *dev_priv = obj->base.dev->dev_private; struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; @@ -365,7 +437,20 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, obj->has_aliasing_ppgtt_mapping = 1; } - entry->offset = obj->gtt_offset; + if (entry->offset != obj->gtt_offset) { + entry->offset = obj->gtt_offset; + *need_reloc = true; + } + + if (entry->flags & EXEC_OBJECT_WRITE) { + obj->base.pending_read_domains = I915_GEM_DOMAIN_RENDER; + obj->base.pending_write_domain = I915_GEM_DOMAIN_RENDER; + } + + if (entry->flags & EXEC_OBJECT_NEEDS_GTT && + !obj->has_global_gtt_mapping) + i915_gem_gtt_bind_object(obj, obj->cache_level); + return 0; } @@ -391,7 +476,8 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj) static int i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, struct drm_file *file, - struct list_head *objects) + struct list_head *objects, + bool *need_relocs) { struct drm_i915_gem_object *obj; struct list_head ordered_objects; @@ -419,7 +505,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, else list_move_tail(&obj->exec_list, &ordered_objects); - obj->base.pending_read_domains = 0; + obj->base.pending_read_domains = I915_GEM_GPU_DOMAINS & ~I915_GEM_DOMAIN_COMMAND; obj->base.pending_write_domain = 0; obj->pending_fenced_gpu_access = false; } @@ -459,7 +545,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, (need_mappable && !obj->map_and_fenceable)) ret = i915_gem_object_unbind(obj); else - ret = i915_gem_execbuffer_reserve_object(obj, ring); + ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs); if (ret) goto err; } @@ -469,7 +555,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, if (obj->gtt_space) continue; - ret = i915_gem_execbuffer_reserve_object(obj, ring); + ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs); if (ret) goto err; } @@ -489,21 +575,22 @@ err: /* Decrement pin count for bound objects */ static int i915_gem_execbuffer_relocate_slow(struct drm_device *dev, + struct drm_i915_gem_execbuffer2 *args, struct drm_file *file, struct intel_ring_buffer *ring, - struct list_head *objects, struct eb_objects *eb, - struct drm_i915_gem_exec_object2 *exec, - int count) + struct drm_i915_gem_exec_object2 *exec) { struct drm_i915_gem_relocation_entry *reloc; struct drm_i915_gem_object *obj; + bool need_relocs; int *reloc_offset; int i, total, ret; + int count = args->buffer_count; /* We may process another execbuffer during the unlock... */ - while (!list_empty(objects)) { - obj = list_first_entry(objects, + while (!list_empty(&eb->objects)) { + obj = list_first_entry(&eb->objects, struct drm_i915_gem_object, exec_list); list_del_init(&obj->exec_list); @@ -550,27 +637,16 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, /* reacquire the objects */ eb_reset(eb); - for (i = 0; i < count; i++) { - obj = to_intel_bo(drm_gem_object_lookup(dev, file, - exec[i].handle)); - if (&obj->base == NULL) { - DRM_DEBUG("Invalid object handle %d at index %d\n", - exec[i].handle, i); - ret = -ENOENT; - goto err; - } - - list_add_tail(&obj->exec_list, objects); - obj->exec_handle = exec[i].handle; - obj->exec_entry = &exec[i]; - eb_add_object(eb, obj); - } + ret = eb_lookup_objects(eb, exec, args, file); + if (ret) + goto err; - ret = i915_gem_execbuffer_reserve(ring, file, objects); + need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; + ret = i915_gem_execbuffer_reserve(ring, file, &eb->objects, &need_relocs); if (ret) goto err; - list_for_each_entry(obj, objects, exec_list) { + list_for_each_entry(obj, &eb->objects, exec_list) { int offset = obj->exec_entry - exec; ret = i915_gem_execbuffer_relocate_object_slow(obj, eb, reloc + reloc_offset[offset]); @@ -624,6 +700,9 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring, static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec) { + if (exec->flags & __I915_EXEC_UNKNOWN_FLAGS) + return false; + return ((exec->batch_start_offset | exec->batch_len) & 0x7) == 0; } @@ -637,6 +716,9 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, char __user *ptr = (char __user *)(uintptr_t)exec[i].relocs_ptr; int length; /* limited by fault_in_pages_readable() */ + if (exec[i].flags & __EXEC_OBJECT_UNKNOWN_FLAGS) + return -EINVAL; + /* First check for malicious input causing overflow */ if (exec[i].relocation_count > INT_MAX / sizeof(struct drm_i915_gem_relocation_entry)) @@ -644,9 +726,6 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, length = exec[i].relocation_count * sizeof(struct drm_i915_gem_relocation_entry); - if (!access_ok(VERIFY_READ, ptr, length)) - return -EFAULT; - /* we may also need to update the presumed offsets */ if (!access_ok(VERIFY_WRITE, ptr, length)) return -EFAULT; @@ -668,8 +747,10 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects, u32 old_read = obj->base.read_domains; u32 old_write = obj->base.write_domain; - obj->base.read_domains = obj->base.pending_read_domains; obj->base.write_domain = obj->base.pending_write_domain; + if (obj->base.write_domain == 0) + obj->base.pending_read_domains |= obj->base.read_domains; + obj->base.read_domains = obj->base.pending_read_domains; obj->fenced_gpu_access = obj->pending_fenced_gpu_access; i915_gem_object_move_to_active(obj, ring); @@ -728,21 +809,18 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct drm_i915_gem_exec_object2 *exec) { drm_i915_private_t *dev_priv = dev->dev_private; - struct list_head objects; struct eb_objects *eb; struct drm_i915_gem_object *batch_obj; struct drm_clip_rect *cliprects = NULL; struct intel_ring_buffer *ring; u32 ctx_id = i915_execbuffer2_get_context_id(*args); u32 exec_start, exec_len; - u32 mask; - u32 flags; + u32 mask, flags; int ret, mode, i; + bool need_relocs; - if (!i915_gem_check_execbuffer(args)) { - DRM_DEBUG("execbuf with invalid offset/length\n"); + if (!i915_gem_check_execbuffer(args)) return -EINVAL; - } ret = validate_exec_list(exec, args->buffer_count); if (ret) @@ -863,7 +941,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto pre_mutex_err; } - eb = eb_create(args->buffer_count); + eb = eb_create(args); if (eb == NULL) { mutex_unlock(&dev->struct_mutex); ret = -ENOMEM; @@ -871,51 +949,28 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } /* Look up object handles */ - INIT_LIST_HEAD(&objects); - for (i = 0; i < args->buffer_count; i++) { - struct drm_i915_gem_object *obj; - - obj = to_intel_bo(drm_gem_object_lookup(dev, file, - exec[i].handle)); - if (&obj->base == NULL) { - DRM_DEBUG("Invalid object handle %d at index %d\n", - exec[i].handle, i); - /* prevent error path from reading uninitialized data */ - ret = -ENOENT; - goto err; - } - - if (!list_empty(&obj->exec_list)) { - 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; - } - - list_add_tail(&obj->exec_list, &objects); - obj->exec_handle = exec[i].handle; - obj->exec_entry = &exec[i]; - eb_add_object(eb, obj); - } + ret = eb_lookup_objects(eb, exec, args, file); + if (ret) + goto err; /* take note of the batch buffer before we might reorder the lists */ - batch_obj = list_entry(objects.prev, + batch_obj = list_entry(eb->objects.prev, struct drm_i915_gem_object, exec_list); /* Move the objects en-masse into the GTT, evicting if necessary. */ - ret = i915_gem_execbuffer_reserve(ring, file, &objects); + need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; + ret = i915_gem_execbuffer_reserve(ring, file, &eb->objects, &need_relocs); if (ret) goto err; /* The objects are in their final locations, apply the relocations. */ - ret = i915_gem_execbuffer_relocate(dev, eb, &objects); + if (need_relocs) + ret = i915_gem_execbuffer_relocate(dev, eb); if (ret) { if (ret == -EFAULT) { - ret = i915_gem_execbuffer_relocate_slow(dev, file, ring, - &objects, eb, - exec, - args->buffer_count); + ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring, + eb, exec); BUG_ON(!mutex_is_locked(&dev->struct_mutex)); } if (ret) @@ -937,7 +992,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if (flags & I915_DISPATCH_SECURE && !batch_obj->has_global_gtt_mapping) i915_gem_gtt_bind_object(batch_obj, batch_obj->cache_level); - ret = i915_gem_execbuffer_move_to_gpu(ring, &objects); + ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->objects); if (ret) goto err; @@ -991,20 +1046,11 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags); - i915_gem_execbuffer_move_to_active(&objects, ring); + i915_gem_execbuffer_move_to_active(&eb->objects, ring); i915_gem_execbuffer_retire_commands(dev, file, ring); err: eb_destroy(eb); - while (!list_empty(&objects)) { - struct drm_i915_gem_object *obj; - - obj = list_first_entry(&objects, - struct drm_i915_gem_object, - exec_list); - list_del_init(&obj->exec_list); - drm_gem_object_unreference(&obj->base); - } mutex_unlock(&dev->struct_mutex); @@ -1113,7 +1159,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, } exec2_list = kmalloc(sizeof(*exec2_list)*args->buffer_count, - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); if (exec2_list == NULL) exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index a4af0f79e972..bdaca3f47988 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -44,9 +44,9 @@ typedef uint32_t gtt_pte_t; #define GEN6_PTE_CACHE_LLC_MLC (3 << 1) #define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) -static inline gtt_pte_t pte_encode(struct drm_device *dev, - dma_addr_t addr, - enum i915_cache_level level) +static inline gtt_pte_t gen6_pte_encode(struct drm_device *dev, + dma_addr_t addr, + enum i915_cache_level level) { gtt_pte_t pte = GEN6_PTE_VALID; pte |= GEN6_PTE_ADDR_ENCODE(addr); @@ -77,7 +77,7 @@ static inline gtt_pte_t pte_encode(struct drm_device *dev, } /* PPGTT support for Sandybdrige/Gen6 and later */ -static void i915_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt, +static void gen6_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt, unsigned first_entry, unsigned num_entries) { @@ -87,8 +87,9 @@ static void i915_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt, unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; unsigned last_pte, i; - scratch_pte = pte_encode(ppgtt->dev, ppgtt->scratch_page_dma_addr, - I915_CACHE_LLC); + scratch_pte = gen6_pte_encode(ppgtt->dev, + ppgtt->scratch_page_dma_addr, + I915_CACHE_LLC); while (num_entries) { last_pte = first_pte + num_entries; @@ -108,10 +109,72 @@ static void i915_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt, } } -int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) +static void gen6_ppgtt_insert_entries(struct i915_hw_ppgtt *ppgtt, + struct sg_table *pages, + unsigned first_entry, + enum i915_cache_level cache_level) { + gtt_pte_t *pt_vaddr; + 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 = pages->sgl; + i = 0; + segment_len = sg_dma_len(sg) >> PAGE_SHIFT; + m = 0; + + while (i < pages->nents) { + 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); + pt_vaddr[j] = gen6_pte_encode(ppgtt->dev, page_addr, + cache_level); + + /* grab the next page */ + if (++m == segment_len) { + if (++i == pages->nents) + break; + + sg = sg_next(sg); + segment_len = sg_dma_len(sg) >> PAGE_SHIFT; + m = 0; + } + } + + kunmap_atomic(pt_vaddr); + + first_pte = 0; + act_pd++; + } +} + +static void gen6_ppgtt_cleanup(struct i915_hw_ppgtt *ppgtt) +{ + int i; + + if (ppgtt->pt_dma_addr) { + for (i = 0; i < ppgtt->num_pd_entries; i++) + pci_unmap_page(ppgtt->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 int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) +{ + struct drm_device *dev = ppgtt->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_ppgtt *ppgtt; unsigned first_pd_entry_in_global_pt; int i; int ret = -ENOMEM; @@ -119,18 +182,17 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) /* 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 = dev_priv->mm.gtt->gtt_total_entries - I915_PPGTT_PD_ENTRIES; + first_pd_entry_in_global_pt = + gtt_total_entries(dev_priv->gtt) - I915_PPGTT_PD_ENTRIES; - ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL); - if (!ppgtt) - return ret; - - ppgtt->dev = dev; ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES; + ppgtt->clear_range = gen6_ppgtt_clear_range; + ppgtt->insert_entries = gen6_ppgtt_insert_entries; + ppgtt->cleanup = gen6_ppgtt_cleanup; ppgtt->pt_pages = kzalloc(sizeof(struct page *)*ppgtt->num_pd_entries, GFP_KERNEL); if (!ppgtt->pt_pages) - goto err_ppgtt; + return -ENOMEM; for (i = 0; i < ppgtt->num_pd_entries; i++) { ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL); @@ -138,39 +200,32 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) 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; + ppgtt->pt_dma_addr = kzalloc(sizeof(dma_addr_t) *ppgtt->num_pd_entries, + GFP_KERNEL); + if (!ppgtt->pt_dma_addr) + goto err_pt_alloc; - for (i = 0; i < ppgtt->num_pd_entries; i++) { - dma_addr_t pt_addr; + for (i = 0; i < ppgtt->num_pd_entries; i++) { + dma_addr_t pt_addr; - pt_addr = pci_map_page(dev->pdev, ppgtt->pt_pages[i], - 0, 4096, - PCI_DMA_BIDIRECTIONAL); + 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; + if (pci_dma_mapping_error(dev->pdev, pt_addr)) { + ret = -EIO; + goto err_pd_pin; - } - ppgtt->pt_dma_addr[i] = pt_addr; } + ppgtt->pt_dma_addr[i] = pt_addr; } - ppgtt->scratch_page_dma_addr = dev_priv->mm.gtt->scratch_page_dma; + ppgtt->scratch_page_dma_addr = dev_priv->gtt.scratch_page_dma; - i915_ppgtt_clear_range(ppgtt, 0, - ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES); + ppgtt->clear_range(ppgtt, 0, + ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES); ppgtt->pd_offset = (first_pd_entry_in_global_pt)*sizeof(gtt_pte_t); - dev_priv->mm.aliasing_ppgtt = ppgtt; - return 0; err_pd_pin: @@ -186,94 +241,57 @@ err_pt_alloc: __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) +static int i915_gem_init_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; + struct i915_hw_ppgtt *ppgtt; + int ret; + ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL); if (!ppgtt) - return; + return -ENOMEM; - 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); - } + ppgtt->dev = dev; - 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); + ret = gen6_ppgtt_init(ppgtt); + if (ret) + kfree(ppgtt); + else + dev_priv->mm.aliasing_ppgtt = ppgtt; + + return ret; } -static void i915_ppgtt_insert_sg_entries(struct i915_hw_ppgtt *ppgtt, - const struct sg_table *pages, - unsigned first_entry, - enum i915_cache_level cache_level) +void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev) { - gtt_pte_t *pt_vaddr; - 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 = pages->sgl; - i = 0; - segment_len = sg_dma_len(sg) >> PAGE_SHIFT; - m = 0; - - while (i < pages->nents) { - 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); - pt_vaddr[j] = pte_encode(ppgtt->dev, page_addr, - cache_level); - - /* grab the next page */ - if (++m == segment_len) { - if (++i == pages->nents) - break; - - sg = sg_next(sg); - segment_len = sg_dma_len(sg) >> PAGE_SHIFT; - m = 0; - } - } + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; - kunmap_atomic(pt_vaddr); + if (!ppgtt) + return; - first_pte = 0; - act_pd++; - } + ppgtt->cleanup(ppgtt); } void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt, struct drm_i915_gem_object *obj, enum i915_cache_level cache_level) { - i915_ppgtt_insert_sg_entries(ppgtt, - obj->pages, - obj->gtt_space->start >> PAGE_SHIFT, - cache_level); + ppgtt->insert_entries(ppgtt, obj->pages, + obj->gtt_space->start >> PAGE_SHIFT, + cache_level); } 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); + ppgtt->clear_range(ppgtt, + obj->gtt_space->start >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT); } void i915_gem_init_ppgtt(struct drm_device *dev) @@ -290,15 +308,11 @@ void i915_gem_init_ppgtt(struct drm_device *dev) return; - pd_addr = (gtt_pte_t __iomem*)dev_priv->mm.gsm + ppgtt->pd_offset/sizeof(gtt_pte_t); + pd_addr = (gtt_pte_t __iomem*)dev_priv->gtt.gsm + ppgtt->pd_offset/sizeof(gtt_pte_t); for (i = 0; i < ppgtt->num_pd_entries; i++) { dma_addr_t pt_addr; - if (dev_priv->mm.gtt->needs_dmar) - pt_addr = ppgtt->pt_dma_addr[i]; - else - pt_addr = page_to_phys(ppgtt->pt_pages[i]); - + pt_addr = ppgtt->pt_dma_addr[i]; pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr); pd_entry |= GEN6_PDE_VALID; @@ -338,11 +352,27 @@ void i915_gem_init_ppgtt(struct drm_device *dev) } } +extern int intel_iommu_gfx_mapped; +/* Certain Gen5 chipsets require require idling the GPU before + * unmapping anything from the GTT when VT-d is enabled. + */ +static inline bool needs_idle_maps(struct drm_device *dev) +{ +#ifdef CONFIG_INTEL_IOMMU + /* Query intel_iommu to see if we need the workaround. Presumably that + * was loaded first. + */ + if (IS_GEN5(dev) && IS_MOBILE(dev) && intel_iommu_gfx_mapped) + return true; +#endif + return false; +} + static bool do_idling(struct drm_i915_private *dev_priv) { bool ret = dev_priv->mm.interruptible; - if (unlikely(dev_priv->mm.gtt->do_idle_maps)) { + if (unlikely(dev_priv->gtt.do_idle_maps)) { dev_priv->mm.interruptible = false; if (i915_gpu_idle(dev_priv->dev)) { DRM_ERROR("Couldn't idle GPU\n"); @@ -356,45 +386,18 @@ static bool do_idling(struct drm_i915_private *dev_priv) static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible) { - if (unlikely(dev_priv->mm.gtt->do_idle_maps)) + if (unlikely(dev_priv->gtt.do_idle_maps)) dev_priv->mm.interruptible = interruptible; } - -static void i915_ggtt_clear_range(struct drm_device *dev, - unsigned first_entry, - unsigned num_entries) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - gtt_pte_t scratch_pte; - gtt_pte_t __iomem *gtt_base = (gtt_pte_t __iomem *) dev_priv->mm.gsm + first_entry; - const int max_entries = dev_priv->mm.gtt->gtt_total_entries - first_entry; - int i; - - if (INTEL_INFO(dev)->gen < 6) { - intel_gtt_clear_range(first_entry, num_entries); - return; - } - - if (WARN(num_entries > max_entries, - "First entry = %d; Num entries = %d (max=%d)\n", - first_entry, num_entries, max_entries)) - num_entries = max_entries; - - scratch_pte = pte_encode(dev, dev_priv->mm.gtt->scratch_page_dma, I915_CACHE_LLC); - for (i = 0; i < num_entries; i++) - iowrite32(scratch_pte, >t_base[i]); - readl(gtt_base); -} - void i915_gem_restore_gtt_mappings(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; /* First fill our portion of the GTT with scratch pages */ - i915_ggtt_clear_range(dev, dev_priv->mm.gtt_start / PAGE_SIZE, - (dev_priv->mm.gtt_end - dev_priv->mm.gtt_start) / PAGE_SIZE); + dev_priv->gtt.gtt_clear_range(dev, dev_priv->gtt.start / PAGE_SIZE, + dev_priv->gtt.total / PAGE_SIZE); list_for_each_entry(obj, &dev_priv->mm.bound_list, gtt_list) { i915_gem_clflush_object(obj); @@ -423,17 +426,15 @@ int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj) * within the global GTT as well as accessible by the GPU through the GMADR * mapped BAR (dev_priv->mm.gtt->gtt). */ -static void gen6_ggtt_bind_object(struct drm_i915_gem_object *obj, - enum i915_cache_level level) +static void gen6_ggtt_insert_entries(struct drm_device *dev, + struct sg_table *st, + unsigned int first_entry, + enum i915_cache_level level) { - struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct sg_table *st = obj->pages; struct scatterlist *sg = st->sgl; - const int first_entry = obj->gtt_space->start >> PAGE_SHIFT; - const int max_entries = dev_priv->mm.gtt->gtt_total_entries - first_entry; gtt_pte_t __iomem *gtt_entries = - (gtt_pte_t __iomem *)dev_priv->mm.gsm + first_entry; + (gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry; int unused, i = 0; unsigned int len, m = 0; dma_addr_t addr; @@ -442,14 +443,12 @@ static void gen6_ggtt_bind_object(struct drm_i915_gem_object *obj, len = sg_dma_len(sg) >> PAGE_SHIFT; for (m = 0; m < len; m++) { addr = sg_dma_address(sg) + (m << PAGE_SHIFT); - iowrite32(pte_encode(dev, addr, level), >t_entries[i]); + iowrite32(gen6_pte_encode(dev, addr, level), + >t_entries[i]); i++; } } - BUG_ON(i > max_entries); - BUG_ON(i != obj->base.size / PAGE_SIZE); - /* XXX: This serves as a posting read to make sure that the PTE has * actually been updated. There is some concern that even though * registers and PTEs are within the same BAR that they are potentially @@ -457,7 +456,8 @@ static void gen6_ggtt_bind_object(struct drm_i915_gem_object *obj, * hardware should work, we must keep this posting read for paranoia. */ if (i != 0) - WARN_ON(readl(>t_entries[i-1]) != pte_encode(dev, addr, level)); + WARN_ON(readl(>t_entries[i-1]) + != gen6_pte_encode(dev, addr, level)); /* This next bit makes the above posting read even more important. We * want to flush the TLBs only after we're certain all the PTE updates @@ -467,28 +467,70 @@ static void gen6_ggtt_bind_object(struct drm_i915_gem_object *obj, POSTING_READ(GFX_FLSH_CNTL_GEN6); } +static void gen6_ggtt_clear_range(struct drm_device *dev, + unsigned int first_entry, + unsigned int num_entries) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + gtt_pte_t scratch_pte; + gtt_pte_t __iomem *gtt_base = (gtt_pte_t __iomem *) dev_priv->gtt.gsm + first_entry; + const int max_entries = gtt_total_entries(dev_priv->gtt) - first_entry; + int i; + + if (WARN(num_entries > max_entries, + "First entry = %d; Num entries = %d (max=%d)\n", + first_entry, num_entries, max_entries)) + num_entries = max_entries; + + scratch_pte = gen6_pte_encode(dev, dev_priv->gtt.scratch_page_dma, + I915_CACHE_LLC); + for (i = 0; i < num_entries; i++) + iowrite32(scratch_pte, >t_base[i]); + readl(gtt_base); +} + + +static void i915_ggtt_insert_entries(struct drm_device *dev, + struct sg_table *st, + unsigned int pg_start, + enum i915_cache_level cache_level) +{ + unsigned int flags = (cache_level == I915_CACHE_NONE) ? + AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY; + + intel_gtt_insert_sg_entries(st, pg_start, flags); + +} + +static void i915_ggtt_clear_range(struct drm_device *dev, + unsigned int first_entry, + unsigned int num_entries) +{ + intel_gtt_clear_range(first_entry, num_entries); +} + + void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level) { struct drm_device *dev = obj->base.dev; - if (INTEL_INFO(dev)->gen < 6) { - unsigned int flags = (cache_level == I915_CACHE_NONE) ? - AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY; - intel_gtt_insert_sg_entries(obj->pages, - obj->gtt_space->start >> PAGE_SHIFT, - flags); - } else { - gen6_ggtt_bind_object(obj, cache_level); - } + struct drm_i915_private *dev_priv = dev->dev_private; + + dev_priv->gtt.gtt_insert_entries(dev, obj->pages, + obj->gtt_space->start >> PAGE_SHIFT, + cache_level); obj->has_global_gtt_mapping = 1; } void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj) { - i915_ggtt_clear_range(obj->base.dev, - obj->gtt_space->start >> PAGE_SHIFT, - obj->base.size >> PAGE_SHIFT); + struct drm_device *dev = obj->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + dev_priv->gtt.gtt_clear_range(obj->base.dev, + obj->gtt_space->start >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT); obj->has_global_gtt_mapping = 0; } @@ -525,17 +567,27 @@ static void i915_gtt_color_adjust(struct drm_mm_node *node, *end -= 4096; } } - void i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start, unsigned long mappable_end, unsigned long end) { + /* 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. + */ drm_i915_private_t *dev_priv = dev->dev_private; struct drm_mm_node *entry; struct drm_i915_gem_object *obj; unsigned long hole_start, hole_end; + BUG_ON(mappable_end > end); + /* Subtract the guard page ... */ drm_mm_init(&dev_priv->mm.gtt_space, start, end - start - PAGE_SIZE); if (!HAS_LLC(dev)) @@ -554,24 +606,20 @@ void i915_gem_setup_global_gtt(struct drm_device *dev, obj->has_global_gtt_mapping = 1; } - dev_priv->mm.gtt_start = start; - dev_priv->mm.gtt_mappable_end = mappable_end; - dev_priv->mm.gtt_end = end; - dev_priv->mm.gtt_total = end - start; - dev_priv->mm.mappable_gtt_total = min(end, mappable_end) - start; + dev_priv->gtt.start = start; + dev_priv->gtt.total = end - start; /* Clear any non-preallocated blocks */ drm_mm_for_each_hole(entry, &dev_priv->mm.gtt_space, hole_start, hole_end) { DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n", hole_start, hole_end); - i915_ggtt_clear_range(dev, - hole_start / PAGE_SIZE, - (hole_end-hole_start) / PAGE_SIZE); + dev_priv->gtt.gtt_clear_range(dev, hole_start / PAGE_SIZE, + (hole_end-hole_start) / PAGE_SIZE); } /* And finally clear the reserved guard page */ - i915_ggtt_clear_range(dev, end / PAGE_SIZE - 1, 1); + dev_priv->gtt.gtt_clear_range(dev, end / PAGE_SIZE - 1, 1); } static bool @@ -593,12 +641,12 @@ void i915_gem_init_global_gtt(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; unsigned long gtt_size, mappable_size; - int ret; - gtt_size = dev_priv->mm.gtt->gtt_total_entries << PAGE_SHIFT; - mappable_size = dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; + gtt_size = dev_priv->gtt.total; + mappable_size = dev_priv->gtt.mappable_end; if (intel_enable_ppgtt(dev) && HAS_ALIASING_PPGTT(dev)) { + int ret; /* 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; @@ -606,23 +654,14 @@ void i915_gem_init_global_gtt(struct drm_device *dev) i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size); ret = i915_gem_init_aliasing_ppgtt(dev); - if (ret) { - mutex_unlock(&dev->struct_mutex); + if (!ret) return; - } - } 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_setup_global_gtt(dev, 0, mappable_size, gtt_size); + + DRM_ERROR("Aliased PPGTT setup failed %d\n", ret); + drm_mm_takedown(&dev_priv->mm.gtt_space); + gtt_size += I915_PPGTT_PD_ENTRIES*PAGE_SIZE; } + i915_gem_setup_global_gtt(dev, 0, mappable_size, gtt_size); } static int setup_scratch_page(struct drm_device *dev) @@ -645,8 +684,8 @@ static int setup_scratch_page(struct drm_device *dev) #else dma_addr = page_to_phys(page); #endif - dev_priv->mm.gtt->scratch_page = page; - dev_priv->mm.gtt->scratch_page_dma = dma_addr; + dev_priv->gtt.scratch_page = page; + dev_priv->gtt.scratch_page_dma = dma_addr; return 0; } @@ -654,11 +693,11 @@ static int setup_scratch_page(struct drm_device *dev) static void teardown_scratch_page(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - set_pages_wb(dev_priv->mm.gtt->scratch_page, 1); - pci_unmap_page(dev->pdev, dev_priv->mm.gtt->scratch_page_dma, + set_pages_wb(dev_priv->gtt.scratch_page, 1); + pci_unmap_page(dev->pdev, dev_priv->gtt.scratch_page_dma, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); - put_page(dev_priv->mm.gtt->scratch_page); - __free_page(dev_priv->mm.gtt->scratch_page); + put_page(dev_priv->gtt.scratch_page); + __free_page(dev_priv->gtt.scratch_page); } static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl) @@ -668,14 +707,14 @@ static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl) return snb_gmch_ctl << 20; } -static inline unsigned int gen6_get_stolen_size(u16 snb_gmch_ctl) +static inline size_t gen6_get_stolen_size(u16 snb_gmch_ctl) { snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT; snb_gmch_ctl &= SNB_GMCH_GMS_MASK; return snb_gmch_ctl << 25; /* 32 MB units */ } -static inline unsigned int gen7_get_stolen_size(u16 snb_gmch_ctl) +static inline size_t gen7_get_stolen_size(u16 snb_gmch_ctl) { static const int stolen_decoder[] = { 0, 0, 0, 0, 0, 32, 48, 64, 128, 256, 96, 160, 224, 352}; @@ -684,103 +723,122 @@ static inline unsigned int gen7_get_stolen_size(u16 snb_gmch_ctl) return stolen_decoder[snb_gmch_ctl] << 20; } -int i915_gem_gtt_init(struct drm_device *dev) +static int gen6_gmch_probe(struct drm_device *dev, + size_t *gtt_total, + size_t *stolen) { struct drm_i915_private *dev_priv = dev->dev_private; phys_addr_t gtt_bus_addr; + unsigned int gtt_size; u16 snb_gmch_ctl; int ret; - /* On modern platforms we need not worry ourself with the legacy - * hostbridge query stuff. Skip it entirely + /* 64/512MB is the current min/max we actually know of, but this is just + * a coarse sanity check. */ - if (INTEL_INFO(dev)->gen < 6) { - ret = intel_gmch_probe(dev_priv->bridge_dev, dev->pdev, NULL); - if (!ret) { - DRM_ERROR("failed to set up gmch\n"); - return -EIO; - } - - dev_priv->mm.gtt = intel_gtt_get(); - if (!dev_priv->mm.gtt) { - DRM_ERROR("Failed to initialize GTT\n"); - intel_gmch_remove(); - return -ENODEV; - } - return 0; + if ((dev_priv->gtt.mappable_end < (64<<20) || + (dev_priv->gtt.mappable_end > (512<<20)))) { + DRM_ERROR("Unknown GMADR size (%lx)\n", + dev_priv->gtt.mappable_end); + return -ENXIO; } - dev_priv->mm.gtt = kzalloc(sizeof(*dev_priv->mm.gtt), GFP_KERNEL); - if (!dev_priv->mm.gtt) - return -ENOMEM; - if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(40))) pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(40)); + pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); + gtt_size = gen6_get_total_gtt_size(snb_gmch_ctl); -#ifdef CONFIG_INTEL_IOMMU - dev_priv->mm.gtt->needs_dmar = 1; -#endif + if (IS_GEN7(dev)) + *stolen = gen7_get_stolen_size(snb_gmch_ctl); + else + *stolen = gen6_get_stolen_size(snb_gmch_ctl); + + *gtt_total = (gtt_size / sizeof(gtt_pte_t)) << PAGE_SHIFT; /* For GEN6+ the PTEs for the ggtt live at 2MB + BAR0 */ gtt_bus_addr = pci_resource_start(dev->pdev, 0) + (2<<20); - dev_priv->mm.gtt->gma_bus_addr = pci_resource_start(dev->pdev, 2); - - /* i9xx_setup */ - pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); - dev_priv->mm.gtt->gtt_total_entries = - gen6_get_total_gtt_size(snb_gmch_ctl) / sizeof(gtt_pte_t); - if (INTEL_INFO(dev)->gen < 7) - dev_priv->mm.gtt->stolen_size = gen6_get_stolen_size(snb_gmch_ctl); - else - dev_priv->mm.gtt->stolen_size = gen7_get_stolen_size(snb_gmch_ctl); - - dev_priv->mm.gtt->gtt_mappable_entries = pci_resource_len(dev->pdev, 2) >> PAGE_SHIFT; - /* 64/512MB is the current min/max we actually know of, but this is just a - * coarse sanity check. - */ - if ((dev_priv->mm.gtt->gtt_mappable_entries >> 8) < 64 || - dev_priv->mm.gtt->gtt_mappable_entries > dev_priv->mm.gtt->gtt_total_entries) { - DRM_ERROR("Unknown GMADR entries (%d)\n", - dev_priv->mm.gtt->gtt_mappable_entries); - ret = -ENXIO; - goto err_out; + dev_priv->gtt.gsm = ioremap_wc(gtt_bus_addr, gtt_size); + if (!dev_priv->gtt.gsm) { + DRM_ERROR("Failed to map the gtt page table\n"); + return -ENOMEM; } ret = setup_scratch_page(dev); - if (ret) { + if (ret) DRM_ERROR("Scratch setup failed\n"); - goto err_out; - } - dev_priv->mm.gsm = ioremap_wc(gtt_bus_addr, - dev_priv->mm.gtt->gtt_total_entries * sizeof(gtt_pte_t)); - if (!dev_priv->mm.gsm) { - DRM_ERROR("Failed to map the gtt page table\n"); - teardown_scratch_page(dev); - ret = -ENOMEM; - goto err_out; + dev_priv->gtt.gtt_clear_range = gen6_ggtt_clear_range; + dev_priv->gtt.gtt_insert_entries = gen6_ggtt_insert_entries; + + return ret; +} + +static void gen6_gmch_remove(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + iounmap(dev_priv->gtt.gsm); + teardown_scratch_page(dev_priv->dev); +} + +static int i915_gmch_probe(struct drm_device *dev, + size_t *gtt_total, + size_t *stolen) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int ret; + + ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->dev->pdev, NULL); + if (!ret) { + DRM_ERROR("failed to set up gmch\n"); + return -EIO; } - /* GMADR is the PCI aperture used by SW to access tiled GFX surfaces in a linear fashion. */ - DRM_INFO("Memory usable by graphics device = %dM\n", dev_priv->mm.gtt->gtt_total_entries >> 8); - DRM_DEBUG_DRIVER("GMADR size = %dM\n", dev_priv->mm.gtt->gtt_mappable_entries >> 8); - DRM_DEBUG_DRIVER("GTT stolen size = %dM\n", dev_priv->mm.gtt->stolen_size >> 20); + intel_gtt_get(gtt_total, stolen); + + dev_priv->gtt.do_idle_maps = needs_idle_maps(dev_priv->dev); + dev_priv->gtt.gtt_clear_range = i915_ggtt_clear_range; + dev_priv->gtt.gtt_insert_entries = i915_ggtt_insert_entries; return 0; +} -err_out: - kfree(dev_priv->mm.gtt); - if (INTEL_INFO(dev)->gen < 6) - intel_gmch_remove(); - return ret; +static void i915_gmch_remove(struct drm_device *dev) +{ + intel_gmch_remove(); } -void i915_gem_gtt_fini(struct drm_device *dev) +int i915_gem_gtt_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - iounmap(dev_priv->mm.gsm); - teardown_scratch_page(dev); - if (INTEL_INFO(dev)->gen < 6) - intel_gmch_remove(); - kfree(dev_priv->mm.gtt); + struct i915_gtt *gtt = &dev_priv->gtt; + unsigned long gtt_size; + int ret; + + gtt->mappable_base = pci_resource_start(dev->pdev, 2); + gtt->mappable_end = pci_resource_len(dev->pdev, 2); + + if (INTEL_INFO(dev)->gen <= 5) { + dev_priv->gtt.gtt_probe = i915_gmch_probe; + dev_priv->gtt.gtt_remove = i915_gmch_remove; + } else { + dev_priv->gtt.gtt_probe = gen6_gmch_probe; + dev_priv->gtt.gtt_remove = gen6_gmch_remove; + } + + ret = dev_priv->gtt.gtt_probe(dev, &dev_priv->gtt.total, + &dev_priv->gtt.stolen_size); + if (ret) + return ret; + + gtt_size = (dev_priv->gtt.total >> PAGE_SHIFT) * sizeof(gtt_pte_t); + + /* GMADR is the PCI mmio aperture into the global GTT. */ + DRM_INFO("Memory usable by graphics device = %zdM\n", + dev_priv->gtt.total >> 20); + DRM_DEBUG_DRIVER("GMADR size = %ldM\n", + dev_priv->gtt.mappable_end >> 20); + DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", + dev_priv->gtt.stolen_size >> 20); + + return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index f21ae17e298f..69d97cbac13c 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -187,11 +187,11 @@ int i915_gem_init_stolen(struct drm_device *dev) if (dev_priv->mm.stolen_base == 0) return 0; - DRM_DEBUG_KMS("found %d bytes of stolen memory at %08lx\n", - dev_priv->mm.gtt->stolen_size, dev_priv->mm.stolen_base); + DRM_DEBUG_KMS("found %zd bytes of stolen memory at %08lx\n", + dev_priv->gtt.stolen_size, dev_priv->mm.stolen_base); /* Basic memrange allocator for stolen space */ - drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->mm.gtt->stolen_size); + drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->gtt.stolen_size); return 0; } @@ -205,7 +205,7 @@ i915_pages_create_for_stolen(struct drm_device *dev, struct scatterlist *sg; DRM_DEBUG_DRIVER("offset=0x%x, size=%d\n", offset, size); - BUG_ON(offset > dev_priv->mm.gtt->stolen_size - size); + BUG_ON(offset > dev_priv->gtt.stolen_size - size); /* We hide that we have no struct page backing our stolen object * by wrapping the contiguous physical allocation with a fake diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 65f1d4f3f775..abcba2f5a788 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -272,18 +272,7 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode) return false; } - /* - * Previous chips need to be aligned to the size of the smallest - * fence register that can contain the object. - */ - if (INTEL_INFO(obj->base.dev)->gen == 3) - size = 1024*1024; - else - size = 512*1024; - - while (size < obj->base.size) - size <<= 1; - + size = i915_gem_get_gtt_size(obj->base.dev, obj->base.size, tiling_mode); if (obj->gtt_space->size != size) return false; @@ -368,15 +357,15 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, obj->map_and_fenceable = obj->gtt_space == NULL || - (obj->gtt_offset + obj->base.size <= dev_priv->mm.gtt_mappable_end && + (obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end && i915_gem_object_fence_ok(obj, args->tiling_mode)); /* Rebind if we need a change of alignment */ if (!obj->map_and_fenceable) { u32 unfenced_alignment = - i915_gem_get_unfenced_gtt_alignment(dev, - obj->base.size, - args->tiling_mode); + i915_gem_get_gtt_alignment(dev, obj->base.size, + args->tiling_mode, + false); if (obj->gtt_offset & (unfenced_alignment - 1)) ret = i915_gem_object_unbind(obj); } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 6689a61b02a3..5648d846cdbf 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -356,8 +356,8 @@ static void notify_ring(struct drm_device *dev, wake_up_all(&ring->irq_queue); if (i915_enable_hangcheck) { - dev_priv->hangcheck_count = 0; - mod_timer(&dev_priv->hangcheck_timer, + dev_priv->gpu_error.hangcheck_count = 0; + mod_timer(&dev_priv->gpu_error.hangcheck_timer, round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES)); } } @@ -862,23 +862,60 @@ done: */ static void i915_error_work_func(struct work_struct *work) { - drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t, - error_work); + struct i915_gpu_error *error = container_of(work, struct i915_gpu_error, + work); + drm_i915_private_t *dev_priv = container_of(error, drm_i915_private_t, + gpu_error); struct drm_device *dev = dev_priv->dev; + struct intel_ring_buffer *ring; char *error_event[] = { "ERROR=1", NULL }; char *reset_event[] = { "RESET=1", NULL }; char *reset_done_event[] = { "ERROR=0", NULL }; + int i, ret; kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, error_event); - if (atomic_read(&dev_priv->mm.wedged)) { + /* + * Note that there's only one work item which does gpu resets, so we + * need not worry about concurrent gpu resets potentially incrementing + * error->reset_counter twice. We only need to take care of another + * racing irq/hangcheck