diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-22 13:08:22 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-03-22 13:08:22 -0700 |
commit | be53bfdb8088e9d1924199cc1a96e113756b1075 (patch) | |
tree | 8c65eb9d82ca4c0f11c17cfdc44d5263820b415b /drivers/gpu/drm/i915 | |
parent | b2094ef840697bc8ca5d17a83b7e30fad5f1e9fa (diff) | |
parent | 5466c7b1683a23dbbcfb7ee4a71c4f23886001c7 (diff) | |
download | linux-3.10-be53bfdb8088e9d1924199cc1a96e113756b1075.tar.gz linux-3.10-be53bfdb8088e9d1924199cc1a96e113756b1075.tar.bz2 linux-3.10-be53bfdb8088e9d1924199cc1a96e113756b1075.zip |
Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux
Pull drm main changes from Dave Airlie:
"This is the main drm pull request, I'm probably going to send two more
smaller ones, will explain below.
This contains a patch that is also in the fbdev tree, but it should be
the same patch, it added an API for hot unplugging framebuffer
devices, and I need that API for a new driver.
It also contains some changes to the i2c tree which Jean has acked,
and one change to moorestown platform stuff in x86.
Highlights:
- new drivers: UDL driver for USB displaylink devices, kms only,
should support correct hotplug operations.
- core: i2c speedups + better hotplug support, EDID overriding via
firmware interface - allows user to load a firmware for a broken
monitor/kvm from userspace, it even has documentation for it.
- exynos: new HDMI audio + hdmi 1.4 + virtual output driver
- gma500: code cleanup
- radeon: cleanups, CS optimisations, streamout support and pageflip
fix
- nouveau: NVD9 displayport support + more reclocking work
- i915: re-enabling GMBUS, finish gpu patch (might help hibernation
who knows), missed irq fixes, stencil tiling fixes, interlaced
support, aliasesd PPGTT support for SNB/IVB, swizzling for SNB/IVB,
semaphore fixes
As well as the usual bunch of cleanups and fixes all over the place.
I've got two things I'd like to merge a bit later:
a) AMD support for all their new radeonhd 7000 series GPU and APUs.
AMD dropped this a bit late due to insane internal review
processes, (please AMD just follow Intel and let open source guys
ship stuff early) however I don't want to penalise people who own
this hardware (since its been on sale for 3-4 months and GPU hw
doesn't exactly have a lifetime in years) and consign them to
using closed drivers for longer than necessary. The changes are
well contained and just plug into the driver new gpu functionality
so they should be fairly regression proof. I just want to give
them a bit of a run on the hw AMD kindly sent me.
b) drm prime/dma-buf interface code. This is just infrastructure
code to expose the dma-buf stuff to drm drivers and to userspace.
I'm not planning on pushing any driver support in this cycle
(except maybe exynos), but I'd like to get the infrastructure code
in so for the next cycle I can start getting the driver support
into the individual drivers. We have started driver support for
i915, nouveau and udl along with I think exynos and omap in
staging. However this code relies on the dma-buf tree being
pulled into your tree first since it needs the latest interfaces
from that tree. I'll push to get that tree sent asap.
(oh and any warnings you see in i915 are gcc's fault from what anyone
can see)."
Fix up trivial conflicts in arch/x86/platform/mrst/mrst.c due to the new
msic_thermal_platform_data() thermal function being added next to the
tc35876x_platform_data() i2c device function..
* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (326 commits)
drm/i915: use DDC_ADDR instead of hard-coding it
drm/radeon: use DDC_ADDR instead of hard-coding it
drm: remove unneeded redefinition of DDC_ADDR
drm/exynos: added virtual display driver.
drm: allow loading an EDID as firmware to override broken monitor
drm/exynos: enable hdmi audio feature
drm/exynos: add default pixel format for plane
drm/exynos: cleanup exynos_hdmi.h
drm/exynos: add is_local member in exynos_drm_subdrv struct
drm/exynos: add subdrv open/close functions
drm/exynos: remove module of exynos drm subdrv
drm/exynos: release pending pageflip events when closed
drm/exynos: added new funtion to get/put dma address.
drm/exynos: update gem and buffer framework.
drm/exynos: added mode_fixup feature and code clean.
drm/exynos: add HDMI version 1.4 support
drm/exynos: remove exynos_mixer.h
gma500: Fix mmap frambuffer
drm/radeon: Drop radeon_gem_object_(un)pin.
drm/radeon: Restrict offset for legacy display engine.
...
Diffstat (limited to 'drivers/gpu/drm/i915')
32 files changed, 1902 insertions, 1517 deletions
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 808b255d7fc..ce7fc77678b 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -3,7 +3,7 @@ # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. ccflags-y := -Iinclude/drm -i915-y := i915_drv.o i915_dma.o i915_irq.o i915_mem.o \ +i915-y := i915_drv.o i915_dma.o i915_irq.o \ i915_debugfs.o \ i915_suspend.o \ i915_gem.o \ diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index deaa657292b..fdb7ccefffb 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -83,6 +83,7 @@ static int i915_capabilities(struct seq_file *m, void *data) B(supports_tv); B(has_bsd_ring); B(has_blt_ring); + B(has_llc); #undef B return 0; @@ -563,45 +564,6 @@ static int i915_hws_info(struct seq_file *m, void *data) return 0; } -static void i915_dump_object(struct seq_file *m, - struct io_mapping *mapping, - struct drm_i915_gem_object *obj) -{ - int page, page_count, i; - - page_count = obj->base.size / PAGE_SIZE; - for (page = 0; page < page_count; page++) { - u32 *mem = io_mapping_map_wc(mapping, - obj->gtt_offset + page * PAGE_SIZE); - for (i = 0; i < PAGE_SIZE; i += 4) - seq_printf(m, "%08x : %08x\n", i, mem[i / 4]); - io_mapping_unmap(mem); - } -} - -static int i915_batchbuffer_info(struct seq_file *m, void *data) -{ - struct drm_info_node *node = (struct drm_info_node *) m->private; - struct drm_device *dev = node->minor->dev; - drm_i915_private_t *dev_priv = dev->dev_private; - struct drm_i915_gem_object *obj; - int ret; - - ret = mutex_lock_interruptible(&dev->struct_mutex); - if (ret) - return ret; - - list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list) { - if (obj->base.read_domains & I915_GEM_DOMAIN_COMMAND) { - seq_printf(m, "--- gtt_offset = 0x%08x\n", obj->gtt_offset); - i915_dump_object(m, dev_priv->mm.gtt_mapping, obj); - } - } - - mutex_unlock(&dev->struct_mutex); - return 0; -} - static int i915_ringbuffer_data(struct seq_file *m, void *data) { struct drm_info_node *node = (struct drm_info_node *) m->private; @@ -668,9 +630,9 @@ static int i915_ringbuffer_info(struct seq_file *m, void *data) static const char *ring_str(int ring) { switch (ring) { - case RING_RENDER: return " render"; - case RING_BSD: return " bsd"; - case RING_BLT: return " blt"; + case RCS: return "render"; + case VCS: return "bsd"; + case BCS: return "blt"; default: return ""; } } @@ -713,7 +675,7 @@ static void print_error_buffers(struct seq_file *m, seq_printf(m, "%s [%d]:\n", name, count); while (count--) { - seq_printf(m, " %08x %8u %04x %04x %08x%s%s%s%s%s%s", + seq_printf(m, " %08x %8u %04x %04x %08x%s%s%s%s%s%s%s", err->gtt_offset, err->size, err->read_domains, @@ -723,6 +685,7 @@ static void print_error_buffers(struct seq_file *m, tiling_flag(err->tiling), dirty_flag(err->dirty), purgeable_flag(err->purgeable), + err->ring != -1 ? " " : "", ring_str(err->ring), cache_level_str(err->cache_level)); @@ -736,6 +699,38 @@ static void print_error_buffers(struct seq_file *m, } } +static void i915_ring_error_state(struct seq_file *m, + struct drm_device *dev, + struct drm_i915_error_state *error, + unsigned ring) +{ + seq_printf(m, "%s command stream:\n", ring_str(ring)); + seq_printf(m, " HEAD: 0x%08x\n", error->head[ring]); + seq_printf(m, " TAIL: 0x%08x\n", error->tail[ring]); + seq_printf(m, " ACTHD: 0x%08x\n", error->acthd[ring]); + seq_printf(m, " IPEIR: 0x%08x\n", error->ipeir[ring]); + seq_printf(m, " IPEHR: 0x%08x\n", error->ipehr[ring]); + seq_printf(m, " INSTDONE: 0x%08x\n", error->instdone[ring]); + if (ring == RCS && INTEL_INFO(dev)->gen >= 4) { + seq_printf(m, " INSTDONE1: 0x%08x\n", error->instdone1); + seq_printf(m, " BBADDR: 0x%08llx\n", error->bbaddr); + } + if (INTEL_INFO(dev)->gen >= 4) + seq_printf(m, " INSTPS: 0x%08x\n", error->instps[ring]); + seq_printf(m, " INSTPM: 0x%08x\n", error->instpm[ring]); + if (INTEL_INFO(dev)->gen >= 6) { + seq_printf(m, " FADDR: 0x%08x\n", error->faddr[ring]); + seq_printf(m, " FAULT_REG: 0x%08x\n", error->fault_reg[ring]); + seq_printf(m, " SYNC_0: 0x%08x\n", + error->semaphore_mboxes[ring][0]); + seq_printf(m, " SYNC_1: 0x%08x\n", + error->semaphore_mboxes[ring][1]); + } + seq_printf(m, " seqno: 0x%08x\n", error->seqno[ring]); + seq_printf(m, " ring->head: 0x%08x\n", error->cpu_ring_head[ring]); + seq_printf(m, " ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]); +} + static int i915_error_state(struct seq_file *m, void *unused) { struct drm_info_node *node = (struct drm_info_node *) m->private; @@ -743,7 +738,7 @@ static int i915_error_state(struct seq_file *m, void *unused) drm_i915_private_t *dev_priv = dev->dev_private; struct drm_i915_error_state *error; unsigned long flags; - int i, page, offset, elt; + int i, j, page, offset, elt; spin_lock_irqsave(&dev_priv->error_lock, flags); if (!dev_priv->first_error) { @@ -758,35 +753,20 @@ static int i915_error_state(struct seq_file *m, void *unused) seq_printf(m, "PCI ID: 0x%04x\n", dev->pci_device); seq_printf(m, "EIR: 0x%08x\n", error->eir); seq_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er); + + for (i = 0; i < dev_priv->num_fence_regs; i++) + seq_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]); + if (INTEL_INFO(dev)->gen >= 6) { seq_printf(m, "ERROR: 0x%08x\n", error->error); - seq_printf(m, "Blitter command stream:\n"); - seq_printf(m, " ACTHD: 0x%08x\n", error->bcs_acthd); - seq_printf(m, " IPEIR: 0x%08x\n", error->bcs_ipeir); - seq_printf(m, " IPEHR: 0x%08x\n", error->bcs_ipehr); - seq_printf(m, " INSTDONE: 0x%08x\n", error->bcs_instdone); - seq_printf(m, " seqno: 0x%08x\n", error->bcs_seqno); - seq_printf(m, "Video (BSD) command stream:\n"); - seq_printf(m, " ACTHD: 0x%08x\n", error->vcs_acthd); - seq_printf(m, " IPEIR: 0x%08x\n", error->vcs_ipeir); - seq_printf(m, " IPEHR: 0x%08x\n", error->vcs_ipehr); - seq_printf(m, " INSTDONE: 0x%08x\n", error->vcs_instdone); - seq_printf(m, " seqno: 0x%08x\n", error->vcs_seqno); - } - seq_printf(m, "Render command stream:\n"); - seq_printf(m, " ACTHD: 0x%08x\n", error->acthd); - seq_printf(m, " IPEIR: 0x%08x\n", error->ipeir); - seq_printf(m, " IPEHR: 0x%08x\n", error->ipehr); - seq_printf(m, " INSTDONE: 0x%08x\n", error->instdone); - if (INTEL_INFO(dev)->gen >= 4) { - seq_printf(m, " INSTDONE1: 0x%08x\n", error->instdone1); - seq_printf(m, " INSTPS: 0x%08x\n", error->instps); + seq_printf(m, "DONE_REG: 0x%08x\n", error->done_reg); } - seq_printf(m, " INSTPM: 0x%08x\n", error->instpm); - seq_printf(m, " seqno: 0x%08x\n", error->seqno); - for (i = 0; i < dev_priv->num_fence_regs; i++) - seq_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]); + i915_ring_error_state(m, dev, error, RCS); + if (HAS_BLT(dev)) + i915_ring_error_state(m, dev, error, BCS); + if (HAS_BSD(dev)) + i915_ring_error_state(m, dev, error, VCS); if (error->active_bo) print_error_buffers(m, "Active", @@ -798,10 +778,10 @@ static int i915_error_state(struct seq_file *m, void *unused) error->pinned_bo, error->pinned_bo_count); - for (i = 0; i < ARRAY_SIZE(error->batchbuffer); i++) { - if (error->batchbuffer[i]) { - struct drm_i915_error_object *obj = error->batchbuffer[i]; + for (i = 0; i < ARRAY_SIZE(error->ring); i++) { + struct drm_i915_error_object *obj; + if ((obj = error->ring[i].batchbuffer)) { seq_printf(m, "%s --- gtt_offset = 0x%08x\n", dev_priv->ring[i].name, obj->gtt_offset); @@ -813,11 +793,20 @@ static int i915_error_state(struct seq_file *m, void *unused) } } } - } - for (i = 0; i < ARRAY_SIZE(error->ringbuffer); i++) { - if (error->ringbuffer[i]) { - struct drm_i915_error_object *obj = error->ringbuffer[i]; + if (error->ring[i].num_requests) { + seq_printf(m, "%s --- %d requests\n", + dev_priv->ring[i].name, + error->ring[i].num_requests); + for (j = 0; j < error->ring[i].num_requests; j++) { + seq_printf(m, " seqno 0x%08x, emitted %ld, tail 0x%08x\n", + error->ring[i].requests[j].seqno, + error->ring[i].requests[j].jiffies, + error->ring[i].requests[j].tail); + } + } + + if ((obj = error->ring[i].ringbuffer)) { seq_printf(m, "%s --- ringbuffer = 0x%08x\n", dev_priv->ring[i].name, obj->gtt_offset); @@ -1414,9 +1403,108 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data) return 0; } +static const char *swizzle_string(unsigned swizzle) +{ + switch(swizzle) { + case I915_BIT_6_SWIZZLE_NONE: + return "none"; + case I915_BIT_6_SWIZZLE_9: + return "bit9"; + case I915_BIT_6_SWIZZLE_9_10: + return "bit9/bit10"; + case I915_BIT_6_SWIZZLE_9_11: + return "bit9/bit11"; + case I915_BIT_6_SWIZZLE_9_10_11: + return "bit9/bit10/bit11"; + case I915_BIT_6_SWIZZLE_9_17: + return "bit9/bit17"; + case I915_BIT_6_SWIZZLE_9_10_17: + return "bit9/bit10/bit17"; + case I915_BIT_6_SWIZZLE_UNKNOWN: + return "unkown"; + } + + return "bug"; +} + +static int i915_swizzle_info(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + mutex_lock(&dev->struct_mutex); + seq_printf(m, "bit6 swizzle for X-tiling = %s\n", + swizzle_string(dev_priv->mm.bit_6_swizzle_x)); + seq_printf(m, "bit6 swizzle for Y-tiling = %s\n", + swizzle_string(dev_priv->mm.bit_6_swizzle_y)); + + if (IS_GEN3(dev) || IS_GEN4(dev)) { + seq_printf(m, "DDC = 0x%08x\n", + I915_READ(DCC)); + seq_printf(m, "C0DRB3 = 0x%04x\n", + I915_READ16(C0DRB3)); + seq_printf(m, "C1DRB3 = 0x%04x\n", + I915_READ16(C1DRB3)); + } else if (IS_GEN6(dev) || IS_GEN7(dev)) { + seq_printf(m, "MAD_DIMM_C0 = 0x%08x\n", + I915_READ(MAD_DIMM_C0)); + seq_printf(m, "MAD_DIMM_C1 = 0x%08x\n", + I915_READ(MAD_DIMM_C1)); + seq_printf(m, "MAD_DIMM_C2 = 0x%08x\n", + I915_READ(MAD_DIMM_C2)); + seq_printf(m, "TILECTL = 0x%08x\n", + I915_READ(TILECTL)); + seq_printf(m, "ARB_MODE = 0x%08x\n", + I915_READ(ARB_MODE)); + seq_printf(m, "DISP_ARB_CTL = 0x%08x\n", + I915_READ(DISP_ARB_CTL)); + } + mutex_unlock(&dev->struct_mutex); + + return 0; +} + +static int i915_ppgtt_info(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_ring_buffer *ring; + int i, ret; + + + ret = mutex_lock_interruptible(&dev->struct_mutex); + if (ret) + return ret; + if (INTEL_INFO(dev)->gen == 6) + seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(GFX_MODE)); + + for (i = 0; i < I915_NUM_RINGS; i++) { + ring = &dev_priv->ring[i]; + + seq_printf(m, "%s\n", ring->name); + if (INTEL_INFO(dev)->gen == 7) + seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(RING_MODE_GEN7(ring))); + seq_printf(m, "PP_DIR_BASE: 0x%08x\n", I915_READ(RING_PP_DIR_BASE(ring))); + seq_printf(m, "PP_DIR_BASE_READ: 0x%08x\n", I915_READ(RING_PP_DIR_BASE_READ(ring))); + seq_printf(m, "PP_DIR_DCLV: 0x%08x\n", I915_READ(RING_PP_DIR_DCLV(ring))); + } + if (dev_priv->mm.aliasing_ppgtt) { + struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; + + seq_printf(m, "aliasing PPGTT:\n"); + seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd_offset); + } + seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK)); + mutex_unlock(&dev->struct_mutex); + + return 0; +} + static int -i915_wedged_open(struct inode *inode, - struct file *filp) +i915_debugfs_common_open(struct inode *inode, + struct file *filp) { filp->private_data = inode->i_private; return 0; @@ -1472,20 +1560,12 @@ i915_wedged_write(struct file *filp, static const struct file_operations i915_wedged_fops = { .owner = THIS_MODULE, - .open = i915_wedged_open, + .open = i915_debugfs_common_open, .read = i915_wedged_read, .write = i915_wedged_write, .llseek = default_llseek, }; -static int -i915_max_freq_open(struct inode *inode, - struct file *filp) -{ - filp->private_data = inode->i_private; - return 0; -} - static ssize_t i915_max_freq_read(struct file *filp, char __user *ubuf, @@ -1542,20 +1622,12 @@ i915_max_freq_write(struct file *filp, static const struct file_operations i915_max_freq_fops = { .owner = THIS_MODULE, - .open = i915_max_freq_open, + .open = i915_debugfs_common_open, .read = i915_max_freq_read, .write = i915_max_freq_write, .llseek = default_llseek, }; -static int -i915_cache_sharing_open(struct inode *inode, - struct file *filp) -{ - filp->private_data = inode->i_private; - return 0; -} - static ssize_t i915_cache_sharing_read(struct file *filp, char __user *ubuf, @@ -1621,7 +1693,7 @@ i915_cache_sharing_write(struct file *filp, static const struct file_operations i915_cache_sharing_fops = { .owner = THIS_MODULE, - .open = i915_cache_sharing_open, + .open = i915_debugfs_common_open, .read = i915_cache_sharing_read, .write = i915_cache_sharing_write, .llseek = default_llseek, @@ -1653,21 +1725,6 @@ drm_add_fake_info_node(struct drm_minor *minor, return 0; } -static int i915_wedged_create(struct dentry *root, struct drm_minor *minor) -{ - struct