declaring the gpu dead for a second time. A + * quick check for that is good enough: schedule_work ensures the + * correct ordering between hang detection and this work item, and since + * the reset in-progress bit is only ever set by code outside of this + * work we don't need to worry about any other races. + */ + if (i915_reset_in_progress(error) && !i915_terminally_wedged(error)) { DRM_DEBUG_DRIVER("resetting chip\n"); - kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, reset_event); - if (!i915_reset(dev)) { - atomic_set(&dev_priv->mm.wedged, 0); - kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, reset_done_event); + kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, + reset_event); + + ret = i915_reset(dev); + + if (ret == 0) { + /* + * After all the gem state is reset, increment the reset + * counter and wake up everyone waiting for the reset to + * complete. + * + * Since unlock operations are a one-sided barrier only, + * we need to insert a barrier here to order any seqno + * updates before + * the counter increment. + */ + smp_mb__before_atomic_inc(); + atomic_inc(&dev_priv->gpu_error.reset_counter); + + kobject_uevent_env(&dev->primary->kdev.kobj, + KOBJ_CHANGE, reset_done_event); + } else { + atomic_set(&error->reset_counter, I915_WEDGED); } - complete_all(&dev_priv->error_completion); + + for_each_ring(ring, dev_priv, i) + wake_up_all(&ring->irq_queue); + + wake_up_all(&dev_priv->gpu_error.reset_queue); } } @@ -939,7 +976,7 @@ i915_error_object_create(struct drm_i915_private *dev_priv, goto unwind; local_irq_save(flags); - if (reloc_offset < dev_priv->mm.gtt_mappable_end && + if (reloc_offset < dev_priv->gtt.mappable_end && src->has_global_gtt_mapping) { void __iomem *s; @@ -948,7 +985,7 @@ i915_error_object_create(struct drm_i915_private *dev_priv, * captures what the GPU read. */ - s = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, + s = io_mapping_map_atomic_wc(dev_priv->gtt.mappable, reloc_offset); memcpy_fromio(d, s, PAGE_SIZE); io_mapping_unmap_atomic(s); @@ -1255,9 +1292,9 @@ static void i915_capture_error_state(struct drm_device *dev) unsigned long flags; int i, pipe; - spin_lock_irqsave(&dev_priv->error_lock, flags); - error = dev_priv->first_error; - spin_unlock_irqrestore(&dev_priv->error_lock, flags); + spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); + error = dev_priv->gpu_error.first_error; + spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); if (error) return; @@ -1268,7 +1305,8 @@ static void i915_capture_error_state(struct drm_device *dev) return; } - DRM_INFO("capturing error event; look for more information in /debug/dri/%d/i915_error_state\n", + DRM_INFO("capturing error event; look for more information in" + "/sys/kernel/debug/dri/%d/i915_error_state\n", dev->primary->index); kref_init(&error->ref); @@ -1341,12 +1379,12 @@ static void i915_capture_error_state(struct drm_device *dev) error->overlay = intel_overlay_capture_error_state(dev); error->display = intel_display_capture_error_state(dev); - spin_lock_irqsave(&dev_priv->error_lock, flags); - if (dev_priv->first_error == NULL) { - dev_priv->first_error = error; + spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); + if (dev_priv->gpu_error.first_error == NULL) { + dev_priv->gpu_error.first_error = error; error = NULL; } - spin_unlock_irqrestore(&dev_priv->error_lock, flags); + spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); if (error) i915_error_state_free(&error->ref); @@ -1358,10 +1396,10 @@ void i915_destroy_error_state(struct drm_device *dev) struct drm_i915_error_state *error; unsigned long flags; - spin_lock_irqsave(&dev_priv->error_lock, flags); - error = dev_priv->first_error; - dev_priv->first_error = NULL; - spin_unlock_irqrestore(&dev_priv->error_lock, flags); + spin_lock_irqsave(&dev_priv->gpu_error.lock, flags); + error = dev_priv->gpu_error.first_error; + dev_priv->gpu_error.first_error = NULL; + spin_unlock_irqrestore(&dev_priv->gpu_error.lock, flags); if (error) kref_put(&error->ref, i915_error_state_free); @@ -1482,17 +1520,18 @@ void i915_handle_error(struct drm_device *dev, bool wedged) i915_report_and_clear_eir(dev); if (wedged) { - INIT_COMPLETION(dev_priv->error_completion); - atomic_set(&dev_priv->mm.wedged, 1); + atomic_set_mask(I915_RESET_IN_PROGRESS_FLAG, + &dev_priv->gpu_error.reset_counter); /* - * Wakeup waiting processes so they don't hang + * Wakeup waiting processes so that the reset work item + * doesn't deadlock trying to grab various locks. */ for_each_ring(ring, dev_priv, i) wake_up_all(&ring->irq_queue); } - queue_work(dev_priv->wq, &dev_priv->error_work); + queue_work(dev_priv->wq, &dev_priv->gpu_error.work); } static void i915_pageflip_stall_check(struct drm_device *dev, int pipe) @@ -1723,7 +1762,7 @@ static bool i915_hangcheck_hung(struct drm_device *dev) { drm_i915_private_t *dev_priv = dev->dev_private; - if (dev_priv->hangcheck_count++ > 1) { + if (dev_priv->gpu_error.hangcheck_count++ > 1) { bool hung = true; DRM_ERROR("Hangcheck timer elapsed... GPU hung\n"); @@ -1782,25 +1821,29 @@ void i915_hangcheck_elapsed(unsigned long data) goto repeat; } - dev_priv->hangcheck_count = 0; + dev_priv->gpu_error.hangcheck_count = 0; return; } i915_get_extra_instdone(dev, instdone); - if (memcmp(dev_priv->last_acthd, acthd, sizeof(acthd)) == 0 && - memcmp(dev_priv->prev_instdone, instdone, sizeof(instdone)) == 0) { + if (memcmp(dev_priv->gpu_error.last_acthd, acthd, + sizeof(acthd)) == 0 && + memcmp(dev_priv->gpu_error.prev_instdone, instdone, + sizeof(instdone)) == 0) { if (i915_hangcheck_hung(dev)) return; } else { - dev_priv->hangcheck_count = 0; + dev_priv->gpu_error.hangcheck_count = 0; - memcpy(dev_priv->last_acthd, acthd, sizeof(acthd)); - memcpy(dev_priv->prev_instdone, instdone, sizeof(instdone)); + memcpy(dev_priv->gpu_error.last_acthd, acthd, + sizeof(acthd)); + memcpy(dev_priv->gpu_error.prev_instdone, instdone, + sizeof(instdone)); } repeat: /* Reset timer case chip hangs without another request being added */ - mod_timer(&dev_priv->hangcheck_timer, + mod_timer(&dev_priv->gpu_error.hangcheck_timer, round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES)); } @@ -1892,6 +1935,7 @@ static int ironlake_irq_postinstall(struct drm_device *dev) DE_AUX_CHANNEL_A; u32 render_irqs; u32 hotplug_mask; + u32 pch_irq_mask; dev_priv->irq_mask = ~display_mask; @@ -1935,10 +1979,10 @@ static int ironlake_irq_postinstall(struct drm_device *dev) SDE_AUX_MASK); } - dev_priv->pch_irq_mask = ~hotplug_mask; + pch_irq_mask = ~hotplug_mask; I915_WRITE(SDEIIR, I915_READ(SDEIIR)); - I915_WRITE(SDEIMR, dev_priv->pch_irq_mask); + I915_WRITE(SDEIMR, pch_irq_mask); I915_WRITE(SDEIER, hotplug_mask); POSTING_READ(SDEIER); @@ -1966,6 +2010,7 @@ static int ivybridge_irq_postinstall(struct drm_device *dev) DE_AUX_CHANNEL_A_IVB; u32 render_irqs; u32 hotplug_mask; + u32 pch_irq_mask; dev_priv->irq_mask = ~display_mask; @@ -1995,10 +2040,10 @@ static int ivybridge_irq_postinstall(struct drm_device *dev) SDE_PORTD_HOTPLUG_CPT | SDE_GMBUS_CPT | SDE_AUX_MASK_CPT); - dev_priv->pch_irq_mask = ~hotplug_mask; + pch_irq_mask = ~hotplug_mask; I915_WRITE(SDEIIR, I915_READ(SDEIIR)); - I915_WRITE(SDEIMR, dev_priv->pch_irq_mask); + I915_WRITE(SDEIMR, pch_irq_mask); I915_WRITE(SDEIER, hotplug_mask); POSTING_READ(SDEIER); @@ -2767,11 +2812,12 @@ void intel_irq_init(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; INIT_WORK(&dev_priv->hotplug_work, i915_hotplug_work_func); - INIT_WORK(&dev_priv->error_work, i915_error_work_func); + INIT_WORK(&dev_priv->gpu_error.work, i915_error_work_func); INIT_WORK(&dev_priv->rps.work, gen6_pm_rps_work); INIT_WORK(&dev_priv->l3_parity.error_work, ivybridge_parity_work); - setup_timer(&dev_priv->hangcheck_timer, i915_hangcheck_elapsed, + setup_timer(&dev_priv->gpu_error.hangcheck_timer, + i915_hangcheck_elapsed, (unsigned long) dev); pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY, PM_QOS_DEFAULT_VALUE); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 3b039f4268e3..e2b592a68f58 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -141,9 +141,15 @@ #define VGA_MSR_MEM_EN (1<<1) #define VGA_MSR_CGA_MODE (1<<0) -#define VGA_SR_INDEX 0x3c4 +/* + * SR01 is the only VGA register touched on non-UMS setups. + * VLV doesn't do UMS, so the sequencer index/data registers + * are the only VGA registers which need to include + * display_mmio_offset. + */ +#define VGA_SR_INDEX (dev_priv->info->display_mmio_offset + 0x3c4) #define SR01 1 -#define VGA_SR_DATA 0x3c5 +#define VGA_SR_DATA (dev_priv->info->display_mmio_offset + 0x3c5) #define VGA_AR_INDEX 0x3c0 #define VGA_AR_VID_EN (1<<5) @@ -336,17 +342,19 @@ * 0x801c/3c: core clock bits * 0x8048/68: low pass filter coefficients * 0x8100: fast clock controls + * + * DPIO is VLV only. */ -#define DPIO_PKT 0x2100 +#define DPIO_PKT (VLV_DISPLAY_BASE + 0x2100) #define DPIO_RID (0<<24) #define DPIO_OP_WRITE (1<<16) #define DPIO_OP_READ (0<<16) #define DPIO_PORTID (0x12<<8) #define DPIO_BYTE (0xf<<4) #define DPIO_BUSY (1<<0) /* status only */ -#define DPIO_DATA 0x2104 -#define DPIO_REG 0x2108 -#define DPIO_CTL 0x2110 +#define DPIO_DATA (VLV_DISPLAY_BASE + 0x2104) +#define DPIO_REG (VLV_DISPLAY_BASE + 0x2108) +#define DPIO_CTL (VLV_DISPLAY_BASE + 0x2110) #define DPIO_MODSEL1 (1<<3) /* if ref clk b == 27 */ #define DPIO_MODSEL0 (1<<2) /* if ref clk a == 27 */ #define DPIO_SFR_BYPASS (1<<1) @@ -554,13 +562,13 @@ #define IIR 0x020a4 #define IMR 0x020a8 #define ISR 0x020ac -#define VLV_GUNIT_CLOCK_GATE 0x182060 +#define VLV_GUNIT_CLOCK_GATE (VLV_DISPLAY_BASE + 0x2060) #define GCFG_DIS (1<<8) -#define VLV_IIR_RW 0x182084 -#define VLV_IER 0x1820a0 -#define VLV_IIR 0x1820a4 -#define VLV_IMR 0x1820a8 -#define VLV_ISR 0x1820ac +#define VLV_IIR_RW (VLV_DISPLAY_BASE + 0x2084) +#define VLV_IER (VLV_DISPLAY_BASE + 0x20a0) +#define VLV_IIR (VLV_DISPLAY_BASE + 0x20a4) +#define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8) +#define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac) #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT (1<<18) #define I915_DISPLAY_PORT_INTERRUPT (1<<17) #define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT (1<<15) @@ -733,6 +741,7 @@ #define GEN7_FF_TS_SCHED_HS0 (0x3<<16) #define GEN7_FF_TS_SCHED_LOAD_BALANCE (0x1<<16) #define GEN7_FF_TS_SCHED_HW (0x0<<16) /* Default */ +#define GEN7_FF_VS_REF_CNT_FFME (1 << 15) #define GEN7_FF_VS_SCHED_HS1 (0x5<<12) #define GEN7_FF_VS_SCHED_HS0 (0x3<<12) #define GEN7_FF_VS_SCHED_LOAD_BALANCE (0x1<<12) /* Default */ @@ -919,8 +928,8 @@ #define VGA1_PD_P1_DIV_2 (1 << 13) #define VGA1_PD_P1_SHIFT 8 #define VGA1_PD_P1_MASK (0x1f << 8) -#define _DPLL_A 0x06014 -#define _DPLL_B 0x06018 +#define _DPLL_A (dev_priv->info->display_mmio_offset + 0x6014) +#define _DPLL_B (dev_priv->info->display_mmio_offset + 0x6018) #define DPLL(pipe) _PIPE(pipe, _DPLL_A, _DPLL_B) #define DPLL_VCO_ENABLE (1 << 31) #define DPLL_DVO_HIGH_SPEED (1 << 30) @@ -979,7 +988,7 @@ #define SDVO_MULTIPLIER_MASK 0x000000ff #define SDVO_MULTIPLIER_SHIFT_HIRES 4 #define SDVO_MULTIPLIER_SHIFT_VGA 0 -#define _DPLL_A_MD 0x0601c /* 965+ only */ +#define _DPLL_A_MD (dev_priv->info->display_mmio_offset + 0x601c) /* 965+ only */ /* * UDI pixel divider, controlling how many pixels are stuffed into a packet. * @@ -1016,7 +1025,7 @@ */ #define DPLL_MD_VGA_UDI_MULTIPLIER_MASK 0x0000003f #define DPLL_MD_VGA_UDI_MULTIPLIER_SHIFT 0 -#define _DPLL_B_MD 0x06020 /* 965+ only */ +#define _DPLL_B_MD (dev_priv->info->display_mmio_offset + 0x6020) /* 965+ only */ #define DPLL_MD(pipe) _PIPE(pipe, _DPLL_A_MD, _DPLL_B_MD) #define _FPA0 0x06040 @@ -1159,15 +1168,15 @@ #define RAMCLK_GATE_D 0x6210 /* CRL only */ #define DEUC 0x6214 /* CRL only */ -#define FW_BLC_SELF_VLV 0x6500 +#define FW_BLC_SELF_VLV (VLV_DISPLAY_BASE + 0x6500) #define FW_CSPWRDWNEN (1<<15) /* * Palette regs */ -#define _PALETTE_A 0x0a000 -#define _PALETTE_B 0x0a800 +#define _PALETTE_A (dev_priv->info->display_mmio_offset + 0xa000) +#define _PALETTE_B (dev_priv->info->display_mmio_offset + 0xa800) #define PALETTE(pipe) _PIPE(pipe, _PALETTE_A, _PALETTE_B) /* MCH MMIO space */ @@ -1532,26 +1541,26 @@ */ /* Pipe A timing regs */ -#define _HTOTAL_A 0x60000 -#define _HBLANK_A 0x60004 -#define _HSYNC_A 0x60008 -#define _VTOTAL_A 0x6000c -#define _VBLANK_A 0x60010 -#define _VSYNC_A 0x60014 -#define _PIPEASRC 0x6001c -#define _BCLRPAT_A 0x60020 -#define _VSYNCSHIFT_A 0x60028 +#define _HTOTAL_A (dev_priv->info->display_mmio_offset + 0x60000) +#define _HBLANK_A (dev_priv->info->display_mmio_offset + 0x60004) +#define _HSYNC_A (dev_priv->info->display_mmio_offset + 0x60008) +#define _VTOTAL_A (dev_priv->info->display_mmio_offset + 0x6000c) +#define _VBLANK_A (dev_priv->info->display_mmio_offset + 0x60010) +#define _VSYNC_A (dev_priv->info->display_mmio_offset + 0x60014) +#define _PIPEASRC (dev_priv->info->display_mmio_offset + 0x6001c) +#define _BCLRPAT_A (dev_priv->info->display_mmio_offset + 0x60020) +#define _VSYNCSHIFT_A (dev_priv->info->display_mmio_offset + 0x60028) /* Pipe B timing regs */ -#define _HTOTAL_B 0x61000 -#define _HBLANK_B 0x61004 -#define _HSYNC_B 0x61008 -#define _VTOTAL_B 0x6100c -#define _VBLANK_B 0x61010 -#define _VSYNC_B 0x61014 -#define _PIPEBSRC 0x6101c -#define _BCLRPAT_B 0x61020 -#define _VSYNCSHIFT_B 0x61028 +#define _HTOTAL_B (dev_priv->info->display_mmio_offset + 0x61000) +#define _HBLANK_B (dev_priv->info->display_mmio_offset + 0x61004) +#define _HSYNC_B (dev_priv->info->display_mmio_offset + 0x61008) +#define _VTOTAL_B (dev_priv->info->display_mmio_offset + 0x6100c) +#define _VBLANK_B (dev_priv->info->display_mmio_offset + 0x61010) +#define _VSYNC_B (dev_priv->info->display_mmio_offset + 0x61014) +#define _PIPEBSRC (dev_priv->info->display_mmio_offset + 0x6101c) +#define _BCLRPAT_B (dev_priv->info->display_mmio_offset + 0x61020) +#define _VSYNCSHIFT_B (dev_priv->info->display_mmio_offset + 0x61028) #define HTOTAL(trans) _TRANSCODER(trans, _HTOTAL_A, _HTOTAL_B) @@ -1612,7 +1621,7 @@ /* Hotplug control (945+ only) */ -#define PORT_HOTPLUG_EN 0x61110 +#define PORT_HOTPLUG_EN (dev_priv->info->display_mmio_offset + 0x61110) #define HDMIB_HOTPLUG_INT_EN (1 << 29) #define DPB_HOTPLUG_INT_EN (1 << 29) #define HDMIC_HOTPLUG_INT_EN (1 << 28) @@ -1639,7 +1648,7 @@ #define CRT_HOTPLUG_DETECT_VOLTAGE_325MV (0 << 2) #define CRT_HOTPLUG_DETECT_VOLTAGE_475MV (1 << 2) -#define PORT_HOTPLUG_STAT 0x61114 +#define PORT_HOTPLUG_STAT (dev_priv->info->display_mmio_offset + 0x61114) /* HDMI/DP bits are gen4+ */ #define DPB_HOTPLUG_LIVE_STATUS (1 << 29) #define DPC_HOTPLUG_LIVE_STATUS (1 << 28) @@ -1858,7 +1867,7 @@ #define PP_DIVISOR 0x61210 /* Panel fitting */ -#define PFIT_CONTROL 0x61230 +#define PFIT_CONTROL (dev_priv->info->display_mmio_offset + 0x61230) #define PFIT_ENABLE (1 << 31) #define PFIT_PIPE_MASK (3 << 29) #define PFIT_PIPE_SHIFT 29 @@ -1876,7 +1885,7 @@ #define PFIT_SCALING_PROGRAMMED (1 << 26) #define PFIT_SCALING_PILLAR (2 << 26) #define PFIT_SCALING_LETTER (3 << 26) -#define PFIT_PGM_RATIOS 0x61234 +#define PFIT_PGM_RATIOS (dev_priv->info->display_mmio_offset + 0x61234) /* Pre-965 */ #define PFIT_VERT_SCALE_SHIFT 20 #define PFIT_VERT_SCALE_MASK 0xfff00000 @@ -1888,7 +1897,7 @@ #define PFIT_HORIZ_SCALE_SHIFT_965 0 #define PFIT_HORIZ_SCALE_MASK_965 0x00001fff -#define PFIT_AUTO_RATIOS 0x61238 +#define PFIT_AUTO_RATIOS (dev_priv->info->display_mmio_offset + 0x61238) /* Backlight control */ #define BLC_PWM_CTL2 0x61250 /* 965+ only */ @@ -2618,10 +2627,10 @@ /* Display & cursor control */ /* Pipe A */ -#define _PIPEADSL 0x70000 +#define _PIPEADSL (dev_priv->info->display_mmio_offset + 0x70000) #define DSL_LINEMASK_GEN2 0x00000fff #define DSL_LINEMASK_GEN3 0x00001fff -#define _PIPEACONF 0x70008 +#define _PIPEACONF (dev_priv->info->display_mmio_offset + 0x70008) #define PIPECONF_ENABLE (1<<31) #define PIPECONF_DISABLE 0 #define PIPECONF_DOUBLE_WIDE (1<<30) @@ -2650,6 +2659,7 @@ #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_COLOR_RANGE_SELECT (1 << 13) #define PIPECONF_BPC_MASK (0x7 << 5) #define PIPECONF_8BPC (0<<5) #define PIPECONF_10BPC (1<<5) @@ -2661,7 +2671,7 @@ #define PIPECONF_DITHER_TYPE_ST1 (1<<2) #define PIPECONF_DITHER_TYPE_ST2 (2<<2) #define PIPECONF_DITHER_TYPE_TEMP (3<<2) -#define _PIPEASTAT 0x70024 +#define _PIPEASTAT (dev_priv->info->display_mmio_offset + 0x70024) #define PIPE_FIFO_UNDERRUN_STATUS (1UL<<31) #define SPRITE1_FLIPDONE_INT_EN_VLV (1UL<<30) #define PIPE_CRC_ERROR_ENABLE (1UL<<29) @@ -2672,7 +2682,7 @@ #define PIPE_VSYNC_INTERRUPT_ENABLE (1UL<<25) #define PIPE_DISPLAY_LINE_COMPARE_ENABLE (1UL<<24) #define PIPE_DPST_EVENT_ENABLE (1UL<<23) -#define SPRITE0_FLIP_DONE_INT_EN_VLV (1UL<<26) +#define SPRITE0_FLIP_DONE_INT_EN_VLV (1UL<<22) #define PIPE_LEGACY_BLC_EVENT_ENABLE (1UL<<22) #define PIPE_ODD_FIELD_INTERRUPT_ENABLE (1UL<<21) #define PIPE_EVEN_FIELD_INTERRUPT_ENABLE (1UL<<20) @@ -2682,7 +2692,7 @@ #define PIPEA_HBLANK_INT_EN_VLV (1UL<<16) #define PIPE_OVERLAY_UPDATED_ENABLE (1UL<<16) #define SPRITE1_FLIPDONE_INT_STATUS_VLV (1UL<<15) -#define SPRITE0_FLIPDONE_INT_STATUS_VLV (1UL<<15) +#define SPRITE0_FLIPDONE_INT_STATUS_VLV (1UL<<14) #define PIPE_CRC_ERROR_INTERRUPT_STATUS (1UL<<13) #define PIPE_CRC_DONE_INTERRUPT_STATUS (1UL<<12) #define PIPE_GMBUS_INTERRUPT_STATUS (1UL<<11) @@ -2706,7 +2716,7 @@ #define PIPEFRAMEPIXEL(pipe) _PIPE(pipe, _PIPEAFRAMEPIXEL, _PIPEBFRAMEPIXEL) #define PIPESTAT(pipe) _PIPE(pipe, _PIPEASTAT, _PIPEBSTAT) -#define VLV_DPFLIPSTAT 0x70028 +#define VLV_DPFLIPSTAT (VLV_DISPLAY_BASE + 0x70028) #define PIPEB_LINE_COMPARE_INT_EN (1<<29) #define PIPEB_HLINE_INT_EN (1<<28) #define PIPEB_VBLANK_INT_EN (1<<27) @@ -2720,7 +2730,7 @@ #define SPRITEA_FLIPDONE_INT_EN (1<<17) #define PLANEA_FLIPDONE_INT_EN (1<<16) -#define DPINVGTT 0x7002c /* VLV only */ +#define DPINVGTT (VLV_DISPLAY_BASE + 0x7002c) /* VLV only */ #define CURSORB_INVALID_GTT_INT_EN (1<<23) #define CURSORA_INVALID_GTT_INT_EN (1<<22) #define SPRITED_INVALID_GTT_INT_EN (1<<21) @@ -2748,7 +2758,7 @@ #define DSPARB_BEND_SHIFT 9 /* on 855 */ #define DSPARB_AEND_SHIFT 0 -#define DSPFW1 0x70034 +#define DSPFW1 (dev_priv->info->display_mmio_offset + 0x70034) #define DSPFW_SR_SHIFT 23 #define DSPFW_SR_MASK (0x1ff<<23) #define DSPFW_CURSORB_SHIFT 16 @@ -2756,11 +2766,11 @@ #define DSPFW_PLANEB_SHIFT 8 #define DSPFW_PLANEB_MASK (0x7f<<8) #define DSPFW_PLANEA_MASK (0x7f) -#define DSPFW2 0x70038 +#define DSPFW2 (dev_priv->info->display_mmio_offset + 0x70038) #define DSPFW_CURSORA_MASK 0x00003f00 #define DSPFW_CURSORA_SHIFT 8 #define DSPFW_PLANEC_MASK (0x7f) -#define DSPFW3 0x7003c +#define DSPFW3 (dev_priv->info->display_mmio_offset + 0x7003c) #define DSPFW_HPLL_SR_EN (1<<31) #define DSPFW_CURSOR_SR_SHIFT 24 #define PINEVIEW_SELF_REFRESH_EN (1<<30) @@ -2772,13 +2782,13 @@ /* drain latency register values*/ #define DRAIN_LATENCY_PRECISION_32 32 #define DRAIN_LATENCY_PRECISION_16 16 -#define VLV_DDL1 0x70050 +#define VLV_DDL1 (VLV_DISPLAY_BASE + 0x70050) #define DDL_CURSORA_PRECISION_32 (1<<31) #define DDL_CURSORA_PRECISION_16 (0<<31) #define DDL_CURSORA_SHIFT 24 #define DDL_PLANEA_PRECISION_32 (1<<7) #define DDL_PLANEA_PRECISION_16 (0<<7) -#define VLV_DDL2 0x70054 +#define VLV_DDL2 (VLV_DISPLAY_BASE + 0x70054) #define DDL_CURSORB_PRECISION_32 (1<<31) #define DDL_CURSORB_PRECISION_16 (0<<31) #define DDL_CURSORB_SHIFT 24 @@ -2922,10 +2932,10 @@ * } while (high1 != high2); * frame = (high1 << 8) | low1; */ -#define _PIPEAFRAMEHIGH 0x70040 +#define _PIPEAFRAMEHIGH (dev_priv->info->display_mmio_offset + 0x70040) #define PIPE_FRAME_HIGH_MASK 0x0000ffff #define PIPE_FRAME_HIGH_SHIFT 0 -#define _PIPEAFRAMEPIXEL 0x70044 +#define _PIPEAFRAMEPIXEL (dev_priv->info->display_mmio_offset + 0x70044) #define PIPE_FRAME_LOW_MASK 0xff000000 #define PIPE_FRAME_LOW_SHIFT 24 #define PIPE_PIXEL_MASK 0x00ffffff @@ -2936,7 +2946,7 @@ #define PIPE_FRMCOUNT_GM45(pipe) _PIPE(pipe, _PIPEA_FRMCOUNT_GM45, _PIPEB_FRMCOUNT_GM45) /* Cursor A & B regs */ -#define _CURACNTR 0x70080 +#define _CURACNTR (dev_priv->info->display_mmio_offset + 0x70080) /* Old style CUR*CNTR flags (desktop 8xx) */ #define CURSOR_ENABLE 0x80000000 #define CURSOR_GAMMA_ENABLE 0x40000000 @@ -2957,16 +2967,16 @@ #define MCURSOR_PIPE_A 0x00 #define MCURSOR_PIPE_B (1 << 28) #define MCURSOR_GAMMA_ENABLE (1 << 26) -#define _CURABASE 0x70084 -#define _CURAPOS 0x70088 +#define _CURABASE (dev_priv->info->display_mmio_offset + 0x70084) +#define _CURAPOS (dev_priv->info->display_mmio_offset + 0x70088) #define CURSOR_POS_MASK 0x007FF #define CURSOR_POS_SIGN 0x8000 #define CURSOR_X_SHIFT 0 #define CURSOR_Y_SHIFT 16 #define CURSIZE 0x700a0 -#define _CURBCNTR 0x700c0 -#define _CURBBASE 0x700c4 -#define _CURBPOS 0x700c8 +#define _CURBCNTR (dev_priv->info->display_mmio_offset + 0x700c0) +#define _CURBBASE (dev_priv->info->display_mmio_offset + 0x700c4) +#define _CURBPOS (dev_priv->info->display_mmio_offset + 0x700c8) #define _CURBCNTR_IVB 0x71080 #define _CURBBASE_IVB 0x71084 @@ -2981,7 +2991,7 @@ #define CURPOS_IVB(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS_IVB) /* Display A control */ -#define _DSPACNTR 0x70180 +#define _DSPACNTR (dev_priv->info->display_mmio_offset + 0x70180) #define DISPLAY_PLANE_ENABLE (1<<31) #define DISPLAY_PLANE_DISABLE 0 #define DISPPLANE_GAMMA_ENABLE (1<<30) @@ -3014,14 +3024,14 @@ #define DISPPLANE_STEREO_POLARITY_SECOND (1<<18) #define DISPPLANE_TRICKLE_FEED_DISABLE (1<<14) /* Ironlake */ #define DISPPLANE_TILED (1<<10) -#define _DSPAADDR 0x70184 -#define _DSPASTRIDE 0x70188 -#define _DSPAPOS 0x7018C /* reserved */ -#define _DSPASIZE 0x70190 -#define _DSPASURF 0x7019C /* 965+ only */ -#define _DSPATILEOFF 0x701A4 /* 965+ only */ -#define _DSPAOFFSET 0x701A4 /* HSW */ -#define _DSPASURFLIVE 0x701AC +#define _DSPAADDR (dev_priv->info->display_mmio_offset + 0x70184) +#define _DSPASTRIDE (dev_priv->info->display_mmio_offset + 0x70188) +#define _DSPAPOS (dev_priv->info->display_mmio_offset + 0x7018C) /* reserved */ +#define _DSPASIZE (dev_priv->info->display_mmio_offset + 0x70190) +#define _DSPASURF (dev_priv->info->display_mmio_offset + 0x7019C) /* 965+ only */ +#define _DSPATILEOFF (dev_priv->info->display_mmio_offset + 0x701A4) /* 965+ only */ +#define _DSPAOFFSET (dev_priv->info->display_mmio_offset + 0x701A4) /* HSW */ +#define _DSPASURFLIVE (dev_priv->info->display_mmio_offset + 0x701AC) #define DSPCNTR(plane) _PIPE(plane, _DSPACNTR, _DSPBCNTR) #define DSPADDR(plane) _PIPE(plane, _DSPAADDR, _DSPBADDR) @@ -3042,44 +3052,44 @@ (I915_WRITE((reg), (gfx_addr) | I915_LO_DISPBASE(I915_READ(reg)))) /* VBIOS flags */ -#define SWF00 0x71410 -#define SWF01 0x71414 -#define SWF02 0x71418 -#define SWF03 0x7141c -#define SWF04 0x71420 -#define SWF05 0x71424 -#define SWF06 0x71428 -#define SWF10 0x70410 -#define SWF11 0x70414 -#define SWF14 0x71420 -#define SWF30 0x72414 -#define SWF31 0x72418 -#define SWF32 0x7241c +#define SWF00 (dev_priv->info->display_mmio_offset + 0x71410) +#define SWF01 (dev_priv->info->display_mmio_offset + 0x71414) +#define SWF02 (dev_priv->info->display_mmio_offset + 0x71418) +#define SWF03 (dev_priv->info->display_mmio_offset + 0x7141c) +#define SWF04 (dev_priv->info->display_mmio_offset + 0x71420) +#define SWF05 (dev_priv->info->display_mmio_offset + 0x71424) +#define SWF06 (dev_priv->info->display_mmio_offset + 0x71428) +#define SWF10 (dev_priv->info->display_mmio_offset + 0x70410) +#define SWF11 (dev_priv->info->display_mmio_offset + 0x70414) +#define SWF14 (dev_priv->info->display_mmio_offset + 0x71420) +#define SWF30 (dev_priv->info->display_mmio_offset + 0x72414) +#define SWF31 (dev_priv->info->display_mmio_offset + 0x72418) +#define SWF32 (dev_priv->info->display_mmio_offset + 0x7241c) /* Pipe B */ -#define _PIPEBDSL 0x71000 -#define _PIPEBCONF 0x71008 -#define _PIPEBSTAT 0x71024 -#define _PIPEBFRAMEHIGH 0x71040 -#define _PIPEBFRAMEPIXEL 0x71044 +#define _PIPEBDSL (dev_priv->info->display_mmio_offset + 0x71000) +#define _PIPEBCONF (dev_priv->info->display_mmio_offset + 0x71008) +#define _PIPEBSTAT (dev_priv->info->display_mmio_offset + 0x71024) +#define _PIPEBFRAMEHIGH (dev_priv->info->display_mmio_offset + 0x71040) +#define _PIPEBFRAMEPIXEL (dev_priv->info->display_mmio_offset + 0x71044) #define _PIPEB_FRMCOUNT_GM45 0x71040 #define _PIPEB_FLIPCOUNT_GM45 0x71044 /* Display B control */ -#define _DSPBCNTR 0x71180 +#define _DSPBCNTR (dev_priv->info->display_mmio_offset + 0x71180) #define DISPPLANE_ALPHA_TRANS_ENABLE (1<<15) #define DISPPLANE_ALPHA_TRANS_DISABLE 0 #define DISPPLANE_SPRITE_ABOVE_DISPLAY 0 #define DISPPLANE_SPRITE_ABOVE_OVERLAY (1) -#define _DSPBADDR 0x71184 -#define _DSPBSTRIDE 0x71188 -#define _DSPBPOS 0x7118C -#define _DSPBSIZE 0x71190 -#define _DSPBSURF 0x7119C -#define _DSPBTILEOFF 0x711A4 -#define _DSPBOFFSET 0x711A4 -#define _DSPBSURFLIVE 0x711AC +#define _DSPBADDR (dev_priv->info->display_mmio_offset + 0x71184) +#define _DSPBSTRIDE (dev_priv->info->display_mmio_offset + 0x71188) +#define _DSPBPOS (dev_priv->info->display_mmio_offset + 0x7118C) +#define _DSPBSIZE (dev_priv->info->display_mmio_offset + 0x71190) +#define _DSPBSURF (dev_priv->info->display_mmio_offset + 0x7119C) +#define _DSPBTILEOFF (dev_priv->info->display_mmio_offset + 0x711A4) +#define _DSPBOFFSET (dev_priv->info->display_mmio_offset + 0x711A4) +#define _DSPBSURFLIVE (dev_priv->info->display_mmio_offset + 0x711AC) /* Sprite A control */ #define _DVSACNTR 0x72180 @@ -3228,6 +3238,8 @@ # define VGA_2X_MODE (1 << 30) # define VGA_PIPE_B_SELECT (1 << 29) +#define VLV_VGACNTRL (VLV_DISPLAY_BASE + 0x71400) + /* Ironlake */ #define CPU_VGACNTRL 0x41000 @@ -3268,41 +3280,41 @@ #define FDI_PLL_FREQ_DISABLE_COUNT_LIMIT_MASK 0xff -#define _PIPEA_DATA_M1 0x60030 +#define _PIPEA_DATA_M1 (dev_priv->info->display_mmio_offset + 0x60030) #define TU_SIZE(x) (((x)-1) << 25) /* default size 64 */ #define TU_SIZE_MASK 0x7e000000 #define PIPE_DATA_M1_OFFSET 0 -#define _PIPEA_DATA_N1 0x60034 +#define _PIPEA_DATA_N1 (dev_priv->info->display_mmio_offset + 0x60034) #define PIPE_DATA_N1_OFFSET 0 -#define _PIPEA_DATA_M2 0x60038 +#define _PIPEA_DATA_M2 (dev_priv->info->display_mmio_offset + 0x60038) #define PIPE_DATA_M2_OFFSET 0 -#define _PIPEA_DATA_N2 0x6003c +#define _PIPEA_DATA_N2 (dev_priv->info->display_mmio_offset + 0x6003c) #define PIPE_DATA_N2_OFFSET 0 -#define _PIPEA_LINK_M1 0x60040 +#define _PIPEA_LINK_M1 (dev_priv->info->display_mmio_offset + 0x60040) #define PIPE_LINK_M1_OFFSET 0 -#define _PIPEA_LINK_N1 0x60044 +#define _PIPEA_LINK_N1 (dev_priv->info->display_mmio_offset + 0x60044) #define PIPE_LINK_N1_OFFSET 0 -#define _PIPEA_LINK_M2 0x60048 +#define _PIPEA_LINK_M2 (dev_priv->info->display_mmio_offset + 0x60048) #define PIPE_LINK_M2_OFFSET 0 -#define _PIPEA_LINK_N2 0x6004c +#define _PIPEA_LINK_N2 (dev_priv->info->display_mmio_offset + 0x6004c) #define PIPE_LINK_N2_OFFSET 0 /* PIPEB timing regs are same start from 0x61000 */ -#define _PIPEB_DATA_M1 0x61030 -#define _PIPEB_DATA_N1 0x61034 +#define _PIPEB_DATA_M1 (dev_priv->info->display_mmio_offset + 0x61030) +#define _PIPEB_DATA_N1 (dev_priv->info->display_mmio_offset + 0x61034) -#define _PIPEB_DATA_M2 0x61038 -#define _PIPEB_DATA_N2 0x6103c +#define _PIPEB_DATA_M2 (dev_priv->info->display_mmio_offset + 0x61038) +#define _PIPEB_DATA_N2 (dev_priv->info->display_mmio_offset + 0x6103c) -#define _PIPEB_LINK_M1 0x61040 -#define _PIPEB_LINK_N1 0x61044 +#define _PIPEB_LINK_M1 (dev_priv->info->display_mmio_offset + 0x61040) +#define _PIPEB_LINK_N1 (dev_priv->info->display_mmio_offset + 0x61044) -#define _PIPEB_LINK_M2 0x61048 -#define _PIPEB_LINK_N2 0x6104c +#define _PIPEB_LINK_M2 (dev_priv->info->display_mmio_offset + 0x61048) +#define _PIPEB_LINK_N2 (dev_priv->info->display_mmio_offset + 0x6104c) #define PIPE_DATA_M1(tran) _TRANSCODER(tran, _PIPEA_DATA_M1, _PIPEB_DATA_M1) #define PIPE_DATA_N1(tran) _TRANSCODER(tran, _PIPEA_DATA_N1, _PIPEB_DATA_N1) @@ -3699,13 +3711,13 @@ #define TVIDEO_DIP_DATA(pipe) _PIPE(pipe, _VIDEO_DIP_DATA_A, _VIDEO_DIP_DATA_B) #define TVIDEO_DIP_GCP(pipe) _PIPE(pipe, _VIDEO_DIP_GCP_A, _VIDEO_DIP_GCP_B) -#define VLV_VIDEO_DIP_CTL_A 0x60200 -#define VLV_VIDEO_DIP_DATA_A 0x60208 -#define VLV_VIDEO_DIP_GDCP_PAYLOAD_A 0x60210 +#define VLV_VIDEO_DIP_CTL_A (VLV_DISPLAY_BASE + 0x60200) +#define VLV_VIDEO_DIP_DATA_A (VLV_DISPLAY_BASE + 0x60208) +#define VLV_VIDEO_DIP_GDCP_PAYLOAD_A (VLV_DISPLAY_BASE + 0x60210) -#define VLV_VIDEO_DIP_CTL_B 0x61170 -#define VLV_VIDEO_DIP_DATA_B 0x61174 -#define VLV_VIDEO_DIP_GDCP_PAYLOAD_B 0x61178 +#define VLV_VIDEO_DIP_CTL_B (VLV_DISPLAY_BASE + 0x61170) +#define VLV_VIDEO_DIP_DATA_B (VLV_DISPLAY_BASE + 0x61174) +#define VLV_VIDEO_DIP_GDCP_PAYLOAD_B (VLV_DISPLAY_BASE + 0x61178) #define VLV_TVIDEO_DIP_CTL(pipe) \ _PIPE(pipe, VLV_VIDEO_DIP_CTL_A, VLV_VIDEO_DIP_CTL_B) @@ -3995,17 +4007,17 @@ #define LVDS_DETECTED (1 << 1) /* vlv has 2 sets of panel control regs. */ -#define PIPEA_PP_STATUS 0x61200 -#define PIPEA_PP_CONTROL 0x61204 -#define PIPEA_PP_ON_DELAYS 0x61208 -#define PIPEA_PP_OFF_DELAYS 0x6120c -#define PIPEA_PP_DIVISOR 0x61210 - -#define PIPEB_PP_STATUS 0x61300 -#define PIPEB_PP_CONTROL 0x61304 -#define PIPEB_PP_ON_DELAYS 0x61308 -#define PIPEB_PP_OFF_DELAYS 0x6130c -#define PIPEB_PP_DIVISOR 0x61310 +#define PIPEA_PP_STATUS (VLV_DISPLAY_BASE + 0x61200) +#define PIPEA_PP_CONTROL (VLV_DISPLAY_BASE + 0x61204) +#define PIPEA_PP_ON_DELAYS (VLV_DISPLAY_BASE + 0x61208) +#define PIPEA_PP_OFF_DELAYS (VLV_DISPLAY_BASE + 0x6120c) +#define PIPEA_PP_DIVISOR (VLV_DISPLAY_BASE + 0x61210) + +#define PIPEB_PP_STATUS (VLV_DISPLAY_BASE + 0x61300) +#define PIPEB_PP_CONTROL (VLV_DISPLAY_BASE + 0x61304) +#define PIPEB_PP_ON_DELAYS (VLV_DISPLAY_BASE + 0x61308) +#define PIPEB_PP_OFF_DELAYS (VLV_DISPLAY_BASE + 0x6130c) +#define PIPEB_PP_DIVISOR (VLV_DISPLAY_BASE + 0x61310) #define PCH_PP_STATUS 0xc7200 #define PCH_PP_CONTROL 0xc7204 @@ -4186,7 +4198,9 @@ #define GEN6_RP_INTERRUPT_LIMITS 0xA014 #define GEN6_RPSTAT1 0xA01C #define GEN6_CAGF_SHIFT 8 +#define HSW_CAGF_SHIFT 7 #define GEN6_CAGF_MASK (0x7f << GEN6_CAGF_SHIFT) +#define HSW_CAGF_MASK (0x7f << HSW_CAGF_SHIFT) #define GEN6_RP_CONTROL 0xA024 #define GEN6_RP_MEDIA_TURBO (1<<11) #define GEN6_RP_MEDIA_MODE_MASK (3<<9) @@ -4297,7 +4311,7 @@ #define GEN7_ROW_CHICKEN2_GT2 0xf4f4 #define DOP_CLOCK_GATING_DISABLE (1<<0) -#define G4X_AUD_VID_DID 0x62020 +#define G4X_AUD_VID_DID (dev_priv->info->display_mmio_offset + 0x62020) #define INTEL_AUDIO_DEVCL 0x808629FB #define INTEL_AUDIO_DEVBLC 0x80862801 #define INTEL_AUDIO_DEVCTG 0x80862802 @@ -4413,10 +4427,10 @@ #define AUDIO_CP_READY_C (1<<9) /* HSW Power Wells */ -#define HSW_PWR_WELL_CTL1 0x45400 /* BIOS */ -#define HSW_PWR_WELL_CTL2 0x45404 /* Driver */ -#define HSW_PWR_WELL_CTL3 0x45408 /* KVMR */ -#define HSW_PWR_WELL_CTL4 0x4540C /* Debug */ +#define HSW_PWR_WELL_BIOS 0x45400 /* CTL1 */ +#define HSW_PWR_WELL_DRIVER 0x45404 /* CTL2 */ +#define HSW_PWR_WELL_KVMR 0x45408 /* CTL3 */ +#define HSW_PWR_WELL_DEBUG 0x4540C /* CTL4 */ #define HSW_PWR_WELL_ENABLE (1<<31) #define HSW_PWR_WELL_STATE (1<<30) #define HSW_PWR_WELL_CTL5 0x45410 diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 63d4d30c39de..2135f21ea458 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -29,67 +29,6 @@ #include "intel_drv.h" #include "i915_reg.h" -static bool i915_pipe_enabled(struct drm_device *dev, enum pipe pipe) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - u32 dpll_reg; - - /* On IVB, 3rd pipe shares PLL with another one */ - if (pipe > 1) - return false; - - if (HAS_PCH_SPLIT(dev)) - dpll_reg = _PCH_DPLL(pipe); - else - dpll_reg = (pipe == PIPE_A) ? _DPLL_A : _DPLL_B; - - return (I915_READ(dpll_reg) & DPLL_VCO_ENABLE); -} - -static void i915_save_palette(struct drm_device *dev, enum pipe pipe) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - unsigned long reg = (pipe == PIPE_A ? _PALETTE_A : _PALETTE_B); - u32 *array; - int i; - - if (!i915_pipe_enabled(dev, pipe)) - return; - - if (HAS_PCH_SPLIT(dev)) - reg = (pipe == PIPE_A) ? _LGC_PALETTE_A : _LGC_PALETTE_B; - - if (pipe == PIPE_A) - array = dev_priv->regfile.save_palette_a; - else - array = dev_priv->regfile.save_palette_b; - - for (i = 0; i < 256; i++) - array[i] = I915_READ(reg + (i << 2)); -} - -static void i915_restore_palette(struct drm_device *dev, enum pipe pipe) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - unsigned long reg = (pipe == PIPE_A ? _PALETTE_A : _PALETTE_B); - u32 *array; - int i; - - if (!i915_pipe_enabled(dev, pipe)) - return; - - if (HAS_PCH_SPLIT(dev)) - reg = (pipe == PIPE_A) ? _LGC_PALETTE_A : _LGC_PALETTE_B; - - if (pipe == PIPE_A) - array = dev_priv->regfile.save_palette_a; - else - array = dev_priv->regfile.save_palette_b; - - for (i = 0; i < 256; i++) - I915_WRITE(reg + (i << 2), array[i]); -} - static u8 i915_read_indexed(struct drm_device *dev, u16 index_port, u16 data_port, u8 reg) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -130,6 +69,12 @@ static void i915_save_vga(struct drm_device *dev) int i; u16 cr_index, cr_data, st01; + /* VGA state */ + dev_priv->regfile.saveVGA0 = I915_READ(VGA0); + dev_priv->regfile.saveVGA1 = I915_READ(VGA1); + dev_priv->regfile.saveVGA_PD = I915_READ(VGA_PD); + dev_priv->regfile.saveVGACNTRL = I915_READ(i915_vgacntrl_reg(dev)); + /* VGA color palette registers */ dev_priv->regfile.saveDACMASK = I915_READ8(VGA_DACMASK); @@ -188,6 +133,15 @@ static void i915_restore_vga(struct drm_device *dev) int i; u16 cr_index, cr_data, st01; + /* VGA state */ + I915_WRITE(i915_vgacntrl_reg(dev), dev_priv->regfile.saveVGACNTRL); + + I915_WRITE(VGA0, dev_priv->regfile.saveVGA0); + I915_WRITE(VGA1, dev_priv->regfile.saveVGA1); + I915_WRITE(VGA_PD, dev_priv->regfile.saveVGA_PD); + POSTING_READ(VGA_PD); + udelay(150); + /* MSR bits */ I915_WRITE8(VGA_MSR_WRITE, dev_priv->regfile.saveMSR); if (dev_priv->regfile.saveMSR & VGA_MSR_CGA_MODE) { @@ -235,396 +189,18 @@ static void i915_restore_vga(struct drm_device *dev) I915_WRITE8(VGA_DACMASK, dev_priv->regfile.saveDACMASK); } -static void i915_save_modeset_reg(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - int i; - - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return; - - /* Cursor state */ - dev_priv->regfile.saveCURACNTR = I915_READ(_CURACNTR); - dev_priv->regfile.saveCURAPOS = I915_READ(_CURAPOS); - dev_priv->regfile.saveCURABASE = I915_READ(_CURABASE); - dev_priv->regfile.saveCURBCNTR = I915_READ(_CURBCNTR); - dev_priv->regfile.saveCURBPOS = I915_READ(_CURBPOS); - dev_priv->regfile.saveCURBBASE = I915_READ(_CURBBASE); - if (IS_GEN2(dev)) - dev_priv->regfile.saveCURSIZE = I915_READ(CURSIZE); - - if (HAS_PCH_SPLIT(dev)) { - dev_priv->regfile.savePCH_DREF_CONTROL = I915_READ(PCH_DREF_CONTROL); - dev_priv->regfile.saveDISP_ARB_CTL = I915_READ(DISP_ARB_CTL); - } - - /* Pipe & plane A info */ - dev_priv->regfile.savePIPEACONF = I915_READ(_PIPEACONF); - dev_priv->regfile.savePIPEASRC = I915_READ(_PIPEASRC); - if (HAS_PCH_SPLIT(dev)) { - dev_priv->regfile.saveFPA0 = I915_READ(_PCH_FPA0); - dev_priv->regfile.saveFPA1 = I915_READ(_PCH_FPA1); - dev_priv->regfile.saveDPLL_A = I915_READ(_PCH_DPLL_A); - } else { - dev_priv->regfile.saveFPA0 = I915_READ(_FPA0); - dev_priv->regfile.saveFPA1 = I915_READ(_FPA1); - dev_priv->regfile.saveDPLL_A = I915_READ(_DPLL_A); - } - if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) - dev_priv->regfile.saveDPLL_A_MD = I915_READ(_DPLL_A_MD); - dev_priv->regfile.saveHTOTAL_A = I915_READ(_HTOTAL_A); - dev_priv->regfile.saveHBLANK_A = I915_READ(_HBLANK_A); - dev_priv->regfile.saveHSYNC_A = I915_READ(_HSYNC_A); - dev_priv->regfile.saveVTOTAL_A = I915_READ(_VTOTAL_A); - dev_priv->regfile.saveVBLANK_A = I915_READ(_VBLANK_A); - dev_priv->regfile.saveVSYNC_A = I915_READ(_VSYNC_A); - if (!HAS_PCH_SPLIT(dev)) - dev_priv->regfile.saveBCLRPAT_A = I915_READ(_BCLRPAT_A); - - if (HAS_PCH_SPLIT(dev)) { - dev_priv->regfile.savePIPEA_DATA_M1 = I915_READ(_PIPEA_DATA_M1); - dev_priv->regfile.savePIPEA_DATA_N1 = I915_READ(_PIPEA_DATA_N1); - dev_priv->regfile.savePIPEA_LINK_M1 = I915_READ(_PIPEA_LINK_M1); - dev_priv->regfile.savePIPEA_LINK_N1 = I915_READ(_PIPEA_LINK_N1); - - dev_priv->regfile.saveFDI_TXA_CTL = I915_READ(_FDI_TXA_CTL); - dev_priv->regfile.saveFDI_RXA_CTL = I915_READ(_FDI_RXA_CTL); - - dev_priv->regfile.savePFA_CTL_1 = I915_READ(_PFA_CTL_1); - dev_priv->regfile.savePFA_WIN_SZ = I915_READ(_PFA_WIN_SZ); - dev_priv->regfile.savePFA_WIN_POS = I915_READ(_PFA_WIN_POS); - - dev_priv->regfile.saveTRANSACONF = I915_READ(_TRANSACONF); - dev_priv->regfile.saveTRANS_HTOTAL_A = I915_READ(_TRANS_HTOTAL_A); - dev_priv->regfile.saveTRANS_HBLANK_A = I915_READ(_TRANS_HBLANK_A); - dev_priv->regfile.saveTRANS_HSYNC_A = I915_READ(_TRANS_HSYNC_A); - dev_priv->regfile.saveTRANS_VTOTAL_A = I915_READ(_TRANS_VTOTAL_A); - dev_priv->regfile.saveTRANS_VBLANK_A = I915_READ(_TRANS_VBLANK_A); - dev_priv->regfile.saveTRANS_VSYNC_A = I915_READ(_TRANS_VSYNC_A); - } - - dev_priv->regfile.saveDSPACNTR = I915_READ(_DSPACNTR); - dev_priv->regfile.saveDSPASTRIDE = I915_READ(_DSPASTRIDE); - dev_priv->regfile.saveDSPASIZE = I915_READ(_DSPASIZE); - dev_priv->regfile.saveDSPAPOS = I915_READ(_DSPAPOS); - dev_priv->regfile.saveDSPAADDR = I915_READ(_DSPAADDR); - if (INTEL_INFO(dev)->gen >= 4) { - dev_priv->regfile.saveDSPASURF = I915_READ(_DSPASURF); - dev_priv->regfile.saveDSPATILEOFF = I915_READ(_DSPATILEOFF); - } - i915_save_palette(dev, PIPE_A); - dev_priv->regfile.savePIPEASTAT = I915_READ(_PIPEASTAT); - - /* Pipe & plane B info */ - dev_priv->regfile.savePIPEBCONF = I915_READ(_PIPEBCONF); - dev_priv->regfile.savePIPEBSRC = I915_READ(_PIPEBSRC); - if (HAS_PCH_SPLIT(dev)) { - dev_priv->regfile.saveFPB0 = I915_READ(_PCH_FPB0); - dev_priv->regfile.saveFPB1 = I915_READ(_PCH_FPB1); - dev_priv->regfile.saveDPLL_B = I915_READ(_PCH_DPLL_B); - } else { - dev_priv->regfile.saveFPB0 = I915_READ(_FPB0); - dev_priv->regfile.saveFPB1 = I915_READ(_FPB1); - dev_priv->regfile.saveDPLL_B = I915_READ(_DPLL_B); - } - if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) - dev_priv->regfile.saveDPLL_B_MD = I915_READ(_DPLL_B_MD); - dev_priv->regfile.saveHTOTAL_B = I915_READ(_HTOTAL_B); - dev_priv->regfile.saveHBLANK_B = I915_READ(_HBLANK_B); - dev_priv->regfile.saveHSYNC_B = I915_READ(_HSYNC_B); - dev_priv->regfile.saveVTOTAL_B = I915_READ(_VTOTAL_B); - dev_priv->regfile.saveVBLANK_B = I915_READ(_VBLANK_B); - dev_priv->regfile.saveVSYNC_B = I915_READ(_VSYNC_B); - if (!HAS_PCH_SPLIT(dev)) - dev_priv->regfile.saveBCLRPAT_B = I915_READ(_BCLRPAT_B); - - if (HAS_PCH_SPLIT(dev)) { - dev_priv->regfile.savePIPEB_DATA_M1 = I915_READ(_PIPEB_DATA_M1); - dev_priv->regfile.savePIPEB_DATA_N1 = I915_READ(_PIPEB_DATA_N1); - dev_priv->regfile.savePIPEB_LINK_M1 = I915_READ(_PIPEB_LINK_M1); - dev_priv->regfile.savePIPEB_LINK_N1 = I915_READ(_PIPEB_LINK_N1); - - dev_priv->regfile.saveFDI_TXB_CTL = I915_READ(_FDI_TXB_CTL); - dev_priv->regfile.saveFDI_RXB_CTL = I915_READ(_FDI_RXB_CTL); - - dev_priv->regfile.savePFB_CTL_1 = I915_READ(_PFB_CTL_1); - dev_priv->regfile.savePFB_WIN_SZ = I915_READ(_PFB_WIN_SZ); - dev_priv->regfile.savePFB_WIN_POS = I915_READ(_PFB_WIN_POS); - - dev_priv->regfile.saveTRANSBCONF = I915_READ(_TRANSBCONF); - dev_priv->regfile.saveTRANS_HTOTAL_B = I915_READ(_TRANS_HTOTAL_B); - dev_priv->regfile.saveTRANS_HBLANK_B = I915_READ(_TRANS_HBLANK_B); - dev_priv->regfile.saveTRANS_HSYNC_B = I915_READ(_TRANS_HSYNC_B); - dev_priv->regfile.saveTRANS_VTOTAL_B = I915_READ(_TRANS_VTOTAL_B); - dev_priv->regfile.saveTRANS_VBLANK_B = I915_READ(_TRANS_VBLANK_B); - dev_priv->regfile.saveTRANS_VSYNC_B = I915_READ(_TRANS_VSYNC_B); - } - - dev_priv->regfile.saveDSPBCNTR = I915_READ(_DSPBCNTR); - dev_priv->regfile.saveDSPBSTRIDE = I915_READ(_DSPBSTRIDE); - dev_priv->regfile.saveDSPBSIZE = I915_READ(_DSPBSIZE); - dev_priv->regfile.saveDSPBPOS = I915_READ(_DSPBPOS); - dev_priv->regfile.saveDSPBADDR = I915_READ(_DSPBADDR); - if (INTEL_INFO(dev)->gen >= 4) { - dev_priv->regfile.saveDSPBSURF = I915_READ(_DSPBSURF); - dev_priv->regfile.saveDSPBTILEOFF = I915_READ(_DSPBTILEOFF); - } - i915_save_palette(dev, PIPE_B); - dev_priv->regfile.savePIPEBSTAT = I915_READ(_PIPEBSTAT); - - /* Fences */ - switch (INTEL_INFO(dev)->gen) { - case 7: - case 6: - for (i = 0; i < 16; i++) - dev_priv->regfile.saveFENCE[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8)); - break; - case 5: - case 4: - for (i = 0; i < 16; i++) - dev_priv->regfile.saveFENCE[i] = I915_READ64(FENCE_REG_965_0 + (i * 8)); - break; - case 3: - if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) - for (i = 0; i < 8; i++) - dev_priv->regfile.saveFENCE[i+8] = I915_READ(FENCE_REG_945_8 + (i * 4)); - case 2: - for (i = 0; i < 8; i++) - dev_priv->regfile.saveFENCE[i] = I915_READ(FENCE_REG_830_0 + (i * 4)); - break; - } - - /* CRT state */ - if (HAS_PCH_SPLIT(dev)) - dev_priv->regfile.saveADPA = I915_READ(PCH_ADPA); - else - dev_priv->regfile.saveADPA = I915_READ(ADPA); - - return; -} - -static void i915_restore_modeset_reg(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - int dpll_a_reg, fpa0_reg, fpa1_reg; - int dpll_b_reg, fpb0_reg, fpb1_reg; - int i; - - if (drm_core_check_feature(dev, DRIVER_MODESET)) - return; - - /* Fences */ - switch (INTEL_INFO(dev)->gen) { - case 7: - case 6: - for (i = 0; i < 16; i++) - I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (i * 8), dev_priv->regfile.saveFENCE[i]); - break; - case 5: - case 4: - for (i = 0; i < 16; i++) - I915_WRITE64(FENCE_REG_965_0 + (i * 8), dev_priv->regfile.saveFENCE[i]); - break; - case 3: - case 2: - if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) - for (i = 0; i < 8; i++) - I915_WRITE(FENCE_REG_945_8 + (i * 4), dev_priv->regfile.saveFENCE[i+8]); - for (i = 0; i < 8; i++) - I915_WRITE(FENCE_REG_830_0 + (i * 4), dev_priv->regfile.saveFENCE[i]); - break; - } - - - if (HAS_PCH_SPLIT(dev)) { - dpll_a_reg = _PCH_DPLL_A; - dpll_b_reg = _PCH_DPLL_B; - fpa0_reg = _PCH_FPA0; - fpb0_reg = _PCH_FPB0; - fpa1_reg = _PCH_FPA1; - fpb1_reg = _PCH_FPB1; - } else { - dpll_a_reg = _DPLL_A; - dpll_b_reg = _DPLL_B; - fpa0_reg = _FPA0; - fpb0_reg = _FPB0; - fpa1_reg = _FPA1; - fpb1_reg = _FPB1; - } - - if (HAS_PCH_SPLIT(dev)) { - I915_WRITE(PCH_DREF_CONTROL, dev_priv->regfile.savePCH_DREF_CONTROL); - I915_WRITE(DISP_ARB_CTL, dev_priv->regfile.saveDISP_ARB_CTL); - } - - /* Pipe & plane A info */ - /* Prime the clock */ - if (dev_priv->regfile.saveDPLL_A & DPLL_VCO_ENABLE) { - I915_WRITE(dpll_a_reg, dev_priv->regfile.saveDPLL_A & - ~DPLL_VCO_ENABLE); - POSTING_READ(dpll_a_reg); - udelay(150); - } - I915_WRITE(fpa0_reg, dev_priv->regfile.saveFPA0); - I915_WRITE(fpa1_reg, dev_priv->regfile.saveFPA1); - /* Actually enable it */ - I915_WRITE(dpll_a_reg, dev_priv->regfile.saveDPLL_A); - POSTING_READ(dpll_a_reg); - udelay(150); - if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) { - I915_WRITE(_DPLL_A_MD, dev_priv->regfile.saveDPLL_A_MD); - POSTING_READ(_DPLL_A_MD); - } - udelay(150); - - /* Restore mode */ - I915_WRITE(_HTOTAL_A, dev_priv->regfile.saveHTOTAL_A); - I915_WRITE(_HBLANK_A, dev_priv->regfile.saveHBLANK_A); - I915_WRITE(_HSYNC_A, dev_priv->regfile.saveHSYNC_A); - I915_WRITE(_VTOTAL_A, dev_priv->regfile.saveVTOTAL_A); - I915_WRITE(_VBLANK_A, dev_priv->regfile.saveVBLANK_A); - I915_WRITE(_VSYNC_A, dev_priv->regfile.saveVSYNC_A); - if (!HAS_PCH_SPLIT(dev)) - I915_WRITE(_BCLRPAT_A, dev_priv->regfile.saveBCLRPAT_A); - - if (HAS_PCH_SPLIT(dev)) { - I915_WRITE(_PIPEA_DATA_M1, dev_priv->regfile.savePIPEA_DATA_M1); - I915_WRITE(_PIPEA_DATA_N1, dev_priv->regfile.savePIPEA_DATA_N1); - I915_WRITE(_PIPEA_LINK_M1, dev_priv->regfile.savePIPEA_LINK_M1); - I915_WRITE(_PIPEA_LINK_N1, dev_priv->regfile.savePIPEA_LINK_N1); - - I915_WRITE(_FDI_RXA_CTL, dev_priv->regfile.saveFDI_RXA_CTL); - I915_WRITE(_FDI_TXA_CTL, dev_priv->regfile.saveFDI_TXA_CTL); - - I915_WRITE(_PFA_CTL_1, dev_priv->regfile.savePFA_CTL_1); - I915_WRITE(_PFA_WIN_SZ, dev_priv->regfile.savePFA_WIN_SZ); - I915_WRITE(_PFA_WIN_POS, dev_priv->regfile.savePFA_WIN_POS); - - I915_WRITE(_TRANSACONF, dev_priv->regfile.saveTRANSACONF); - I915_WRITE(_TRANS_HTOTAL_A, dev_priv->regfile.saveTRANS_HTOTAL_A); - I915_WRITE(_TRANS_HBLANK_A, dev_priv->regfile.saveTRANS_HBLANK_A); - I915_WRITE(_TRANS_HSYNC_A, dev_priv->regfile.saveTRANS_HSYNC_A); - I915_WRITE(_TRANS_VTOTAL_A, dev_priv->regfile.saveTRANS_VTOTAL_A); - I915_WRITE(_TRANS_VBLANK_A, dev_priv->regfile.saveTRANS_VBLANK_A); - I915_WRITE(_TRANS_VSYNC_A, dev_priv->regfile.saveTRANS_VSYNC_A); - } - - /* Restore plane info */ - I915_WRITE(_DSPASIZE, dev_priv->regfile.saveDSPASIZE); - I915_WRITE(_DSPAPOS, dev_priv->regfile.saveDSPAPOS); - I915_WRITE(_PIPEASRC, dev_priv->regfile.savePIPEASRC); - I915_WRITE(_DSPAADDR, dev_priv->regfile.saveDSPAADDR); - I915_WRITE(_DSPASTRIDE, dev_priv->regfile.saveDSPASTRIDE); - if (INTEL_INFO(dev)->gen >= 4) { - I915_WRITE(_DSPASURF, dev_priv->regfile.saveDSPASURF); - I915_WRITE(_DSPATILEOFF, dev_priv->regfile.saveDSPATILEOFF); - } - - I915_WRITE(_PIPEACONF, dev_priv->regfile.savePIPEACONF); - - i915_restore_palette(dev, PIPE_A); - /* Enable the plane */ - I915_WRITE(_DSPACNTR, dev_priv->regfile.saveDSPACNTR); - I915_WRITE(_DSPAADDR, I915_READ(_DSPAADDR)); - - /* Pipe & plane B info */ - if (dev_priv->regfile.saveDPLL_B & DPLL_VCO_ENABLE) { - I915_WRITE(dpll_b_reg, dev_priv->regfile.saveDPLL_B & - ~DPLL_VCO_ENABLE); - POSTING_READ(dpll_b_reg); - udelay(150); - } - I915_WRITE(fpb0_reg, dev_priv->regfile.saveFPB0); - I915_WRITE(fpb1_reg, dev_priv->regfile.saveFPB1); - /* Actually enable it */ - I915_WRITE(dpll_b_reg, dev_priv->regfile.saveDPLL_B); - POSTING_READ(dpll_b_reg); - udelay(150); - if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) { - I915_WRITE(_DPLL_B_MD, dev_priv->regfile.saveDPLL_B_MD); - POSTING_READ(_DPLL_B_MD); - } - udelay(150); - - /* Restore mode */ - I915_WRITE(_HTOTAL_B, dev_priv->regfile.saveHTOTAL_B); - I915_WRITE(_HBLANK_B, dev_priv->regfile.saveHBLANK_B); - I915_WRITE(_HSYNC_B, dev_priv->regfile.saveHSYNC_B); - I915_WRITE(_VTOTAL_B, dev_priv->regfile.saveVTOTAL_B); - I915_WRITE(_VBLANK_B, dev_priv->regfile.saveVBLANK_B); - I915_WRITE(_VSYNC_B, dev_priv->regfile.saveVSYNC_B); - if (!HAS_PCH_SPLIT(dev)) - I915_WRITE(_BCLRPAT_B, dev_priv->regfile.saveBCLRPAT_B); - - if (HAS_PCH_SPLIT(dev)) { - I915_WRITE(_PIPEB_DATA_M1, dev_priv->regfile.savePIPEB_DATA_M1); - I915_WRITE(_PIPEB_DATA_N1, dev_priv->regfile.savePIPEB_DATA_N1); - I915_WRITE(_PIPEB_LINK_M1, dev_priv->regfile.savePIPEB_LINK_M1); - I915_WRITE(_PIPEB_LINK_N1, dev_priv->regfile.savePIPEB_LINK_N1); - - I915_WRITE(_FDI_RXB_CTL, dev_priv->regfile.saveFDI_RXB_CTL); - I915_WRITE(_FDI_TXB_CTL, dev_priv->regfile.saveFDI_TXB_CTL); - - I915_WRITE(_PFB_CTL_1, dev_priv->regfile.savePFB_CTL_1); - I915_WRITE(_PFB_WIN_SZ, dev_priv->regfile.savePFB_WIN_SZ); - I915_WRITE(_PFB_WIN_POS, dev_priv->regfile.savePFB_WIN_POS); - - I915_WRITE(_TRANSBCONF, dev_priv->regfile.saveTRANSBCONF); - I915_WRITE(_TRANS_HTOTAL_B, dev_priv->regfile.saveTRANS_HTOTAL_B); - I915_WRITE(_TRANS_HBLANK_B, dev_priv->regfile.saveTRANS_HBLANK_B); - I915_WRITE(_TRANS_HSYNC_B, dev_priv->regfile.saveTRANS_HSYNC_B); - I915_WRITE(_TRANS_VTOTAL_B, dev_priv->regfile.saveTRANS_VTOTAL_B); - I915_WRITE(_TRANS_VBLANK_B, dev_priv->regfile.saveTRANS_VBLANK_B); - I915_WRITE(_TRANS_VSYNC_B, dev_priv->regfile.saveTRANS_VSYNC_B); - } - - /* Restore plane info */ - I915_WRITE(_DSPBSIZE, dev_priv->regfile.saveDSPBSIZE); - I915_WRITE(_DSPBPOS, dev_priv->regfile.saveDSPBPOS); - I915_WRITE(_PIPEBSRC, dev_priv->regfile.savePIPEBSRC); - I915_WRITE(_DSPBADDR, dev_priv->regfile.saveDSPBADDR); - I915_WRITE(_DSPBSTRIDE, dev_priv->regfile.saveDSPBSTRIDE); - if (INTEL_INFO(dev)->gen >= 4) { - I915_WRITE(_DSPBSURF, dev_priv->regfile.saveDSPBSURF); - I915_WRITE(_DSPBTILEOFF, dev_priv->regfile.saveDSPBTILEOFF); - } - - I915_WRITE(_PIPEBCONF, dev_priv->regfile.savePIPEBCONF); - - i915_restore_palette(dev, PIPE_B); - /* Enable the plane */ - I915_WRITE(_DSPBCNTR, dev_priv->regfile.saveDSPBCNTR); - I915_WRITE(_DSPBADDR, I915_READ(_DSPBADDR)); - - /* Cursor state */ - I915_WRITE(_CURAPOS, dev_priv->regfile.saveCURAPOS); - I915_WRITE(_CURACNTR, dev_priv->regfile.saveCURACNTR); - I915_WRITE(_CURABASE, dev_priv->regfile.saveCURABASE); - I915_WRITE(_CURBPOS, dev_priv->regfile.saveCURBPOS); - I915_WRITE(_CURBCNTR, dev_priv->regfile.saveCURBCNTR); - I915_WRITE(_CURBBASE, dev_priv->regfile.saveCURBBASE); - if (IS_GEN2(dev)) - I915_WRITE(CURSIZE, dev_priv->regfile.saveCURSIZE); - - /* CRT state */ - if (HAS_PCH_SPLIT(dev)) - I915_WRITE(PCH_ADPA, dev_priv->regfile.saveADPA); - else - I915_WRITE(ADPA, dev_priv->regfile.saveADPA); - - return; -} - static void i915_save_display(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; /* Display arbitration control */ - dev_priv->regfile.saveDSPARB = I915_READ(DSPARB); + if (INTEL_INFO(dev)->gen <= 4) + dev_priv->regfile.saveDSPARB = I915_READ(DSPARB); /* This is only meaningful in non-KMS mode */ /* Don't regfile.save them in KMS mode */ - i915_save_modeset_reg(dev); + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + i915_save_display_reg(dev); /* LVDS state */ if (HAS_PCH_SPLIT(dev)) { @@ -658,24 +234,6 @@ static void i915_save_display(struct drm_device *dev) dev_priv->regfile.savePP_DIVISOR = I915_READ(PP_DIVISOR); } - if (!drm_core_check_feature(dev, DRIVER_MODESET)) { - /* Display Port state */ - if (SUPPORTS_INTEGRATED_DP(dev)) { - dev_priv->regfile.saveDP_B = I915_READ(DP_B); - dev_priv->regfile.saveDP_C = I915_READ(DP_C); - dev_priv->regfile.saveDP_D = I915_READ(DP_D); - dev_priv->regfile.savePIPEA_GMCH_DATA_M = I915_READ(_PIPEA_GMCH_DATA_M); - dev_priv->regfile.savePIPEB_GMCH_DATA_M = I915_READ(_PIPEB_GMCH_DATA_M); - dev_priv->regfile.savePIPEA_GMCH_DATA_N = I915_READ(_PIPEA_GMCH_DATA_N); - dev_priv->regfile.savePIPEB_GMCH_DATA_N = I915_READ(_PIPEB_GMCH_DATA_N); - dev_priv->regfile.savePIPEA_DP_LINK_M = I915_READ(_PIPEA_DP_LINK_M); - dev_priv->regfile.savePIPEB_DP_LINK_M = I915_READ(_PIPEB_DP_LINK_M); - dev_priv->regfile.savePIPEA_DP_LINK_N = I915_READ(_PIPEA_DP_LINK_N); - dev_priv->regfile.savePIPEB_DP_LINK_N = I915_READ(_PIPEB_DP_LINK_N); - } - /* FIXME: regfile.save TV & SDVO state */ - } - /* Only regfile.save FBC state on the platform that supports FBC */ if (I915_HAS_FBC(dev)) { if (HAS_PCH_SPLIT(dev)) { @@ -690,16 +248,8 @@ static void i915_save_display(struct drm_device *dev) } } - /* VGA state */ - dev_priv->regfile.saveVGA0 = I915_READ(VGA0); - dev_priv->regfile.saveVGA1 = I915_READ(VGA1); - dev_priv->regfile.saveVGA_PD = I915_READ(VGA_PD); - if (HAS_PCH_SPLIT(dev)) - dev_priv->regfile.saveVGACNTRL = I915_READ(CPU_VGACNTRL); - else - dev_priv->regfile.saveVGACNTRL = I915_READ(VGACNTRL); - - i915_save_vga(dev); + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + i915_save_vga(dev); } static void i915_restore_display(struct drm_device *dev) @@ -707,25 +257,11 @@ static void i915_restore_display(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; /* Display arbitration */ - I915_WRITE(DSPARB, dev_priv->regfile.saveDSPARB); + if (INTEL_INFO(dev)->gen <= 4) + I915_WRITE(DSPARB, dev_priv->regfile.saveDSPARB); - if (!drm_core_check_feature(dev, DRIVER_MODESET)) { - /* Display port ratios (must be done before clock is set) */ - if (SUPPORTS_INTEGRATED_DP(dev)) { - I915_WRITE(_PIPEA_GMCH_DATA_M, dev_priv->regfile.savePIPEA_GMCH_DATA_M); - I915_WRITE(_PIPEB_GMCH_DATA_M, dev_priv->regfile.savePIPEB_GMCH_DATA_M); - I915_WRITE(_PIPEA_GMCH_DATA_N, dev_priv->regfile.savePIPEA_GMCH_DATA_N); - I915_WRITE(_PIPEB_GMCH_DATA_N, dev_priv->regfile.savePIPEB_GMCH_DATA_N); - I915_WRITE(_PIPEA_DP_LINK_M, dev_priv->regfile.savePIPEA_DP_LINK_M); - I915_WRITE(_PIPEB_DP_LINK_M, dev_priv->regfile.savePIPEB_DP_LINK_M); - I915_WRITE(_PIPEA_DP_LINK_N, dev_priv->regfile.savePIPEA_DP_LINK_N); - I915_WRITE(_PIPEB_DP_LINK_N, dev_priv->regfile.savePIPEB_DP_LINK_N); - } - } - - /* This is only meaningful in non-KMS mode */ - /* Don't restore them in KMS mode */ - i915_restore_modeset_reg(dev); + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + i915_restore_display_reg(dev); /* LVDS state */ if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) @@ -763,16 +299,6 @@ static void i915_restore_display(struct drm_device *dev) I915_WRITE(PP_CONTROL, dev_priv->regfile.savePP_CONTROL); } - if (!drm_core_check_feature(dev, DRIVER_MODESET)) { - /* Display Port state */ - if (SUPPORTS_INTEGRATED_DP(dev)) { - I915_WRITE(DP_B, dev_priv->regfile.saveDP_B); - I915_WRITE(DP_C, dev_priv->regfile.saveDP_C); - I915_WRITE(DP_D, dev_priv->regfile.saveDP_D); - } - /* FIXME: restore TV & SDVO state */ - } - /* only restore FBC info on the platform that supports FBC*/ intel_disable_fbc(dev); if (I915_HAS_FBC(dev)) { @@ -787,19 +313,11 @@ static void i915_restore_display(struct drm_device *dev) I915_WRITE(FBC_CONTROL, dev_priv->regfile.saveFBC_CONTROL); } } - /* VGA state */ - if (HAS_PCH_SPLIT(dev)) - I915_WRITE(CPU_VGACNTRL, dev_priv->regfile.saveVGACNTRL); - else - I915_WRITE(VGACNTRL, dev_priv->regfile.saveVGACNTRL); - I915_WRITE(VGA0, dev_priv->regfile.saveVGA0); - I915_WRITE(VGA1, dev_priv->regfile.saveVGA1); - I915_WRITE(VGA_PD, dev_priv->regfile.saveVGA_PD); - POSTING_READ(VGA_PD); - udelay(150); - - i915_restore_vga(dev); + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + i915_restore_vga(dev); + else + i915_redisable_vga(dev); } int i915_save_state(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/i915_ums.c b/drivers/gpu/drm/i915/i915_ums.c new file mode 100644 index 000000000000..985a09716237 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_ums.c @@ -0,0 +1,503 @@ +/* + * + * Copyright 2008 (c) Intel Corporation + * Jesse Barnes <jbarnes@virtuousgeek.org> + * Copyright 2013 (c) Intel Corporation + * Daniel Vetter <daniel.vetter@ffwll.ch> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS + * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. + * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR + * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, + * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE + * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + */ + +#include <drm/drmP.h> +#include <drm/i915_drm.h> +#include "intel_drv.h" +#include "i915_reg.h" + +static bool i915_pipe_enabled(struct drm_device *dev, enum pipe pipe) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 dpll_reg; + + /* On IVB, 3rd pipe shares PLL with another one */ + if (pipe > 1) + return false; + + if (HAS_PCH_SPLIT(dev)) + dpll_reg = _PCH_DPLL(pipe); + else + dpll_reg = (pipe == PIPE_A) ? _DPLL_A : _DPLL_B; + + return (I915_READ(dpll_reg) & DPLL_VCO_ENABLE); +} + +static void i915_save_palette(struct drm_device *dev, enum pipe pipe) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + unsigned long reg = (pipe == PIPE_A ? _PALETTE_A : _PALETTE_B); + u32 *array; + int i; + + if (!i915_pipe_enabled(dev, pipe)) + return; + + if (HAS_PCH_SPLIT(dev)) + reg = (pipe == PIPE_A) ? _LGC_PALETTE_A : _LGC_PALETTE_B; + + if (pipe == PIPE_A) + array = dev_priv->regfile.save_palette_a; + else + array = dev_priv->regfile.save_palette_b; + + for (i = 0; i < 256; i++) + array[i] = I915_READ(reg + (i << 2)); +} + +static void i915_restore_palette(struct drm_device *dev, enum pipe pipe) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + unsigned long reg = (pipe == PIPE_A ? _PALETTE_A : _PALETTE_B); + u32 *array; + int i; + + if (!i915_pipe_enabled(dev, pipe)) + return; + + if (HAS_PCH_SPLIT(dev)) + reg = (pipe == PIPE_A) ? _LGC_PALETTE_A : _LGC_PALETTE_B; + + if (pipe == PIPE_A) + array = dev_priv->regfile.save_palette_a; + else + array = dev_priv->regfile.save_palette_b; + + for (i = 0; i < 256; i++) + I915_WRITE(reg + (i << 2), array[i]); +} + +void i915_save_display_reg(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int i; + + /* Cursor state */ + dev_priv->regfile.saveCURACNTR = I915_READ(_CURACNTR); + dev_priv->regfile.saveCURAPOS = I915_READ(_CURAPOS); + dev_priv->regfile.saveCURABASE = I915_READ(_CURABASE); + dev_priv->regfile.saveCURBCNTR = I915_READ(_CURBCNTR); + dev_priv->regfile.saveCURBPOS = I915_READ(_CURBPOS); + dev_priv->regfile.saveCURBBASE = I915_READ(_CURBBASE); + if (IS_GEN2(dev)) + dev_priv->regfile.saveCURSIZE = I915_READ(CURSIZE); + + if (HAS_PCH_SPLIT(dev)) { + dev_priv->regfile.savePCH_DREF_CONTROL = I915_READ(PCH_DREF_CONTROL); + dev_priv->regfile.saveDISP_ARB_CTL = I915_READ(DISP_ARB_CTL); + } + + /* Pipe & plane A info */ + dev_priv->regfile.savePIPEACONF = I915_READ(_PIPEACONF); + dev_priv->regfile.savePIPEASRC = I915_READ(_PIPEASRC); + if (HAS_PCH_SPLIT(dev)) { + dev_priv->regfile.saveFPA0 = I915_READ(_PCH_FPA0); + dev_priv->regfile.saveFPA1 = I915_READ(_PCH_FPA1); + dev_priv->regfile.saveDPLL_A = I915_READ(_PCH_DPLL_A); + } else { + dev_priv->regfile.saveFPA0 = I915_READ(_FPA0); + dev_priv->regfile.saveFPA1 = I915_READ(_FPA1); + dev_priv->regfile.saveDPLL_A = I915_READ(_DPLL_A); + } + if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) + dev_priv->regfile.saveDPLL_A_MD = I915_READ(_DPLL_A_MD); + dev_priv->regfile.saveHTOTAL_A = I915_READ(_HTOTAL_A); + dev_priv->regfile.saveHBLANK_A = I915_READ(_HBLANK_A); + dev_priv->regfile.saveHSYNC_A = I915_READ(_HSYNC_A); + dev_priv->regfile.saveVTOTAL_A = I915_READ(_VTOTAL_A); + dev_priv->regfile.saveVBLANK_A = I915_READ(_VBLANK_A); + dev_priv->regfile.saveVSYNC_A = I915_READ(_VSYNC_A); + if (!HAS_PCH_SPLIT(dev)) + dev_priv->regfile.saveBCLRPAT_A = I915_READ(_BCLRPAT_A); + + if (HAS_PCH_SPLIT(dev)) { + dev_priv->regfile.savePIPEA_DATA_M1 = I915_READ(_PIPEA_DATA_M1); + dev_priv->regfile.savePIPEA_DATA_N1 = I915_READ(_PIPEA_DATA_N1); + dev_priv->regfile.savePIPEA_LINK_M1 = I915_READ(_PIPEA_LINK_M1); + dev_priv->regfile.savePIPEA_LINK_N1 = I915_READ(_PIPEA_LINK_N1); + + dev_priv->regfile.saveFDI_TXA_CTL = I915_READ(_FDI_TXA_CTL); + dev_priv->regfile.saveFDI_RXA_CTL = I915_READ(_FDI_RXA_CTL); + + dev_priv->regfile.savePFA_CTL_1 = I915_READ(_PFA_CTL_1); + dev_priv->regfile.savePFA_WIN_SZ = I915_READ(_PFA_WIN_SZ); + dev_priv->regfile.savePFA_WIN_POS = I915_READ(_PFA_WIN_POS); + + dev_priv->regfile.saveTRANSACONF = I915_READ(_TRANSACONF); + dev_priv->regfile.saveTRANS_HTOTAL_A = I915_READ(_TRANS_HTOTAL_A); + dev_priv->regfile.saveTRANS_HBLANK_A = I915_READ(_TRANS_HBLANK_A); + dev_priv->regfile.saveTRANS_HSYNC_A = I915_READ(_TRANS_HSYNC_A); + dev_priv->regfile.saveTRANS_VTOTAL_A = I915_READ(_TRANS_VTOTAL_A); + dev_priv->regfile.saveTRANS_VBLANK_A = I915_READ(_TRANS_VBLANK_A); + dev_priv->regfile.saveTRANS_VSYNC_A = I915_READ(_TRANS_VSYNC_A); + } + + dev_priv->regfile.saveDSPACNTR = I915_READ(_DSPACNTR); + dev_priv->regfile.saveDSPASTRIDE = I915_READ(_DSPASTRIDE); + dev_priv->regfile.saveDSPASIZE = I915_READ(_DSPASIZE); + dev_priv->regfile.saveDSPAPOS = I915_READ(_DSPAPOS); + dev_priv->regfile.saveDSPAADDR = I915_READ(_DSPAADDR); + if (INTEL_INFO(dev)->gen >= 4) { + dev_priv->regfile.saveDSPASURF = I915_READ(_DSPASURF); + dev_priv->regfile.saveDSPATILEOFF = I915_READ(_DSPATILEOFF); + } + i915_save_palette(dev, PIPE_A); + dev_priv->regfile.savePIPEASTAT = I915_READ(_PIPEASTAT); + + /* Pipe & plane B info */ + dev_priv->regfile.savePIPEBCONF = I915_READ(_PIPEBCONF); + dev_priv->regfile.savePIPEBSRC = I915_READ(_PIPEBSRC); + if (HAS_PCH_SPLIT(dev)) { + dev_priv->regfile.saveFPB0 = I915_READ(_PCH_FPB0); + dev_priv->regfile.saveFPB1 = I915_READ(_PCH_FPB1); + dev_priv->regfile.saveDPLL_B = I915_READ(_PCH_DPLL_B); + } else { + dev_priv->regfile.saveFPB0 = I915_READ(_FPB0); + dev_priv->regfile.saveFPB1 = I915_READ(_FPB1); + dev_priv->regfile.saveDPLL_B = I915_READ(_DPLL_B); + } + if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) + dev_priv->regfile.saveDPLL_B_MD = I915_READ(_DPLL_B_MD); + dev_priv->regfile.saveHTOTAL_B = I915_READ(_HTOTAL_B); + dev_priv->regfile.saveHBLANK_B = I915_READ(_HBLANK_B); + dev_priv->regfile.saveHSYNC_B = I915_READ(_HSYNC_B); + dev_priv->regfile.saveVTOTAL_B = I915_READ(_VTOTAL_B); + dev_priv->regfile.saveVBLANK_B = I915_READ(_VBLANK_B); + dev_priv->regfile.saveVSYNC_B = I915_READ(_VSYNC_B); + if (!HAS_PCH_SPLIT(dev)) + dev_priv->regfile.saveBCLRPAT_B = I915_READ(_BCLRPAT_B); + + if (HAS_PCH_SPLIT(dev)) { + dev_priv->regfile.savePIPEB_DATA_M1 = I915_READ(_PIPEB_DATA_M1); + dev_priv->regfile.savePIPEB_DATA_N1 = I915_READ(_PIPEB_DATA_N1); + dev_priv->regfile.savePIPEB_LINK_M1 = I915_READ(_PIPEB_LINK_M1); + dev_priv->regfile.savePIPEB_LINK_N1 = I915_READ(_PIPEB_LINK_N1); + + dev_priv->regfile.saveFDI_TXB_CTL = I915_READ(_FDI_TXB_CTL); + dev_priv->regfile.saveFDI_RXB_CTL = I915_READ(_FDI_RXB_CTL); + + dev_priv->regfile.savePFB_CTL_1 = I915_READ(_PFB_CTL_1); + dev_priv->regfile.savePFB_WIN_SZ = I915_READ(_PFB_WIN_SZ); + dev_priv->regfile.savePFB_WIN_POS = I915_READ(_PFB_WIN_POS); + + dev_priv->regfile.saveTRANSBCONF = I915_READ(_TRANSBCONF); + dev_priv->regfile.saveTRANS_HTOTAL_B = I915_READ(_TRANS_HTOTAL_B); + dev_priv->regfile.saveTRANS_HBLANK_B = I915_READ(_TRANS_HBLANK_B); + dev_priv->regfile.saveTRANS_HSYNC_B = I915_READ(_TRANS_HSYNC_B); + dev_priv->regfile.saveTRANS_VTOTAL_B = I915_READ(_TRANS_VTOTAL_B); + dev_priv->regfile.saveTRANS_VBLANK_B = I915_READ(_TRANS_VBLANK_B); + dev_priv->regfile.saveTRANS_VSYNC_B = I915_READ(_TRANS_VSYNC_B); + } + + dev_priv->regfile.saveDSPBCNTR = I915_READ(_DSPBCNTR); + dev_priv->regfile.saveDSPBSTRIDE = I915_READ(_DSPBSTRIDE); + dev_priv->regfile.saveDSPBSIZE = I915_READ(_DSPBSIZE); + dev_priv->regfile.saveDSPBPOS = I915_READ(_DSPBPOS); + dev_priv->regfile.saveDSPBADDR = I915_READ(_DSPBADDR); + if (INTEL_INFO(dev)->gen >= 4) { + dev_priv->regfile.saveDSPBSURF = I915_READ(_DSPBSURF); + dev_priv->regfile.saveDSPBTILEOFF = I915_READ(_DSPBTILEOFF); + } + i915_save_palette(dev, PIPE_B); + dev_priv->regfile.savePIPEBSTAT = I915_READ(_PIPEBSTAT); + + /* Fences */ + switch (INTEL_INFO(dev)->gen) { + case 7: + case 6: + for (i = 0; i < 16; i++) + dev_priv->regfile.saveFENCE[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8)); + break; + case 5: + case 4: + for (i = 0; i < 16; i++) + dev_priv->regfile.saveFENCE[i] = I915_READ64(FENCE_REG_965_0 + (i * 8)); + break; + case 3: + if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) + for (i = 0; i < 8; i++) + dev_priv->regfile.saveFENCE[i+8] = I915_READ(FENCE_REG_945_8 + (i * 4)); + case 2: + for (i = 0; i < 8; i++) + dev_priv->regfile.saveFENCE[i] = I915_READ(FENCE_REG_830_0 + (i * 4)); + break; + } + + /* CRT state */ + if (HAS_PCH_SPLIT(dev)) + dev_priv->regfile.saveADPA = I915_READ(PCH_ADPA); + else + dev_priv->regfile.saveADPA = I915_READ(ADPA); + + /* Display Port state */ + if (SUPPORTS_INTEGRATED_DP(dev)) { + dev_priv->regfile.saveDP_B = I915_READ(DP_B); + dev_priv->regfile.saveDP_C = I915_READ(DP_C); + dev_priv->regfile.saveDP_D = I915_READ(DP_D); + dev_priv->regfile.savePIPEA_GMCH_DATA_M = I915_READ(_PIPEA_GMCH_DATA_M); + dev_priv->regfile.savePIPEB_GMCH_DATA_M = I915_READ(_PIPEB_GMCH_DATA_M); + dev_priv->regfile.savePIPEA_GMCH_DATA_N = I915_READ(_PIPEA_GMCH_DATA_N); + dev_priv->regfile.savePIPEB_GMCH_DATA_N = I915_READ(_PIPEB_GMCH_DATA_N); + dev_priv->regfile.savePIPEA_DP_LINK_M = I915_READ(_PIPEA_DP_LINK_M); + dev_priv->regfile.savePIPEB_DP_LINK_M = I915_READ(_PIPEB_DP_LINK_M); + dev_priv->regfile.savePIPEA_DP_LINK_N = I915_READ(_PIPEA_DP_LINK_N); + dev_priv->regfile.savePIPEB_DP_LINK_N = I915_READ(_PIPEB_DP_LINK_N); + } + /* FIXME: regfile.save TV & SDVO state */ + + return; +} + +void i915_restore_display_reg(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int dpll_a_reg, fpa0_reg, fpa1_reg; + int dpll_b_reg, fpb0_reg, fpb1_reg; + int i; + + /* Display port ratios (must be done before clock is set) */ + if (SUPPORTS_INTEGRATED_DP(dev)) { + I915_WRITE(_PIPEA_GMCH_DATA_M, dev_priv->regfile.savePIPEA_GMCH_DATA_M); + I915_WRITE(_PIPEB_GMCH_DATA_M, dev_priv->regfile.savePIPEB_GMCH_DATA_M); + I915_WRITE(_PIPEA_GMCH_DATA_N, dev_priv->regfile.savePIPEA_GMCH_DATA_N); + I915_WRITE(_PIPEB_GMCH_DATA_N, dev_priv->regfile.savePIPEB_GMCH_DATA_N); + I915_WRITE(_PIPEA_DP_LINK_M, dev_priv->regfile.savePIPEA_DP_LINK_M); + I915_WRITE(_PIPEB_DP_LINK_M, dev_priv->regfile.savePIPEB_DP_LINK_M); + I915_WRITE(_PIPEA_DP_LINK_N, dev_priv->regfile.savePIPEA_DP_LINK_N); + I915_WRITE(_PIPEB_DP_LINK_N, dev_priv->regfile.savePIPEB_DP_LINK_N); + } + + /* Fences */ + switch (INTEL_INFO(dev)->gen) { + case 7: + case 6: + for (i = 0; i < 16; i++) + I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (i * 8), dev_priv->regfile.saveFENCE[i]); + break; + case 5: + case 4: + for (i = 0; i < 16; i++) + I915_WRITE64(FENCE_REG_965_0 + (i * 8), dev_priv->regfile.saveFENCE[i]); + break; + case 3: + case 2: + if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) + for (i = 0; i < 8; i++) + I915_WRITE(FENCE_REG_945_8 + (i * 4), dev_priv->regfile.saveFENCE[i+8]); + for (i = 0; i < 8; i++) + I915_WRITE(FENCE_REG_830_0 + (i * 4), dev_priv->regfile.saveFENCE[i]); + break; + } + + + if (HAS_PCH_SPLIT(dev)) { + dpll_a_reg = _PCH_DPLL_A; + dpll_b_reg = _PCH_DPLL_B; + fpa0_reg = _PCH_FPA0; + fpb0_reg = _PCH_FPB0; + fpa1_reg = _PCH_FPA1; + fpb1_reg = _PCH_FPB1; + } else { + dpll_a_reg = _DPLL_A; + dpll_b_reg = _DPLL_B; + fpa0_reg = _FPA0; + fpb0_reg = _FPB0; + fpa1_reg = _FPA1; + fpb1_reg = _FPB1; + } + + if (HAS_PCH_SPLIT(dev)) { + I915_WRITE(PCH_DREF_CONTROL, dev_priv->regfile.savePCH_DREF_CONTROL); + I915_WRITE(DISP_ARB_CTL, dev_priv->regfile.saveDISP_ARB_CTL); + } + + /* Pipe & plane A info */ + /* Prime the clock */ + if (dev_priv->regfile.saveDPLL_A & DPLL_VCO_ENABLE) { + I915_WRITE(dpll_a_reg, dev_priv->regfile.saveDPLL_A & + ~DPLL_VCO_ENABLE); + POSTING_READ(dpll_a_reg); + udelay(150); + } + I915_WRITE(fpa0_reg, dev_priv->regfile.saveFPA0); + I915_WRITE(fpa1_reg, dev_priv->regfile.saveFPA1); + /* Actually enable it */ + I915_WRITE(dpll_a_reg, dev_priv->regfile.saveDPLL_A); + POSTING_READ(dpll_a_reg); + udelay(150); + if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) { + I915_WRITE(_DPLL_A_MD, dev_priv->regfile.saveDPLL_A_MD); + POSTING_READ(_DPLL_A_MD); + } + udelay(150); + + /* Restore mode */ + I915_WRITE(_HTOTAL_A, dev_priv->regfile.saveHTOTAL_A); + I915_WRITE(_HBLANK_A, dev_priv->regfile.saveHBLANK_A); + I915_WRITE(_HSYNC_A, dev_priv->regfile.saveHSYNC_A); + I915_WRITE(_VTOTAL_A, dev_priv->regfile.saveVTOTAL_A); + I915_WRITE(_VBLANK_A, dev_priv->regfile.saveVBLANK_A); + I915_WRITE(_VSYNC_A, dev_priv->regfile.saveVSYNC_A); + if (!HAS_PCH_SPLIT(dev)) + I915_WRITE(_BCLRPAT_A, dev_priv->regfile.saveBCLRPAT_A); + + if (HAS_PCH_SPLIT(dev)) { + I915_WRITE(_PIPEA_DATA_M1, dev_priv->regfile.savePIPEA_DATA_M1); + I915_WRITE(_PIPEA_DATA_N1, dev_priv->regfile.savePIPEA_DATA_N1); + I915_WRITE(_PIPEA_LINK_M1, dev_priv->regfile.savePIPEA_LINK_M1); + I915_WRITE(_PIPEA_LINK_N1, dev_priv->regfile.savePIPEA_LINK_N1); + + I915_WRITE(_FDI_RXA_CTL, dev_priv->regfile.saveFDI_RXA_CTL); + I915_WRITE(_FDI_TXA_CTL, dev_priv->regfile.saveFDI_TXA_CTL); + + I915_WRITE(_PFA_CTL_1, dev_priv->regfile.savePFA_CTL_1); + I915_WRITE(_PFA_WIN_SZ, dev_priv->regfile.savePFA_WIN_SZ); + I915_WRITE(_PFA_WIN_POS, dev_priv->regfile.savePFA_WIN_POS); + + I915_WRITE(_TRANSACONF, dev_priv->regfile.saveTRANSACONF); + I915_WRITE(_TRANS_HTOTAL_A, dev_priv->regfile.saveTRANS_HTOTAL_A); + I915_WRITE(_TRANS_HBLANK_A, dev_priv->regfile.saveTRANS_HBLANK_A); + I915_WRITE(_TRANS_HSYNC_A, dev_priv->regfile.saveTRANS_HSYNC_A); + I915_WRITE(_TRANS_VTOTAL_A, dev_priv->regfile.saveTRANS_VTOTAL_A); + I915_WRITE(_TRANS_VBLANK_A, dev_priv->regfile.saveTRANS_VBLANK_A); + I915_WRITE(_TRANS_VSYNC_A, dev_priv->regfile.saveTRANS_VSYNC_A); + } + + /* Restore plane info */ + I915_WRITE(_DSPASIZE, dev_priv->regfile.saveDSPASIZE); + I915_WRITE(_DSPAPOS, dev_priv->regfile.saveDSPAPOS); + I915_WRITE(_PIPEASRC, dev_priv->regfile.savePIPEASRC); + I915_WRITE(_DSPAADDR, dev_priv->regfile.saveDSPAADDR); + I915_WRITE(_DSPASTRIDE, dev_priv->regfile.saveDSPASTRIDE); + if (INTEL_INFO(dev)->gen >= 4) { + I915_WRITE(_DSPASURF, dev_priv->regfile.saveDSPASURF); + I915_WRITE(_DSPATILEOFF, dev_priv->regfile.saveDSPATILEOFF); + } + + I915_WRITE(_PIPEACONF, dev_priv->regfile.savePIPEACONF); + + i915_restore_palette(dev, PIPE_A); + /* Enable the plane */ + I915_WRITE(_DSPACNTR, dev_priv->regfile.saveDSPACNTR); + I915_WRITE(_DSPAADDR, I915_READ(_DSPAADDR)); + + /* Pipe & plane B info */ + if (dev_priv->regfile.saveDPLL_B & DPLL_VCO_ENABLE) { + I915_WRITE(dpll_b_reg, dev_priv->regfile.saveDPLL_B & + ~DPLL_VCO_ENABLE); + POSTING_READ(dpll_b_reg); + udelay(150); + } + I915_WRITE(fpb0_reg, dev_priv->regfile.saveFPB0); + I915_WRITE(fpb1_reg, dev_priv->regfile.saveFPB1); + /* Actually enable it */ + I915_WRITE(dpll_b_reg, dev_priv->regfile.saveDPLL_B); + POSTING_READ(dpll_b_reg); + udelay(150); + if (INTEL_INFO(dev)->gen >= 4 && !HAS_PCH_SPLIT(dev)) { + I915_WRITE(_DPLL_B_MD, dev_priv->regfile.saveDPLL_B_MD); + POSTING_READ(_DPLL_B_MD); + } + udelay(150); + + /* Restore mode */ + I915_WRITE(_HTOTAL_B, dev_priv->regfile.saveHTOTAL_B); + I915_WRITE(_HBLANK_B, dev_priv->regfile.saveHBLANK_B); + I915_WRITE(_HSYNC_B, dev_priv->regfile.saveHSYNC_B); + I915_WRITE(_VTOTAL_B, dev_priv->regfile.saveVTOTAL_B); + I915_WRITE(_VBLANK_B, dev_priv->regfile.saveVBLANK_B); + I915_WRITE(_VSYNC_B, dev_priv->regfile.saveVSYNC_B); + if (!HAS_PCH_SPLIT(dev)) + I915_WRITE(_BCLRPAT_B, dev_priv->regfile.saveBCLRPAT_B); + + if (HAS_PCH_SPLIT(dev)) { + I915_WRITE(_PIPEB_DATA_M1, dev_priv->regfile.savePIPEB_DATA_M1); + I915_WRITE(_PIPEB_DATA_N1, dev_priv->regfile.savePIPEB_DATA_N1); + I915_WRITE(_PIPEB_LINK_M1, dev_priv->regfile.savePIPEB_LINK_M1); + I915_WRITE(_PIPEB_LINK_N1, dev_priv->regfile.savePIPEB_LINK_N1); + + I915_WRITE(_FDI_RXB_CTL, dev_priv->regfile.saveFDI_RXB_CTL); + I915_WRITE(_FDI_TXB_CTL, dev_priv->regfile.saveFDI_TXB_CTL); + + I915_WRITE(_PFB_CTL_1, dev_priv->regfile.savePFB_CTL_1); + I915_WRITE(_PFB_WIN_SZ, dev_priv->regfile.savePFB_WIN_SZ); + I915_WRITE(_PFB_WIN_POS, dev_priv->regfile.savePFB_WIN_POS); + + I915_WRITE(_TRANSBCONF, dev_priv->regfile.saveTRANSBCONF); + I915_WRITE(_TRANS_HTOTAL_B, dev_priv->regfile.saveTRANS_HTOTAL_B); + I915_WRITE(_TRANS_HBLANK_B, dev_priv->regfile.saveTRANS_HBLANK_B); + I915_WRITE(_TRANS_HSYNC_B, dev_priv->regfile.saveTRANS_HSYNC_B); + I915_WRITE(_TRANS_VTOTAL_B, dev_priv->regfile.saveTRANS_VTOTAL_B); + I915_WRITE(_TRANS_VBLANK_B, dev_priv->regfile.saveTRANS_VBLANK_B); + I915_WRITE(_TRANS_VSYNC_B, dev_priv->regfile.saveTRANS_VSYNC_B); + } + + /* Restore plane info */ + I915_WRITE(_DSPBSIZE, dev_priv->regfile.saveDSPBSIZE); + I915_WRITE(_DSPBPOS, dev_priv->regfile.saveDSPBPOS); + I915_WRITE(_PIPEBSRC, dev_priv->regfile.savePIPEBSRC); + I915_WRITE(_DSPBADDR, dev_priv->regfile.saveDSPBADDR); + I915_WRITE(_DSPBSTRIDE, dev_priv->regfile.saveDSPBSTRIDE); + if (INTEL_INFO(dev)->gen >= 4) { + I915_WRITE(_DSPBSURF, dev_priv->regfile.saveDSPBSURF); + I915_WRITE(_DSPBTILEOFF, dev_priv->regfile.saveDSPBTILEOFF); + } + + I915_WRITE(_PIPEBCONF, dev_priv->regfile.savePIPEBCONF); + + i915_restore_palette(dev, PIPE_B); + /* Enable the plane */ + I915_WRITE(_DSPBCNTR, dev_priv->regfile.saveDSPBCNTR); + I915_WRITE(_DSPBADDR, I915_READ(_DSPBADDR)); + + /* Cursor state */ + I915_WRITE(_CURAPOS, dev_priv->regfile.saveCURAPOS); + I915_WRITE(_CURACNTR, dev_priv->regfile.saveCURACNTR); + I915_WRITE(_CURABASE, dev_priv->regfile.saveCURABASE); + I915_WRITE(_CURBPOS, dev_priv->regfile.saveCURBPOS); + I915_WRITE(_CURBCNTR, dev_priv->regfile.saveCURBCNTR); + I915_WRITE(_CURBBASE, dev_priv->regfile.saveCURBBASE); + if (IS_GEN2(dev)) + I915_WRITE(CURSIZE, dev_priv->regfile.saveCURSIZE); + + /* CRT state */ + if (HAS_PCH_SPLIT(dev)) + I915_WRITE(PCH_ADPA, dev_priv->regfile.saveADPA); + else + I915_WRITE(ADPA, dev_priv->regfile.saveADPA); + + /* Display Port state */ + if (SUPPORTS_INTEGRATED_DP(dev)) { + I915_WRITE(DP_B, dev_priv->regfile.saveDP_B); + I915_WRITE(DP_C, dev_priv->regfile.saveDP_C); + I915_WRITE(DP_D, dev_priv->regfile.saveDP_D); + } + /* FIXME: restore TV & SDVO state */ + + return; +} diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 71a5ebad14fb..68e79f32e100 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -267,27 +267,27 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector) crt->force_hotplug_required = 0; - save_adpa = adpa = I915_READ(PCH_ADPA); + save_adpa = adpa = I915_READ(crt->adpa_reg); DRM_DEBUG_KMS("trigger hotplug detect cycle: adpa=0x%x\n", adpa); adpa |= ADPA_CRT_HOTPLUG_FORCE_TRIGGER; if (turn_off_dac) adpa &= ~ADPA_DAC_ENABLE; - I915_WRITE(PCH_ADPA, adpa); + I915_WRITE(crt->adpa_reg, adpa); - if (wait_for((I915_READ(PCH_ADPA) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0, + if (wait_for((I915_READ(crt->adpa_reg) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0, 1000)) DRM_DEBUG_KMS("timed out waiting for FORCE_TRIGGER"); if (turn_off_dac) { - I915_WRITE(PCH_ADPA, save_adpa); - POSTING_READ(PCH_ADPA); + I915_WRITE(crt->adpa_reg, save_adpa); + POSTING_READ(crt->adpa_reg); } } /* Check the status to see if both blue and green are on now */ - adpa = I915_READ(PCH_ADPA); + adpa = I915_READ(crt->adpa_reg); if ((adpa & ADPA_CRT_HOTPLUG_MONITOR_MASK) != 0) ret = true; else @@ -300,26 +300,27 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector) static bool valleyview_crt_detect_hotplug(struct drm_connector *connector) { struct drm_device *dev = connector->dev; + struct intel_crt *crt = intel_attached_crt(connector); struct drm_i915_private *dev_priv = dev->dev_private; u32 adpa; bool ret; u32 save_adpa; - save_adpa = adpa = I915_READ(ADPA); + save_adpa = adpa = I915_READ(crt->adpa_reg); DRM_DEBUG_KMS("trigger hotplug detect cycle: adpa=0x%x\n", adpa); adpa |= ADPA_CRT_HOTPLUG_FORCE_TRIGGER; - I915_WRITE(ADPA, adpa); + I915_WRITE(crt->adpa_reg, adpa); - if (wait_for((I915_READ(ADPA) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0, + if (wait_for((I915_READ(crt->adpa_reg) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) == 0, 1000)) { DRM_DEBUG_KMS("timed out waiting for FORCE_TRIGGER"); - I915_WRITE(ADPA, save_adpa); + I915_WRITE(crt->adpa_reg, save_adpa); } /* Check the status to see if both blue and green are on now */ - adpa = I915_READ(ADPA); + adpa = I915_READ(crt->adpa_reg); if ((adpa & ADPA_CRT_HOTPLUG_MONITOR_MASK) != 0) ret = true; else @@ -665,11 +666,11 @@ static void intel_crt_reset(struct drm_connector *connector) if (HAS_PCH_SPLIT(dev)) { u32 adpa; - adpa = I915_READ(PCH_ADPA); + adpa = I915_READ(crt->adpa_reg); adpa &= ~ADPA_CRT_HOTPLUG_MASK; adpa |= ADPA_HOTPLUG_BITS; - I915_WRITE(PCH_ADPA, adpa); - POSTING_READ(PCH_ADPA); + I915_WRITE(crt->adpa_reg, adpa); + POSTING_READ(crt->adpa_reg); DRM_DEBUG_KMS("pch crt adpa set to 0x%x\n", adpa); crt->force_hotplug_required = 1; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 2e904a5cd6cb..cedf4ab5ff16 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -677,6 +677,7 @@ static void intel_ddi_mode_set(struct drm_encoder *encoder, DRM_DEBUG_KMS("Preparing DDI mode for Haswell on port %c, pipe %c\n", port_name(port), pipe_name(pipe)); + intel_crtc->eld_vld = false; if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); @@ -987,7 +988,13 @@ void intel_ddi_enable_pipe_func(struct drm_crtc *crtc) if (cpu_transcoder == TRANSCODER_EDP) { switch (pipe) { case PIPE_A: - temp |= TRANS_DDI_EDP_INPUT_A_ONOFF; + /* Can only use the always-on power well for eDP when + * not using the panel fitter, and when not using motion + * blur mitigation (which we don't support). */ + if (dev_priv->pch_pf_size) + temp |= TRANS_DDI_EDP_INPUT_A_ONOFF; + else + temp |= TRANS_DDI_EDP_INPUT_A_ON; break; case PIPE_B: temp |= TRANS_DDI_EDP_INPUT_B_ONOFF; @@ -1287,10 +1294,14 @@ static void intel_ddi_post_disable(struct intel_encoder *intel_encoder) static void intel_enable_ddi(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; + struct drm_crtc *crtc = encoder->crtc; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + int pipe = intel_crtc->pipe; struct drm_device *dev = encoder->dev; struct drm_i915_private *dev_priv = dev->dev_private; enum port port = intel_ddi_get_encoder_port(intel_encoder); int type = intel_encoder->type; + uint32_t tmp; if (type == INTEL_OUTPUT_HDMI) { /* In HDMI/DVI mode, the port width, and swing/emphasis values @@ -1303,18 +1314,34 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder) ironlake_edp_backlight_on(intel_dp); } + + if (intel_crtc->eld_vld) { + tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); + tmp |= ((AUDIO_OUTPUT_ENABLE_A | AUDIO_ELD_VALID_A) << (pipe * 4)); + I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp); + } } static void intel_disable_ddi(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; + struct drm_crtc *crtc = encoder->crtc; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + int pipe = intel_crtc->pipe; int type = intel_encoder->type; + struct drm_device *dev = encoder->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t tmp; if (type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); ironlake_edp_backlight_off(intel_dp); } + + tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); + tmp &= ~((AUDIO_OUTPUT_ENABLE_A | AUDIO_ELD_VALID_A) << (pipe * 4)); + I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp); } int intel_ddi_get_cdclk_freq(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 53ec6cb0ffdb..0dfecaf599ff 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1214,9 +1214,15 @@ void assert_pipe(struct drm_i915_private *dev_priv, if (pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) state = true; - reg = PIPECONF(cpu_transcoder); - val = I915_READ(reg); - cur_state = !!(val & PIPECONF_ENABLE); + if (IS_HASWELL(dev_priv->dev) && cpu_transcoder != TRANSCODER_EDP && + !(I915_READ(HSW_PWR_WELL_DRIVER) & HSW_PWR_WELL_ENABLE)) { + cur_state = false; + } else { + reg = PIPECONF(cpu_transcoder); + val = I915_READ(reg); + cur_state = !!(val & PIPECONF_ENABLE); + } + WARN(cur_state != state, "pipe %c assertion failure (expected %s, current %s)\n", pipe_name(pipe), state_string(state), state_string(cur_state)); @@ -2220,8 +2226,10 @@ intel_finish_fb(struct drm_framebuffer *old_fb) bool was_interruptible = dev_priv->mm.interruptible; int ret; + WARN_ON(waitqueue_active(&dev_priv->pending_flip_queue)); + wait_event(dev_priv->pending_flip_queue, - atomic_read(&dev_priv->mm.wedged) || + i915_reset_in_progress(&dev_priv->gpu_error) || atomic_read(&obj->pending_flip) == 0); /* Big Hammer, we also need to ensure that any pending @@ -2869,7 +2877,7 @@ static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc) unsigned long flags; bool pending; - if (atomic_read(&dev_priv->mm.wedged)) + if (i915_reset_in_progress(&dev_priv->gpu_error)) return false; spin_lock_irqsave(&dev->event_lock, flags); @@ -2887,6 +2895,8 @@ static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) if (crtc->fb == NULL) return; + WARN_ON(waitqueue_active(&dev_priv->pending_flip_queue)); + wait_event(dev_priv->pending_flip_queue, !intel_crtc_has_pending_flip(crtc)); @@ -3717,10 +3727,12 @@ static void intel_crtc_disable(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct drm_connector *connector; struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); /* crtc should still be enabled when we disable it. */ WARN_ON(!crtc->enabled); + intel_crtc->eld_vld = false; dev_priv->display.crtc_disable(crtc); intel_crtc_update_sarea(crtc, false); dev_priv->display.off(crtc); @@ -4867,6 +4879,8 @@ static void lpt_init_pch_refclk(struct drm_device *dev) if (!has_vga) return; + mutex_lock(&dev_priv->dpio_lock); + /* XXX: Rip out SDV support once Haswell ships for real. */ if (IS_HASWELL(dev) && (dev->pci_device & 0xFF00) == 0x0C00) is_sdv = true; @@ -5009,6 +5023,8 @@ static void lpt_init_pch_refclk(struct drm_device *dev) tmp = intel_sbi_read(dev_priv, SBI_DBUFF0, SBI_ICLK); tmp |= SBI_DBUFF0_ENABLE; intel_sbi_write(dev_priv, SBI_DBUFF0, tmp, SBI_ICLK); + + mutex_unlock(&dev_priv->dpio_lock); } /* @@ -5092,6 +5108,11 @@ static void ironlake_set_pipeconf(struct drm_crtc *crtc, else val |= PIPECONF_PROGRESSIVE; + if (adjusted_mode->private_flags & INTEL_MODE_LIMITED_COLOR_RANGE) + val |= PIPECONF_COLOR_RANGE_SELECT; + else + val &= ~PIPECONF_COLOR_RANGE_SELECT; + I915_WRITE(PIPECONF(pipe), val); POSTING_READ(PIPECONF(pipe)); } @@ -5586,6 +5607,35 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, return fdi_config_ok ? ret : -EINVAL; } +static void haswell_modeset_global_resources(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + bool enable = false; + struct intel_crtc *crtc; + struct intel_encoder *encoder; + + list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + if (crtc->pipe != PIPE_A && crtc->base.enabled) + enable = true; + /* XXX: Should check for edp transcoder here, but thanks to init + * sequence that's not yet available. Just in case desktop eDP + * on PORT D is possible on haswell, too. */ + } + + list_for_each_entry(encoder, &dev->mode_config.encoder_list, + base.head) { + if (encoder->type != INTEL_OUTPUT_EDP && + encoder->connectors_active) + enable = true; + } + + /* Even the eDP panel fitter is outside the always-on well. */ + if (dev_priv->pch_pf_size) + enable = true; + + intel_set_power_well(dev, enable); +} + static int haswell_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode, @@ -5618,11 +5668,6 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc, num_connectors++; } - if (is_cpu_edp) - intel_crtc->cpu_transcoder = TRANSCODER_EDP; - else - intel_crtc->cpu_transcoder = pipe; - /* We are not sure yet this won't happen. */ WARN(!HAS_PCH_LPT(dev), "Unexpected PCH type %d\n", INTEL_PCH_TYPE(dev)); @@ -5687,6 +5732,11 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, int pipe = intel_crtc->pipe; int ret; + if (IS_HASWELL(dev) && intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP)) + intel_crtc->cpu_transcoder = TRANSCODER_EDP; + else + intel_crtc->cpu_transcoder = pipe; + drm_vblank_pre_modeset(dev, pipe); ret = dev_priv->display.crtc_mode_set(crtc, mode, adjusted_mode, @@ -5783,6 +5833,7 @@ static void haswell_write_eld(struct drm_connector *connector, struct drm_i915_private *dev_priv = connector->dev->dev_private; uint8_t *eld = connector->eld; struct drm_device *dev = crtc->dev; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); uint32_t eldv; uint32_t i; int len; @@ -5824,6 +5875,7 @@ static void haswell_write_eld(struct drm_connector *connector, DRM_DEBUG_DRIVER("ELD on pipe %c\n", pipe_name(pipe)); eldv = AUDIO_ELD_VALID_A << (pipe * 4); + intel_crtc->eld_vld = true; if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) { DRM_DEBUG_DRIVER("ELD: DisplayPort detected\n"); @@ -6717,11 +6769,6 @@ void intel_mark_busy(struct drm_device *dev) void intel_mark_idle(struct drm_device *dev) { -} - -void intel_mark_fb_busy(struct drm_i915_gem_object *obj) -{ - struct drm_device *dev = obj->base.dev; struct drm_crtc *crtc; if (!i915_powersave) @@ -6731,12 +6778,11 @@ void intel_mark_fb_busy(struct drm_i915_gem_object *obj) if (!crtc->fb) continue; - if (to_intel_framebuffer(crtc->fb)->obj == obj) - intel_increase_pllclock(crtc); + intel_decrease_pllclock(crtc); } } -void intel_mark_fb_idle(struct drm_i915_gem_object *obj) +void intel_mark_fb_busy(struct drm_i915_gem_object *obj) { struct drm_device *dev = obj->base.dev; struct drm_crtc *crtc; @@ -6749,7 +6795,7 @@ void intel_mark_fb_idle(struct drm_i915_gem_object *obj) continue; if (to_intel_framebuffer(crtc->fb)->obj == obj) - intel_decrease_pllclock(crtc); + intel_increase_pllclock(crtc); } } @@ -6833,7 +6879,7 @@ static void do_intel_finish_page_flip(struct drm_device *dev, obj = work->old_fb_obj; - wake_up(&dev_priv->pending_flip_queue); + wake_up_all(&dev_priv->pending_flip_queue); queue_work(dev_priv->wq, &work->work); @@ -8219,23 +8265,18 @@ 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)) { - int found; - /* Check for built-in panel first. Shares lanes with HDMI on SDVOC */ - if (I915_READ(DP_C) & DP_DETECTED) - intel_dp_init(dev, DP_C, PORT_C); + if (I915_READ(VLV_DISPLAY_BASE + DP_C) & DP_DETECTED) + intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C); - if (I915_READ(SDVOB) & PORT_DETECTED) { - /* SDVOB multiplex with HDMIB */ - found = intel_sdvo_init(dev, SDVOB, true); - if (!found) - intel_hdmi_init(dev, SDVOB, PORT_B); - if (!found && (I915_READ(DP_B) & DP_DETECTED)) - intel_dp_init(dev, DP_B, PORT_B); + if (I915_READ(VLV_DISPLAY_BASE + SDVOB) & PORT_DETECTED) { + intel_hdmi_init(dev, VLV_DISPLAY_BASE + SDVOB, PORT_B); + if (I915_READ(VLV_DISPLAY_BASE + DP_B) & DP_DETECTED) + intel_dp_init(dev, VLV_DISPLAY_BASE + DP_B, PORT_B); } - if (I915_READ(SDVOC) & PORT_DETECTED) - intel_hdmi_init(dev, SDVOC, PORT_C); + if (I915_READ(VLV_DISPLAY_BASE + SDVOC) & PORT_DETECTED) + intel_hdmi_init(dev, VLV_DISPLAY_BASE + SDVOC, PORT_C); } else if (SUPPORTS_DIGITAL_OUTPUTS(dev)) { bool found = false; @@ -8495,6 +8536,8 @@ static void intel_init_display(struct drm_device *dev) } else if (IS_HASWELL(dev)) { dev_priv->display.fdi_link_train = hsw_fdi_link_train; dev_priv->display.write_eld = haswell_write_eld; + dev_priv->display.modeset_global_resources = + haswell_modeset_global_resources; } } else if (IS_G4X(dev)) { dev_priv->display.write_eld = g4x_write_eld; @@ -8617,6 +8660,15 @@ static struct intel_quirk intel_quirks[] = { /* Acer Aspire 5734Z must invert backlight brightness */ { 0x2a42, 0x1025, 0x0459, quirk_invert_brightness }, + + /* Acer/eMachines G725 */ + { 0x2a42, 0x1025, 0x0210, quirk_invert_brightness }, + + /* Acer/eMachines e725 */ + { 0x2a42, 0x1025, 0x0212, quirk_invert_brightness }, + + /* Acer/Packard Bell NCL20 */ + { 0x2a42, 0x1025, 0x034b, quirk_invert_brightness }, }; static void intel_init_quirks(struct drm_device *dev) @@ -8645,12 +8697,7 @@ static void i915_disable_vga(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; u8 sr1; - u32 vga_reg; - - if (HAS_PCH_SPLIT(dev)) - vga_reg = CPU_VGACNTRL; - else - vga_reg = VGACNTRL; + u32 vga_reg = i915_vgacntrl_reg(dev); vga_get_uninterruptible(dev->pdev, VGA_RSRC_LEGACY_IO); outb(SR01, VGA_SR_INDEX); @@ -8665,10 +8712,7 @@ static void i915_disable_vga(struct drm_device *dev) void intel_modeset_init_hw(struct drm_device *dev) { - /* We attempt to init the necessary power wells early in the initialization - * time, so the subsystems that expect power to be enabled can work. - */ - intel_init_power_wells(dev); + intel_init_power_well(dev); intel_prepare_ddi(dev); @@ -8710,7 +8754,7 @@ void intel_modeset_init(struct drm_device *dev) dev->mode_config.max_width = 8192; dev->mode_config.max_height = 8192; } - dev->mode_config.fb_base = dev_priv->mm.gtt_base_addr; + dev->mode_config.fb_base = dev_priv->gtt.mappable_base; DRM_DEBUG_KMS("%d display pipe%s available.\n", dev_priv->num_pipe, dev_priv->num_pipe > 1 ? "s" : ""); @@ -8912,20 +8956,14 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) * the crtc fixup. */ } -static void i915_redisable_vga(struct drm_device *dev) +void i915_redisable_vga(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - u32 vga_reg; - - if (HAS_PCH_SPLIT(dev)) - vga_reg = CPU_VGACNTRL; - else - vga_reg = VGACNTRL; + u32 vga_reg = i915_vgacntrl_reg(dev); if (I915_READ(vga_reg) != VGA_DISP_DISABLE) { DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n"); - I915_WRITE(vga_reg, VGA_DISP_DISABLE); - POSTING_READ(vga_reg); + i915_disable_vga(dev); } } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index e64c75727702..15afcf86ad67 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -763,6 +763,22 @@ intel_dp_mode_fixup(struct drm_encoder *encoder, return false; bpp = adjusted_mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 24; + + if (intel_dp->color_range_auto) { + /* + * See: + * CEA-861-E - 5.1 Default Encoding Parameters + * VESA DisplayPort Ver.1.2a - 5.1.1.1 Video Colorimetry + */ + if (bpp != 18 && drm_mode_cea_vic(adjusted_mode) > 1) + intel_dp->color_range = DP_COLOR_RANGE_16_235; + else + intel_dp->color_range = 0; + } + + if (intel_dp->color_range) + adjusted_mode->private_flags |= INTEL_MODE_LIMITED_COLOR_RANGE; + mode_rate = intel_dp_link_required(adjusted_mode->clock, bpp); for (clock = 0; clock <= max_clock; clock++) { @@ -967,7 +983,8 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, else intel_dp->DP |= DP_PLL_FREQ_270MHZ; } else if (!HAS_PCH_CPT(dev) || is_cpu_edp(intel_dp)) { - intel_dp->DP |= intel_dp->color_range; + if (!HAS_PCH_SPLIT(dev)) + intel_dp->DP |= intel_dp->color_range; if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC) intel_dp->DP |= DP_SYNC_HS_HIGH; @@ -1770,14 +1787,18 @@ intel_dp_set_link_train(struct intel_dp *intel_dp, temp &= ~DP_TP_CTL_LINK_TRAIN_MASK; switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) { case DP_TRAINING_PATTERN_DISABLE: - temp |= DP_TP_CTL_LINK_TRAIN_IDLE; - I915_WRITE(DP_TP_CTL(port), temp); - if (wait_for((I915_READ(DP_TP_STATUS(port)) & - DP_TP_STATUS_IDLE_DONE), 1)) - DRM_ERROR("Timed out waiting for DP idle patterns\n"); + if (port != PORT_A) { + temp |= DP_TP_CTL_LINK_TRAIN_IDLE; + I915_WRITE(DP_TP_CTL(port), temp); + + if (wait_for((I915_READ(DP_TP_STATUS(port)) & + DP_TP_STATUS_IDLE_DONE), 1)) + DRM_ERROR("Timed out waiting for DP idle patterns\n"); + + temp &= ~DP_TP_CTL_LINK_TRAIN_MASK; + } - temp &= ~DP_TP_CTL_LINK_TRAIN_MASK; temp |= DP_TP_CTL_LINK_TRAIN_NORMAL; break; @@ -2276,16 +2297,17 @@ g4x_dp_detect(struct intel_dp *intel_dp) { struct drm_device *dev = intel_dp_to_dev(intel_dp); struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); uint32_t bit; - switch (intel_dp->output_reg) { - case DP_B: + switch (intel_dig_port->port) { + case PORT_B: bit = DPB_HOTPLUG_LIVE_STATUS; break; - case DP_C: + case PORT_C: bit = DPC_HOTPLUG_LIVE_STATUS; break; - case DP_D: + case PORT_D: bit = DPD_HOTPLUG_LIVE_STATUS; break; default: @@ -2459,10 +2481,21 @@ intel_dp_set_property(struct drm_connector *connector, } if (property == dev_priv->broadcast_rgb_property) { - if (val == !!intel_dp->color_range) - return 0; - - intel_dp->color_range = val ? DP_COLOR_RANGE_16_235 : 0; + switch (val) { + case INTEL_BROADCAST_RGB_AUTO: + intel_dp->color_range_auto = true; + break; + case INTEL_BROADCAST_RGB_FULL: + intel_dp->color_range_auto = false; + intel_dp->color_range = 0; + break; + case INTEL_BROADCAST_RGB_LIMITED: + intel_dp->color_range_auto = false; + intel_dp->color_range = DP_COLOR_RANGE_16_235; + break; + default: + return -EINVAL; + } goto done; } @@ -2603,6 +2636,7 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect intel_attach_force_audio_property(connector); intel_attach_broadcast_rgb_property(connector); + intel_dp->color_range_auto = true; if (is_edp(intel_dp)) { drm_mode_create_scaling_mode_property(connector->dev); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 54a034c82061..13afb37d8dec 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -109,6 +109,11 @@ * timings in the mode to prevent the crtc fixup from overwriting them. * Currently only lvds needs that. */ #define INTEL_MODE_CRTC_TIMINGS_SET (0x20) +/* + * Set when limited 16-235 (as opposed to full 0-255) RGB color range is + * to be used. + */ +#define INTEL_MODE_LIMITED_COLOR_RANGE (0x40) static inline void intel_mode_set_pixel_multiplier(struct drm_display_mode *mode, @@ -206,6 +211,7 @@ struct intel_crtc { * some outputs connected to this crtc. */ bool active; + bool eld_vld; bool primary_disabled; /* is the crtc obscured by a plane? */ bool lowfreq_avail; struct intel_overlay *overlay; @@ -284,6 +290,9 @@ struct cxsr_latency { #define DIP_LEN_AVI 13 #define DIP_AVI_PR_1 0 #define DIP_AVI_PR_2 1 +#define DIP_AVI_RGB_QUANT_RANGE_DEFAULT (0 << 2) +#define DIP_AVI_RGB_QUANT_RANGE_LIMITED (1 << 2) +#define DIP_AVI_RGB_QUANT_RANGE_FULL (2 << 2) #define DIP_TYPE_SPD 0x83 #define DIP_VERSION_SPD 0x1 @@ -338,9 +347,11 @@ struct intel_hdmi { u32 sdvox_reg; int ddc_bus; uint32_t color_range; + bool color_range_auto; bool has_hdmi_sink; bool has_audio; enum hdmi_force_audio force_audio; + bool rgb_quant_range_selectable; void (*write_infoframe)(struct drm_encoder *encoder, struct dip_infoframe *frame); void (*set_infoframes)(struct drm_encoder *encoder, @@ -357,6 +368,7 @@ struct intel_dp { bool has_audio; enum hdmi_force_audio force_audio; uint32_t color_range; + bool color_range_auto; uint8_t link_bw; uint8_t lane_count; uint8_t dpcd[DP_RECEIVER_CAP_SIZE]; @@ -440,9 +452,8 @@ extern bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, extern void intel_dvo_init(struct drm_device *dev); extern void intel_tv_init(struct drm_device *dev); extern void intel_mark_busy(struct drm_device *dev); -extern void intel_mark_idle(struct drm_device *dev); extern void intel_mark_fb_busy(struct drm_i915_gem_object *obj); -extern void intel_mark_fb_idle(struct drm_i915_gem_object *obj); +extern void intel_mark_idle(struct drm_device *dev); extern bool intel_lvds_init(struct drm_device *dev); extern bool intel_is_dual_link_lvds(struct drm_device *dev); extern void intel_dp_init(struct drm_device *dev, int output_reg, @@ -655,7 +666,8 @@ extern void intel_update_fbc(struct drm_device *dev); extern void intel_gpu_ips_init(struct drm_i915_private *dev_priv); extern void intel_gpu_ips_teardown(void); -extern void intel_init_power_wells(struct drm_device *dev); +extern void intel_init_power_well(struct drm_device *dev); +extern void intel_set_power_well(struct drm_device *dev, bool enable); extern void intel_enable_gt_powersave(struct drm_device *dev); extern void intel_disable_gt_powersave(struct drm_device *dev); extern void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index 755c27450a2c..1c510da04d16 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -135,14 +135,13 @@ static int intelfb_create(struct intel_fbdev *ifbdev, goto out_unpin; } info->apertures->ranges[0].base = dev->mode_config.fb_base; - info->apertures->ranges[0].size = - dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; + info->apertures->ranges[0].size = dev_priv->gtt.mappable_end; info->fix.smem_start = dev->mode_config.fb_base + obj->gtt_offset; info->fix.smem_len = size; info->screen_base = - ioremap_wc(dev_priv->mm.gtt_base_addr + obj->gtt_offset, + ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset, size); if (!info->screen_base) { ret = -ENOSPC; @@ -306,7 +305,8 @@ void intel_fb_restore_mode(struct drm_device *dev) /* Be sure to shut off any planes that may be active */ list_for_each_entry(plane, &config->plane_list, head) - plane->funcs->disable_plane(plane); + if (plane->enabled) + plane->funcs->disable_plane(plane); drm_modeset_unlock_all(dev); } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 6387f9b0df99..5b4efd64c2f9 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -331,6 +331,7 @@ static void intel_set_infoframe(struct drm_encoder *encoder, static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder, struct drm_display_mode *adjusted_mode) { + struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); struct dip_infoframe avi_if = { .type = DIP_TYPE_AVI, .ver = DIP_VERSION_AVI, @@ -340,6 +341,13 @@ static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder, if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) avi_if.body.avi.YQ_CN_PR |= DIP_AVI_PR_2; + if (intel_hdmi->rgb_quant_range_selectable) { + if (adjusted_mode->private_flags & INTEL_MODE_LIMITED_COLOR_RANGE) + avi_if.body.avi.ITC_EC_Q_SC |= DIP_AVI_RGB_QUANT_RANGE_LIMITED; + else + avi_if.body.avi.ITC_EC_Q_SC |= DIP_AVI_RGB_QUANT_RANGE_FULL; + } + avi_if.body.avi.VIC = drm_mode_cea_vic(adjusted_mode); intel_set_infoframe(encoder, &avi_if); @@ -364,7 +372,8 @@ static void g4x_set_infoframes(struct drm_encoder *encoder, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; - struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); + struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi; u32 reg = VIDEO_DIP_CTL; u32 val = I915_READ(reg); u32 port; @@ -391,11 +400,11 @@ static void g4x_set_infoframes(struct drm_encoder *encoder, return; } - switch (intel_hdmi->sdvox_reg) { - case SDVOB: + switch (intel_dig_port->port) { + case PORT_B: port = VIDEO_DIP_PORT_B; break; - case SDVOC: + case PORT_C: port = VIDEO_DIP_PORT_C; break; default: @@ -428,7 +437,8 @@ static void ibx_set_infoframes(struct drm_encoder *encoder, { struct drm_i915_private *dev_priv = encoder->dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc); - struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); + struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi; u32 reg = TVIDEO_DIP_CTL(intel_crtc->pipe); u32 val = I915_READ(reg); u32 port; @@ -447,14 +457,14 @@ static void ibx_set_infoframes(struct drm_encoder *encoder, return; } - switch (intel_hdmi->sdvox_reg) { - case HDMIB: + switch (intel_dig_port->port) { + case PORT_B: port = VIDEO_DIP_PORT_B; break; - case HDMIC: + case PORT_C: port = VIDEO_DIP_PORT_C; break; - case HDMID: + case PORT_D: port = VIDEO_DIP_PORT_D; break; default: @@ -766,6 +776,20 @@ bool intel_hdmi_mode_fixup(struct drm_encoder *encoder, const struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode) { + struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + + if (intel_hdmi->color_range_auto) { + /* See CEA-861-E - 5.1 Default Encoding Parameters */ + if (intel_hdmi->has_hdmi_sink && + drm_mode_cea_vic(adjusted_mode) > 1) + intel_hdmi->color_range = SDVO_COLOR_RANGE_16_235; + else + intel_hdmi->color_range = 0; + } + + if (intel_hdmi->color_range) + adjusted_mode->private_flags |= INTEL_MODE_LIMITED_COLOR_RANGE; + return true; } @@ -773,13 +797,14 @@ static bool g4x_hdmi_connected(struct intel_hdmi *intel_hdmi) { struct drm_device *dev = intel_hdmi_to_dev(intel_hdmi); struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_digital_port *intel_dig_port = hdmi_to_dig_port(intel_hdmi); uint32_t bit; - switch (intel_hdmi->sdvox_reg) { - case SDVOB: + switch (intel_dig_port->port) { + case PORT_B: bit = HDMIB_HOTPLUG_LIVE_STATUS; break; - case SDVOC: + case PORT_C: bit = HDMIC_HOTPLUG_LIVE_STATUS; break; default: @@ -811,6 +836,7 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) intel_hdmi->has_hdmi_sink = false; intel_hdmi->has_audio = false; + intel_hdmi->rgb_quant_range_selectable = false; edid = drm_get_edid(connector, intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus)); @@ -822,6 +848,8 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) intel_hdmi->has_hdmi_sink = drm_detect_hdmi_monitor(edid); intel_hdmi->has_audio = drm_detect_monitor_audio(edid); + intel_hdmi->rgb_quant_range_selectable = + drm_rgb_quant_range_selectable(edid); } kfree(edid); } @@ -907,10 +935,21 @@ intel_hdmi_set_property(struct drm_connector *connector, } if (property == dev_priv->broadcast_rgb_property) { - if (val == !!intel_hdmi->color_range) - return 0; - - intel_hdmi->color_range = val ? SDVO_COLOR_RANGE_16_235 : 0; + switch (val) { + case INTEL_BROADCAST_RGB_AUTO: + intel_hdmi->color_range_auto = true; + break; + case INTEL_BROADCAST_RGB_FULL: + intel_hdmi->color_range_auto = false; + intel_hdmi->color_range = 0; + break; + case INTEL_BROADCAST_RGB_LIMITED: + intel_hdmi->color_range_auto = false; + intel_hdmi->color_range = SDVO_COLOR_RANGE_16_235; + break; + default: + return -EINVAL; + } goto done; } @@ -959,6 +998,7 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c { intel_attach_force_audio_property(connector); intel_attach_broadcast_rgb_property(connector); + intel_hdmi->color_range_auto = true; } void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 7f0904170963..acf8aec9ada7 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -515,6 +515,8 @@ int intel_setup_gmbus(struct drm_device *dev) if (HAS_PCH_SPLIT(dev)) dev_priv->gpio_mmio_base = PCH_GPIOA - GPIOA; + else if (IS_VALLEYVIEW(dev)) + dev_priv->gpio_mmio_base = VLV_DISPLAY_BASE; else dev_priv->gpio_mmio_base = 0; diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index 49249bb97485..0e860f39933d 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -100,8 +100,9 @@ intel_attach_force_audio_property(struct drm_connector *connector) } static const struct drm_prop_enum_list broadcast_rgb_names[] = { - { 0, "Full" }, - { 1, "Limited 16:235" }, + { INTEL_BROADCAST_RGB_AUTO, "Automatic" }, + { INTEL_BROADCAST_RGB_FULL, "Full" }, + { INTEL_BROADCAST_RGB_LIMITED, "Limited 16:235" }, }; void diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index 7741c22c934c..4d338740f2cb 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -347,7 +347,7 @@ static void intel_didl_outputs(struct drm_device *dev) int i = 0; handle = DEVICE_ACPI_HANDLE(&dev->pdev->dev); - if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &acpi_dev))) + if (!handle || acpi_bus_get_device(handle, &acpi_dev)) return; if (acpi_is_video_device(acpi_dev)) diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index 1e901c3c18af..67a2501d519d 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -195,7 +195,7 @@ intel_overlay_map_regs(struct intel_overlay *overlay) if (OVERLAY_NEEDS_PHYSICAL(overlay->dev)) regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_obj->handle->vaddr; else - regs = io_mapping_map_wc(dev_priv->mm.gtt_mapping, + regs = io_mapping_map_wc(dev_priv->gtt.mappable, overlay->reg_bo->gtt_offset); return regs; @@ -1434,7 +1434,7 @@ intel_overlay_map_regs_atomic(struct intel_overlay *overlay) regs = (struct overlay_registers __iomem *) overlay->reg_bo->phys_obj->handle->vaddr; else - regs = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, + regs = io_mapping_map_atomic_wc(dev_priv->gtt.mappable, overlay->reg_bo->gtt_offset); return regs; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index ca9734529229..f7f67360e740 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3687,6 +3687,10 @@ static void gen7_setup_fixed_func_scheduler(struct drm_i915_private *dev_priv) reg |= GEN7_FF_VS_SCHED_HW; reg |= GEN7_FF_DS_SCHED_HW; + /* WaVSRefCountFullforceMissDisable */ + if (IS_HASWELL(dev_priv->dev)) + reg &= ~GEN7_FF_VS_REF_CNT_FFME; + I915_WRITE(GEN7_FF_THREAD_MODE, reg); } @@ -4050,35 +4054,57 @@ void intel_init_clock_gating(struct drm_device *dev) dev_priv->display.init_clock_gating(dev); } -/* Starting with Haswell, we have different power wells for - * different parts of the GPU. This attempts to enable them all. - */ -void intel_init_power_wells(struct drm_device *dev) +void intel_set_power_well(struct drm_device *dev, bool enable) { struct drm_i915_private *dev_priv = dev->dev_private; - unsigned long power_wells[] = { - HSW_PWR_WELL_CTL1, - HSW_PWR_WELL_CTL2, - HSW_PWR_WELL_CTL4 - }; - int i; + bool is_enabled, enable_requested; + uint32_t tmp; if (!IS_HASWELL(dev)) return; - mutex_lock(&dev->struct_mutex); + tmp = I915_READ(HSW_PWR_WELL_DRIVER); + is_enabled = tmp & HSW_PWR_WELL_STATE; + enable_requested = tmp & HSW_PWR_WELL_ENABLE; - for (i = 0; i < ARRAY_SIZE(power_wells); i++) { - int well = I915_READ(power_wells[i]); + if (enable) { + if (!enable_requested) + I915_WRITE(HSW_PWR_WELL_DRIVER, HSW_PWR_WELL_ENABLE); - if ((well & HSW_PWR_WELL_STATE) == 0) { - I915_WRITE(power_wells[i], well & HSW_PWR_WELL_ENABLE); - if (wait_for((I915_READ(power_wells[i]) & HSW_PWR_WELL_STATE), 20)) - DRM_ERROR("Error enabling power well %lx\n", power_wells[i]); + if (!is_enabled) { + DRM_DEBUG_KMS("Enabling power well\n"); + if (wait_for((I915_READ(HSW_PWR_WELL_DRIVER) & + HSW_PWR_WELL_STATE), 20)) + DRM_ERROR("Timeout enabling power well\n"); + } + } else { + if (enable_requested) { + I915_WRITE(HSW_PWR_WELL_DRIVER, 0); + DRM_DEBUG_KMS("Requesting to disable the power well\n"); } } +} - mutex_unlock(&dev->struct_mutex); +/* + * Starting with Haswell, we have a "Power Down Well" that can be turned off + * when not needed anymore. We have 4 registers that can request the power well + * to be enabled, and it will only be disabled if none of the registers is + * requesting it to be enabled. + */ +void intel_init_power_well(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (!IS_HASWELL(dev)) + return; + + /* For now, we need the power well to be always enabled. */ + intel_set_power_well(dev, true); + + /* We're taking over the BIOS, so clear any requests made by it since + * the driver is in charge now. */ + if (I915_READ(HSW_PWR_WELL_BIOS) & HSW_PWR_WELL_ENABLE) + I915_WRITE(HSW_PWR_WELL_BIOS, 0); } /* Set up chip specific power management-related functions */ diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 59e02691baf3..dc6ae2fa1cee 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1203,7 +1203,7 @@ static int intel_init_ring_buffer(struct drm_device *dev, goto err_unpin; ring->virtual_start = - ioremap_wc(dev_priv->mm.gtt->gma_bus_addr + obj->gtt_offset, + ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset, ring->size); if (ring->virtual_start == NULL) { DRM_ERROR("Failed to map ringbuffer.\n"); @@ -1223,8 +1223,6 @@ static int intel_init_ring_buffer(struct drm_device *dev, if (IS_I830(ring->dev) || IS_845G(ring->dev)) ring->effective_size -= 128; - intel_ring_init_seqno(ring, dev_priv->last_seqno); - return 0; err_unmap: @@ -1371,7 +1369,8 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) msleep(1); - ret = i915_gem_check_wedge(dev_priv, dev_priv->mm.interruptible); + ret = i915_gem_check_wedge(&dev_priv->gpu_error, + dev_priv->mm.interruptible); if (ret) return ret; } while (!time_after(jiffies, end)); @@ -1460,7 +1459,8 @@ int intel_ring_begin(struct intel_ring_buffer *ring, drm_i915_private_t *dev_priv = ring->dev->dev_private; int ret; - ret = i915_gem_check_wedge(dev_priv, dev_priv->mm.interruptible); + ret = i915_gem_check_wedge(&dev_priv->gpu_error, + dev_priv->mm.interruptible); if (ret) return ret; @@ -1491,7 +1491,7 @@ void intel_ring_advance(struct intel_ring_buffer *ring) struct drm_i915_private *dev_priv = ring->dev->dev_private; ring->tail &= ring->size - 1; - if (dev_priv->stop_rings & intel_ring_flag(ring)) + if (dev_priv->gpu_error.stop_rings & intel_ring_flag(ring)) return; ring->write_tail(ring, ring->tail); } diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 153377bed66a..f01063a2323a 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -103,6 +103,7 @@ struct intel_sdvo { * It is only valid when using TMDS encoding and 8 bit per color mode. */ uint32_t color_range; + bool color_range_auto; /** * This is set if we're going to treat the device as TV-out. @@ -125,6 +126,7 @@ struct intel_sdvo { bool is_hdmi; bool has_hdmi_monitor; bool has_hdmi_audio; + bool rgb_quant_range_selectable; /** * This is set if we detect output of sdvo device as LVDS and @@ -946,7 +948,8 @@ static bool intel_sdvo_write_infoframe(struct intel_sdvo *intel_sdvo, &tx_rate, 1); } -static bool intel_sdvo_set_avi_infoframe(struct intel_sdvo *intel_sdvo) +static bool intel_sdvo_set_avi_infoframe(struct intel_sdvo *intel_sdvo, + const struct drm_display_mode *adjusted_mode) { struct dip_infoframe avi_if = { .type = DIP_TYPE_AVI, @@ -955,6 +958,13 @@ static bool intel_sdvo_set_avi_infoframe(struct intel_sdvo *intel_sdvo) }; uint8_t sdvo_data[4 + sizeof(avi_if.body.avi)]; + if (intel_sdvo->rgb_quant_range_selectable) { + if (adjusted_mode->private_flags & INTEL_MODE_LIMITED_COLOR_RANGE) + avi_if.body.avi.ITC_EC_Q_SC |= DIP_AVI_RGB_QUANT_RANGE_LIMITED; + else + avi_if.body.avi.ITC_EC_Q_SC |= DIP_AVI_RGB_QUANT_RANGE_FULL; + } + intel_dip_infoframe_csum(&avi_if); /* sdvo spec says that the ecc is handled by the hw, and it looks like @@ -1064,6 +1074,18 @@ static bool intel_sdvo_mode_fixup(struct drm_encoder *encoder, multiplier = intel_sdvo_get_pixel_multiplier(adjusted_mode); intel_mode_set_pixel_multiplier(adjusted_mode, multiplier); + if (intel_sdvo->color_range_auto) { + /* See CEA-861-E - 5.1 Default Encoding Parameters */ + if (intel_sdvo->has_hdmi_monitor && + drm_mode_cea_vic(adjusted_mode) > 1) + intel_sdvo->color_range = SDVO_COLOR_RANGE_16_235; + else + intel_sdvo->color_range = 0; + } + + if (intel_sdvo->color_range) + adjusted_mode->private_flags |= INTEL_MODE_LIMITED_COLOR_RANGE; + return true; } @@ -1121,7 +1143,7 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder, intel_sdvo_set_encode(intel_sdvo, SDVO_ENCODE_HDMI); intel_sdvo_set_colorimetry(intel_sdvo, SDVO_COLORIMETRY_RGB256); - intel_sdvo_set_avi_infoframe(intel_sdvo); + intel_sdvo_set_avi_infoframe(intel_sdvo, adjusted_mode); } else intel_sdvo_set_encode(intel_sdvo, SDVO_ENCODE_DVI); @@ -1153,7 +1175,7 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder, /* The real mode polarity is set by the SDVO commands, using * struct intel_sdvo_dtd. */ sdvox = SDVO_VSYNC_ACTIVE_HIGH | SDVO_HSYNC_ACTIVE_HIGH; - if (intel_sdvo->is_hdmi) + if (!HAS_PCH_SPLIT(dev) && intel_sdvo->is_hdmi) sdvox |= intel_sdvo->color_range; if (INTEL_INFO(dev)->gen < 5) sdvox |= SDVO_BORDER_ENABLE; @@ -1513,6 +1535,8 @@ intel_sdvo_tmds_sink_detect(struct drm_connector *connector) if (intel_sdvo->is_hdmi) { intel_sdvo->has_hdmi_monitor = drm_detect_hdmi_monitor(edid); intel_sdvo->has_hdmi_audio = drm_detect_monitor_audio(edid); + intel_sdvo->rgb_quant_range_selectable = + drm_rgb_quant_range_selectable(edid); } } else status = connector_status_disconnected; @@ -1564,6 +1588,7 @@ intel_sdvo_detect(struct drm_connector *connector, bool force) intel_sdvo->has_hdmi_monitor = false; intel_sdvo->has_hdmi_audio = false; + intel_sdvo->rgb_quant_range_selectable = false; if ((intel_sdvo_connector->output_flag & response) == 0) ret = connector_status_disconnected; @@ -1897,10 +1922,21 @@ intel_sdvo_set_property(struct drm_connector *connector, } if (property == dev_priv->broadcast_rgb_property) { - if (val == !!intel_sdvo->color_range) - return 0; - - intel_sdvo->color_range = val ? SDVO_COLOR_RANGE_16_235 : 0; + switch (val) { + case INTEL_BROADCAST_RGB_AUTO: + intel_sdvo->color_range_auto = true; + break; + case INTEL_BROADCAST_RGB_FULL: + intel_sdvo->color_range_auto = false; + intel_sdvo->color_range = 0; + break; + case INTEL_BROADCAST_RGB_LIMITED: + intel_sdvo->color_range_auto = false; + intel_sdvo->color_range = SDVO_COLOR_RANGE_16_235; + break; + default: + return -EINVAL; + } goto done; } @@ -2197,13 +2233,16 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector, } static void -intel_sdvo_add_hdmi_properties(struct intel_sdvo_connector *connector) +intel_sdvo_add_hdmi_properties(struct intel_sdvo *intel_sdvo, + struct intel_sdvo_connector *connector) { struct drm_device *dev = connector->base.base.dev; intel_attach_force_audio_property(&connector->base.base); - if (INTEL_INFO(dev)->gen >= 4 && IS_MOBILE(dev)) + if (INTEL_INFO(dev)->gen >= 4 && IS_MOBILE(dev)) { intel_attach_broadcast_rgb_property(&connector->base.base); + intel_sdvo->color_range_auto = true; + } } static bool @@ -2251,7 +2290,7 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo); if (intel_sdvo->is_hdmi) - intel_sdvo_add_hdmi_properties(intel_sdvo_connector); + intel_sdvo_add_hdmi_properties(intel_sdvo, intel_sdvo_connector); return true; } |