drm_device *dev = minor->dev; - struct dentry *ent; - - ent = debugfs_create_file("i915_wedged", - S_IRUGO | S_IWUSR, - root, dev, - &i915_wedged_fops); - if (IS_ERR(ent)) - return PTR_ERR(ent); - - return drm_add_fake_info_node(minor, ent, &i915_wedged_fops); -} - static int i915_forcewake_open(struct inode *inode, struct file *file) { struct drm_device *dev = inode->i_private; @@ -1729,34 +1786,22 @@ static int i915_forcewake_create(struct dentry *root, struct drm_minor *minor) return drm_add_fake_info_node(minor, ent, &i915_forcewake_fops); } -static int i915_max_freq_create(struct dentry *root, struct drm_minor *minor) -{ - struct drm_device *dev = minor->dev; - struct dentry *ent; - - ent = debugfs_create_file("i915_max_freq", - S_IRUGO | S_IWUSR, - root, dev, - &i915_max_freq_fops); - if (IS_ERR(ent)) - return PTR_ERR(ent); - - return drm_add_fake_info_node(minor, ent, &i915_max_freq_fops); -} - -static int i915_cache_sharing_create(struct dentry *root, struct drm_minor *minor) +static int i915_debugfs_create(struct dentry *root, + struct drm_minor *minor, + const char *name, + const struct file_operations *fops) { struct drm_device *dev = minor->dev; struct dentry *ent; - ent = debugfs_create_file("i915_cache_sharing", + ent = debugfs_create_file(name, S_IRUGO | S_IWUSR, root, dev, - &i915_cache_sharing_fops); + fops); if (IS_ERR(ent)) return PTR_ERR(ent); - return drm_add_fake_info_node(minor, ent, &i915_cache_sharing_fops); + return drm_add_fake_info_node(minor, ent, fops); } static struct drm_info_list i915_debugfs_list[] = { @@ -1782,7 +1827,6 @@ static struct drm_info_list i915_debugfs_list[] = { {"i915_bsd_ringbuffer_info", i915_ringbuffer_info, 0, (void *)VCS}, {"i915_blt_ringbuffer_data", i915_ringbuffer_data, 0, (void *)BCS}, {"i915_blt_ringbuffer_info", i915_ringbuffer_info, 0, (void *)BCS}, - {"i915_batchbuffers", i915_batchbuffer_info, 0}, {"i915_error_state", i915_error_state, 0}, {"i915_rstdby_delays", i915_rstdby_delays, 0}, {"i915_cur_delayinfo", i915_cur_delayinfo, 0}, @@ -1798,6 +1842,8 @@ static struct drm_info_list i915_debugfs_list[] = { {"i915_gem_framebuffer", i915_gem_framebuffer_info, 0}, {"i915_context_status", i915_context_status, 0}, {"i915_gen6_forcewake_count", i915_gen6_forcewake_count_info, 0}, + {"i915_swizzle_info", i915_swizzle_info, 0}, + {"i915_ppgtt_info", i915_ppgtt_info, 0}, }; #define I915_DEBUGFS_ENTRIES ARRAY_SIZE(i915_debugfs_list) @@ -1805,17 +1851,25 @@ int i915_debugfs_init(struct drm_minor *minor) { int ret; - ret = i915_wedged_create(minor->debugfs_root, minor); + ret = i915_debugfs_create(minor->debugfs_root, minor, + "i915_wedged", + &i915_wedged_fops); if (ret) return ret; ret = i915_forcewake_create(minor->debugfs_root, minor); if (ret) return ret; - ret = i915_max_freq_create(minor->debugfs_root, minor); + + ret = i915_debugfs_create(minor->debugfs_root, minor, + "i915_max_freq", + &i915_max_freq_fops); if (ret) return ret; - ret = i915_cache_sharing_create(minor->debugfs_root, minor); + + ret = i915_debugfs_create(minor->debugfs_root, minor, + "i915_cache_sharing", + &i915_cache_sharing_fops); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index ddfe3d902b2..9341eb8ce93 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -784,6 +784,9 @@ static int i915_getparam(struct drm_device *dev, void *data, case I915_PARAM_HAS_GEN7_SOL_RESET: value = 1; break; + case I915_PARAM_HAS_LLC: + value = HAS_LLC(dev); + break; default: DRM_DEBUG_DRIVER("Unknown parameter %d\n", param->param); @@ -1193,22 +1196,39 @@ static int i915_load_gem_init(struct drm_device *dev) /* Basic memrange allocator for stolen space */ drm_mm_init(&dev_priv->mm.stolen, 0, prealloc_size); - /* Let GEM Manage all of the aperture. - * - * However, leave one page at the end still bound to the scratch page. - * There are a number of places where the hardware apparently - * prefetches past the end of the object, and we've seen multiple - * hangs with the GPU head pointer stuck in a batchbuffer bound - * at the last page of the aperture. One page should be enough to - * keep any prefetching inside of the aperture. - */ - i915_gem_do_init(dev, 0, mappable_size, gtt_size - PAGE_SIZE); - mutex_lock(&dev->struct_mutex); - ret = i915_gem_init_ringbuffer(dev); + if (i915_enable_ppgtt && HAS_ALIASING_PPGTT(dev)) { + /* PPGTT pdes are stolen from global gtt ptes, so shrink the + * aperture accordingly when using aliasing ppgtt. */ + gtt_size -= I915_PPGTT_PD_ENTRIES*PAGE_SIZE; + /* For paranoia keep the guard page in between. */ + gtt_size -= PAGE_SIZE; + + i915_gem_do_init(dev, 0, mappable_size, gtt_size); + + ret = i915_gem_init_aliasing_ppgtt(dev); + if (ret) + return ret; + } else { + /* Let GEM Manage all of the aperture. + * + * However, leave one page at the end still bound to the scratch + * page. There are a number of places where the hardware + * apparently prefetches past the end of the object, and we've + * seen multiple hangs with the GPU head pointer stuck in a + * batchbuffer bound at the last page of the aperture. One page + * should be enough to keep any prefetching inside of the + * aperture. + */ + i915_gem_do_init(dev, 0, mappable_size, gtt_size - PAGE_SIZE); + } + + ret = i915_gem_init_hw(dev); mutex_unlock(&dev->struct_mutex); - if (ret) + if (ret) { + i915_gem_cleanup_aliasing_ppgtt(dev); return ret; + } /* Try to set up FBC with a reasonable compressed buffer size */ if (I915_HAS_FBC(dev) && i915_powersave) { @@ -1295,6 +1315,7 @@ cleanup_gem: mutex_lock(&dev->struct_mutex); i915_gem_cleanup_ringbuffer(dev); mutex_unlock(&dev->struct_mutex); + i915_gem_cleanup_aliasing_ppgtt(dev); cleanup_vga_switcheroo: vga_switcheroo_unregister_client(dev->pdev); cleanup_vga_client: @@ -1930,6 +1951,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) goto free_priv; } + pci_set_master(dev->pdev); + /* overlay on gen2 is broken and can't address above 1G */ if (IS_GEN2(dev)) dma_set_coherent_mask(&dev->pdev->dev, DMA_BIT_MASK(30)); @@ -2129,7 +2152,7 @@ int i915_driver_unload(struct drm_device *dev) unregister_shrinker(&dev_priv->mm.inactive_shrinker); mutex_lock(&dev->struct_mutex); - ret = i915_gpu_idle(dev); + ret = i915_gpu_idle(dev, true); if (ret) DRM_ERROR("failed to idle hardware: %d\n", ret); mutex_unlock(&dev->struct_mutex); @@ -2182,6 +2205,7 @@ int i915_driver_unload(struct drm_device *dev) i915_gem_free_all_phys_object(dev); i915_gem_cleanup_ringbuffer(dev); mutex_unlock(&dev->struct_mutex); + i915_gem_cleanup_aliasing_ppgtt(dev); if (I915_HAS_FBC(dev) && i915_powersave) i915_cleanup_compression(dev); drm_mm_takedown(&dev_priv->mm.stolen); @@ -2247,18 +2271,12 @@ void i915_driver_lastclose(struct drm_device * dev) i915_gem_lastclose(dev); - if (dev_priv->agp_heap) - i915_mem_takedown(&(dev_priv->agp_heap)); - i915_dma_cleanup(dev); } void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv) { - drm_i915_private_t *dev_priv = dev->dev_private; i915_gem_release(dev, file_priv); - if (!drm_core_check_feature(dev, DRIVER_MODESET)) - i915_mem_release(dev, file_priv, dev_priv->agp_heap); } void i915_driver_postclose(struct drm_device *dev, struct drm_file *file) @@ -2277,11 +2295,11 @@ struct drm_ioctl_desc i915_ioctls[] = { DRM_IOCTL_DEF_DRV(I915_IRQ_WAIT, i915_irq_wait, DRM_AUTH), DRM_IOCTL_DEF_DRV(I915_GETPARAM, i915_getparam, DRM_AUTH), DRM_IOCTL_DEF_DRV(I915_SETPARAM, i915_setparam, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), - DRM_IOCTL_DEF_DRV(I915_ALLOC, i915_mem_alloc, DRM_AUTH), - DRM_IOCTL_DEF_DRV(I915_FREE, i915_mem_free, DRM_AUTH), - DRM_IOCTL_DEF_DRV(I915_INIT_HEAP, i915_mem_init_heap, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_ALLOC, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_FREE, drm_noop, DRM_AUTH), + DRM_IOCTL_DEF_DRV(I915_INIT_HEAP, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF_DRV(I915_CMDBUFFER, i915_cmdbuffer, DRM_AUTH), - DRM_IOCTL_DEF_DRV(I915_DESTROY_HEAP, i915_mem_destroy_heap, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), + DRM_IOCTL_DEF_DRV(I915_DESTROY_HEAP, drm_noop, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF_DRV(I915_SET_VBLANK_PIPE, i915_vblank_pipe_set, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY), DRM_IOCTL_DEF_DRV(I915_GET_VBLANK_PIPE, i915_vblank_pipe_get, DRM_AUTH), DRM_IOCTL_DEF_DRV(I915_VBLANK_SWAP, i915_vblank_swap, DRM_AUTH), diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 308f8191356..0694e170a33 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -103,6 +103,11 @@ MODULE_PARM_DESC(enable_hangcheck, "WARNING: Disabling this can cause system wide hangs. " "(default: true)"); +bool i915_enable_ppgtt __read_mostly = 1; +module_param_named(i915_enable_ppgtt, i915_enable_ppgtt, bool, 0600); +MODULE_PARM_DESC(i915_enable_ppgtt, + "Enable PPGTT (default: true)"); + static struct drm_driver driver; extern int intel_agp_enabled; @@ -198,7 +203,7 @@ static const struct intel_device_info intel_pineview_info = { static const struct intel_device_info intel_ironlake_d_info = { .gen = 5, - .need_gfx_hws = 1, .has_pipe_cxsr = 1, .has_hotplug = 1, + .need_gfx_hws = 1, .has_hotplug = 1, .has_bsd_ring = 1, }; @@ -214,6 +219,7 @@ static const struct intel_device_info intel_sandybridge_d_info = { .need_gfx_hws = 1, .has_hotplug = 1, .has_bsd_ring = 1, .has_blt_ring = 1, + .has_llc = 1, }; static const struct intel_device_info intel_sandybridge_m_info = { @@ -222,6 +228,7 @@ static const struct intel_device_info intel_sandybridge_m_info = { .has_fbc = 1, .has_bsd_ring = 1, .has_blt_ring = 1, + .has_llc = 1, }; static const struct intel_device_info intel_ivybridge_d_info = { @@ -229,6 +236,7 @@ static const struct intel_device_info intel_ivybridge_d_info = { .need_gfx_hws = 1, .has_hotplug = 1, .has_bsd_ring = 1, .has_blt_ring = 1, + .has_llc = 1, }; static const struct intel_device_info intel_ivybridge_m_info = { @@ -237,6 +245,7 @@ static const struct intel_device_info intel_ivybridge_m_info = { .has_fbc = 0, /* FBC is not enabled on Ivybridge mobile yet */ .has_bsd_ring = 1, .has_blt_ring = 1, + .has_llc = 1, }; static const struct pci_device_id pciidlist[] = { /* aka */ @@ -376,16 +385,27 @@ void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv) spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); } +static void gen6_gt_check_fifodbg(struct drm_i915_private *dev_priv) +{ + u32 gtfifodbg; + gtfifodbg = I915_READ_NOTRACE(GTFIFODBG); + if (WARN(gtfifodbg & GT_FIFO_CPU_ERROR_MASK, + "MMIO read or write has been dropped %x\n", gtfifodbg)) + I915_WRITE_NOTRACE(GTFIFODBG, GT_FIFO_CPU_ERROR_MASK); +} + void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv) { I915_WRITE_NOTRACE(FORCEWAKE, 0); - POSTING_READ(FORCEWAKE); + /* The below doubles as a POSTING_READ */ + gen6_gt_check_fifodbg(dev_priv); } void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv) { I915_WRITE_NOTRACE(FORCEWAKE_MT, (1<<16) | 0); - POSTING_READ(FORCEWAKE_MT); + /* The below doubles as a POSTING_READ */ + gen6_gt_check_fifodbg(dev_priv); } /* @@ -401,8 +421,10 @@ void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv) spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags); } -void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) +int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) { + int ret = 0; + if (dev_priv->gt_fifo_count < GT_FIFO_NUM_RESERVED_ENTRIES) { int loop = 500; u32 fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES); @@ -410,10 +432,13 @@ void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv) udelay(10); fifo = I915_READ_NOTRACE(GT_FIFO_FREE_ENTRIES); } - WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES); + if (WARN_ON(loop < 0 && fifo <= GT_FIFO_NUM_RESERVED_ENTRIES)) + ++ret; dev_priv->gt_fifo_count = fifo; } dev_priv->gt_fifo_count--; + + return ret; } static int i915_drm_freeze(struct drm_device *dev) @@ -494,7 +519,7 @@ static int i915_drm_thaw(struct drm_device *dev) mutex_lock(&dev->struct_mutex); dev_priv->mm.suspended = 0; - error = i915_gem_init_ringbuffer(dev); + error = i915_gem_init_hw(dev); mutex_unlock(&dev->struct_mutex); if (HAS_PCH_SPLIT(dev)) @@ -633,7 +658,7 @@ static int gen6_do_reset(struct drm_device *dev, u8 flags) } /** - * i965_reset - reset chip after a hang + * i915_reset - reset chip after a hang * @dev: drm device to reset * @flags: reset domains * @@ -709,12 +734,16 @@ int i915_reset(struct drm_device *dev, u8 flags) !dev_priv->mm.suspended) { dev_priv->mm.suspended = 0; + i915_gem_init_swizzling(dev); + dev_priv->ring[RCS].init(&dev_priv->ring[RCS]); if (HAS_BSD(dev)) dev_priv->ring[VCS].init(&dev_priv->ring[VCS]); if (HAS_BLT(dev)) dev_priv->ring[BCS].init(&dev_priv->ring[BCS]); + i915_gem_init_ppgtt(dev); + mutex_unlock(&dev->struct_mutex); drm_irq_uninstall(dev); drm_mode_config_reset(dev); @@ -977,11 +1006,15 @@ __i915_read(64, q) #define __i915_write(x, y) \ void i915_write##x(struct drm_i915_private *dev_priv, u32 reg, u##x val) { \ + u32 __fifo_ret = 0; \ trace_i915_reg_rw(true, reg, val, sizeof(val)); \ if (NEEDS_FORCE_WAKE((dev_priv), (reg))) { \ - __gen6_gt_wait_for_fifo(dev_priv); \ + __fifo_ret = __gen6_gt_wait_for_fifo(dev_priv); \ } \ write##y(val, dev_priv->regs + reg); \ + if (unlikely(__fifo_ret)) { \ + gen6_gt_check_fifodbg(dev_priv); \ + } \ } __i915_write(8, b) __i915_write(16, w) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 9689ca38b2b..c0f19f57200 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -35,6 +35,7 @@ #include "intel_ringbuffer.h" #include <linux/io-mapping.h> #include <linux/i2c.h> +#include <linux/i2c-algo-bit.h> #include <drm/intel-gtt.h> #include <linux/backlight.h> @@ -135,6 +136,7 @@ struct drm_i915_fence_reg { struct list_head lru_list; struct drm_i915_gem_object *obj; uint32_t setup_seqno; + int pin_count; }; struct sdvo_device_mapping { @@ -152,33 +154,40 @@ struct drm_i915_error_state { u32 eir; u32 pgtbl_er; u32 pipestat[I915_MAX_PIPES]; - u32 ipeir; - u32 ipehr; - u32 instdone; - u32 acthd; + u32 tail[I915_NUM_RINGS]; + u32 head[I915_NUM_RINGS]; + u32 ipeir[I915_NUM_RINGS]; + u32 ipehr[I915_NUM_RINGS]; + u32 instdone[I915_NUM_RINGS]; + u32 acthd[I915_NUM_RINGS]; + u32 semaphore_mboxes[I915_NUM_RINGS][I915_NUM_RINGS - 1]; + /* our own tracking of ring head and tail */ + u32 cpu_ring_head[I915_NUM_RINGS]; + u32 cpu_ring_tail[I915_NUM_RINGS]; u32 error; /* gen6+ */ - u32 bcs_acthd; /* gen6+ blt engine */ - u32 bcs_ipehr; - u32 bcs_ipeir; - u32 bcs_instdone; - u32 bcs_seqno; - u32 vcs_acthd; /* gen6+ bsd engine */ - u32 vcs_ipehr; - u32 vcs_ipeir; - u32 vcs_instdone; - u32 vcs_seqno; - u32 instpm; - u32 instps; + u32 instpm[I915_NUM_RINGS]; + u32 instps[I915_NUM_RINGS]; u32 instdone1; - u32 seqno; + u32 seqno[I915_NUM_RINGS]; u64 bbaddr; + u32 fault_reg[I915_NUM_RINGS]; + u32 done_reg; + u32 faddr[I915_NUM_RINGS]; u64 fence[I915_MAX_NUM_FENCES]; struct timeval time; - struct drm_i915_error_object { - int page_count; - u32 gtt_offset; - u32 *pages[0]; - } *ringbuffer[I915_NUM_RINGS], *batchbuffer[I915_NUM_RINGS]; + struct drm_i915_error_ring { + struct drm_i915_error_object { + int page_count; + u32 gtt_offset; + u32 *pages[0]; + } *ringbuffer, *batchbuffer; + struct drm_i915_error_request { + long jiffies; + u32 seqno; + u32 tail; + } *requests; + int num_requests; + } ring[I915_NUM_RINGS]; struct drm_i915_error_buffer { u32 size; u32 name; @@ -191,7 +200,7 @@ struct drm_i915_error_state { u32 tiling:2; u32 dirty:1; u32 purgeable:1; - u32 ring:4; + s32 ring:4; u32 cache_level:2; } *active_bo, *pinned_bo; u32 active_bo_count, pinned_bo_count; @@ -255,6 +264,17 @@ struct intel_device_info { u8 supports_tv:1; u8 has_bsd_ring:1; u8 has_blt_ring:1; + u8 has_llc:1; +}; + +#define I915_PPGTT_PD_ENTRIES 512 +#define I915_PPGTT_PT_ENTRIES 1024 +struct i915_hw_ppgtt { + unsigned num_pd_entries; + struct page **pt_pages; + uint32_t pd_offset; + dma_addr_t *pt_dma_addr; + dma_addr_t scratch_page_dma_addr; }; enum no_fbc_reason { @@ -279,6 +299,16 @@ enum intel_pch { struct intel_fbdev; struct intel_fbc_work; +struct intel_gmbus { + struct i2c_adapter adapter; + bool force_bit; + bool has_gpio; + u32 reg0; + u32 gpio_reg; + struct i2c_algo_bit_data bit_algo; + struct drm_i915_private *dev_priv; +}; + typedef struct drm_i915_private { struct drm_device *dev; @@ -296,11 +326,11 @@ typedef struct drm_i915_private { /** gt_lock is also taken in irq contexts. */ struct spinlock gt_lock; - struct intel_gmbus { - struct i2c_adapter adapter; - struct i2c_adapter *force_bit; - u32 reg0; - } *gmbus; + struct intel_gmbus *gmbus; + + /** gmbus_mutex protects against concurrent usage of the single hw gmbus + * controller on different i2c buses. */ + struct mutex gmbus_mutex; struct pci_dev *bridge_dev; struct intel_ring_buffer ring[I915_NUM_RINGS]; @@ -335,7 +365,6 @@ typedef struct drm_i915_private { int tex_lru_log_granularity; int allow_batchbuffer; - struct mem_block *agp_heap; unsigned int sr01, adpa, ppcr, dvob, dvoc, lvds; int vblank_pipe; int num_pipe; @@ -584,6 +613,9 @@ typedef struct drm_i915_private { struct io_mapping *gtt_mapping; int gtt_mtrr; + /** PPGTT used for aliasing the PPGTT with the GTT */ + struct i915_hw_ppgtt *aliasing_ppgtt; + struct shrinker inactive_shrinker; /** @@ -749,6 +781,13 @@ typedef struct drm_i915_private { struct drm_property *force_audio_property; } drm_i915_private_t; +enum hdmi_force_audio { + HDMI_AUDIO_OFF_DVI = -2, /* no aux data for HDMI-DVI converter */ + HDMI_AUDIO_OFF, /* force turn off HDMI audio */ + HDMI_AUDIO_AUTO, /* trust EDID */ + HDMI_AUDIO_ON, /* force turn on HDMI audio */ +}; + enum i915_cache_level { I915_CACHE_NONE, I915_CACHE_LLC, @@ -841,6 +880,8 @@ struct drm_i915_gem_object { unsigned int cache_level:2; + unsigned int has_aliasing_ppgtt_mapping:1; + struct page **pages; /** @@ -918,6 +959,9 @@ struct drm_i915_gem_request { /** GEM sequence number associated with this request. */ uint32_t seqno; + /** Postion in the ringbuffer of the end of the request */ + u32 tail; + /** Time at which this request was emitted, in jiffies. */ unsigned long emitted_jiffies; @@ -974,8 +1018,11 @@ struct drm_i915_file_private { #define HAS_BSD(dev) (INTEL_INFO(dev)->has_bsd_ring) #define HAS_BLT(dev) (INTEL_INFO(dev)->has_blt_ring) +#define HAS_LLC(dev) (INTEL_INFO(dev)->has_llc) #define I915_NEED_GFX_HWS(dev) (INTEL_INFO(dev)->need_gfx_hws) +#define HAS_ALIASING_PPGTT(dev) (INTEL_INFO(dev)->gen >=6) + #define HAS_OVERLAY(dev) (INTEL_INFO(dev)->has_overlay) #define OVERLAY_NEEDS_PHYSICAL(dev) (INTEL_INFO(dev)->overlay_needs_physical) @@ -1018,6 +1065,7 @@ extern int i915_vbt_sdvo_panel_type __read_mostly; extern int i915_enable_rc6 __read_mostly; extern int i915_enable_fbc __read_mostly; extern bool i915_enable_hangcheck __read_mostly; +extern bool i915_enable_ppgtt __read_mostly; extern int i915_suspend(struct drm_device *dev, pm_message_t state); extern int i915_resume(struct drm_device *dev); @@ -1079,18 +1127,6 @@ extern void i915_destroy_error_state(struct drm_device *dev); #endif -/* i915_mem.c */ -extern int i915_mem_alloc(struct drm_device *dev, void *data, - struct drm_file *file_priv); -extern int i915_mem_free(struct drm_device *dev, void *data, - struct drm_file *file_priv); -extern int i915_mem_init_heap(struct drm_device *dev, void *data, - struct drm_file *file_priv); -extern int i915_mem_destroy_heap(struct drm_device *dev, void *data, - struct drm_file *file_priv); -extern void i915_mem_takedown(struct mem_block **heap); -extern void i915_mem_release(struct drm_device * dev, - struct drm_file *file_priv, struct mem_block *heap); /* i915_gem.c */ int i915_gem_init_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); @@ -1170,37 +1206,55 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2) return (int32_t)(seq1 - seq2) >= 0; } -static inline u32 -i915_gem_next_request_seqno(struct intel_ring_buffer *ring) -{ - drm_i915_private_t *dev_priv = ring->dev->dev_private; - return ring->outstanding_lazy_request = dev_priv->next_seqno; -} +u32 i915_gem_next_request_seqno(struct intel_ring_buffer *ring); int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj, struct intel_ring_buffer *pipelined); int __must_check i915_gem_object_put_fence(struct drm_i915_gem_object *obj); +static inline void +i915_gem_object_pin_fence(struct drm_i915_gem_object *obj) +{ + if (obj->fence_reg != I915_FENCE_REG_NONE) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; + dev_priv->fence_regs[obj->fence_reg].pin_count++; + } +} + +static inline void +i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj) +{ + if (obj->fence_reg != I915_FENCE_REG_NONE) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; + dev_priv->fence_regs[obj->fence_reg].pin_count--; + } +} + void i915_gem_retire_requests(struct drm_device *dev); +void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring); + void i915_gem_reset(struct drm_device *dev); void i915_gem_clflush_object(struct drm_i915_gem_object *obj); int __must_check i915_gem_object_set_domain(struct drm_i915_gem_object *obj, uint32_t read_domains, uint32_t write_domain); int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj); -int __must_check i915_gem_init_ringbuffer(struct drm_device *dev); +int __must_check i915_gem_init_hw(struct drm_device *dev); +void i915_gem_init_swizzling(struct drm_device *dev); +void i915_gem_init_ppgtt(struct drm_device *dev); void i915_gem_cleanup_ringbuffer(struct drm_device *dev); void i915_gem_do_init(struct drm_device *dev, unsigned long start, unsigned long mappable_end, unsigned long end); -int __must_check i915_gpu_idle(struct drm_device *dev); +int __must_check i915_gpu_idle(struct drm_device *dev, bool do_retire); int __must_check i915_gem_idle(struct drm_device *dev); int __must_check i915_add_request(struct intel_ring_buffer *ring, struct drm_file *file, struct drm_i915_gem_request *request); int __must_check i915_wait_request(struct intel_ring_buffer *ring, - uint32_t seqno); + uint32_t seqno, + bool do_retire); int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf); int __must_check i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, @@ -1227,6 +1281,14 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level); /* i915_gem_gtt.c */ +int __must_check i915_gem_init_aliasing_ppgtt(struct drm_device *dev); +void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev); +void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_object *obj, + enum i915_cache_level cache_level); +void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_object *obj); + void i915_gem_restore_gtt_mappings(struct drm_device *dev); int __must_check i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj); void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj, @@ -1365,7 +1427,7 @@ extern void intel_display_print_error_state(struct seq_file *m, */ void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv); void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv); -void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv); +int __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv); /* We give fast paths for the really cool registers */ #define NEEDS_FORCE_WAKE(dev_priv, reg) \ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index e55badb2d86..1f441f5c240 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -58,6 +58,7 @@ static void i915_gem_free_object_tail(struct drm_i915_gem_object *obj); static int i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc); +static void i915_gem_object_truncate(struct drm_i915_gem_object *obj); /* some bookkeeping */ static void i915_gem_info_add_obj(struct drm_i915_private *dev_priv, @@ -258,73 +259,6 @@ static int i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj) obj->tiling_mode != I915_TILING_NONE; } -static inline void -slow_shmem_copy(struct page *dst_page, - int dst_offset, - struct page *src_page, - int src_offset, - int length) -{ - char *dst_vaddr, *src_vaddr; - - dst_vaddr = kmap(dst_page); - src_vaddr = kmap(src_page); - - memcpy(dst_vaddr + dst_offset, src_vaddr + src_offset, length); - - kunmap(src_page); - kunmap(dst_page); -} - -static inline void -slow_shmem_bit17_copy(struct page *gpu_page, - int gpu_offset, - struct page *cpu_page, - int cpu_offset, - int length, - int is_read) -{ - char *gpu_vaddr, *cpu_vaddr; - - /* Use the unswizzled path if this page isn't affected. */ - if ((page_to_phys(gpu_page) & (1 << 17)) == 0) { - if (is_read) - return slow_shmem_copy(cpu_page, cpu_offset, - gpu_page, gpu_offset, length); - else - return slow_shmem_copy(gpu_page, gpu_offset, - cpu_page, cpu_offset, length); - } - - gpu_vaddr = kmap(gpu_page); - cpu_vaddr = kmap(cpu_page); - - /* Copy the data, XORing A6 with A17 (1). The user already knows he's - * XORing with the other bits (A9 for Y, A9 and A10 for X) - */ - while (length > 0) { - int cacheline_end = ALIGN(gpu_offset + 1, 64); - int this_length = min(cacheline_end - gpu_offset, length); - int swizzled_gpu_offset = gpu_offset ^ 64; - - if (is_read) { - memcpy(cpu_vaddr + cpu_offset, - gpu_vaddr + swizzled_gpu_offset, - this_length); - } else { - memcpy(gpu_vaddr + swizzled_gpu_offset, - cpu_vaddr + cpu_offset, - this_length); - } - cpu_offset += this_length; - gpu_offset += this_length; - length -= this_length; - } - - kunmap(cpu_page); - kunmap(gpu_page); -} - /** * This is the fast shmem pread path, which attempts to copy_from_user directly * from the backing pages of the object to the user's address space. On a @@ -385,6 +319,58 @@ i915_gem_shmem_pread_fast(struct drm_device *dev, return 0; } +static inline int +__copy_to_user_swizzled(char __user *cpu_vaddr, + const char *gpu_vaddr, int gpu_offset, + int length) +{ + int ret, cpu_offset = 0; + + while (length > 0) { + int cacheline_end = ALIGN(gpu_offset + 1, 64); + int this_length = min(cacheline_end - gpu_offset, length); + int swizzled_gpu_offset = gpu_offset ^ 64; + + ret = __copy_to_user(cpu_vaddr + cpu_offset, + gpu_vaddr + swizzled_gpu_offset, + this_length); + if (ret) + return ret + length; + + cpu_offset += this_length; + gpu_offset += this_length; + length -= this_length; + } + + return 0; +} + +static inline int +__copy_from_user_swizzled(char __user *gpu_vaddr, int gpu_offset, + const char *cpu_vaddr, + int length) +{ + int ret, cpu_offset = 0; + + while (length > 0) { + int cacheline_end = ALIGN(gpu_offset + 1, 64); + int this_length = min(cacheline_end - gpu_offset, length); + int swizzled_gpu_offset = gpu_offset ^ 64; + + ret = __copy_from_user(gpu_vaddr + swizzled_gpu_offset, + cpu_vaddr + cpu_offset, + this_length); + if (ret) + return ret + length; + + cpu_offset += this_length; + gpu_offset += this_length; + length -= this_length; + } + + return 0; +} + /** * This is the fallback shmem pread path, which allocates temporary storage * in kernel space to copy_to_user into outside of the struct_mutex, so we @@ -398,72 +384,34 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, struct drm_file *file) { struct address_space *mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping; - struct mm_struct *mm = current->mm; - struct page **user_pages; + char __user *user_data; ssize_t remain; - loff_t offset, pinned_pages, i; - loff_t first_data_page, last_data_page, num_pages; - int shmem_page_offset; - int data_page_index, data_page_offset; - int page_length; - int ret; - uint64_t data_ptr = args->data_ptr; - int do_bit17_swizzling; + loff_t offset; + int shmem_page_offset, page_length, ret; + int obj_do_bit17_swizzling, page_do_bit17_swizzling; + user_data = (char __user *) (uintptr_t) args->data_ptr; remain = args->size; - /* Pin the user pages containing the data. We can't fault while - * holding the struct mutex, yet we want to hold it while - * dereferencing the user data. - */ - first_data_page = data_ptr / PAGE_SIZE; - last_data_page = (data_ptr + args->size - 1) / PAGE_SIZE; - num_pages = last_data_page - first_data_page + 1; + obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); - user_pages = drm_malloc_ab(num_pages, sizeof(struct page *)); - if (user_pages == NULL) - return -ENOMEM; + offset = args->offset; mutex_unlock(&dev->struct_mutex); - down_read(&mm->mmap_sem); - pinned_pages = get_user_pages(current, mm, (uintptr_t)args->data_ptr, - num_pages, 1, 0, user_pages, NULL); - up_read(&mm->mmap_sem); - mutex_lock(&dev->struct_mutex); - if (pinned_pages < num_pages) { - ret = -EFAULT; - goto out; - } - - ret = i915_gem_object_set_cpu_read_domain_range(obj, - args->offset, - args->size); - if (ret) - goto out; - - do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); - - offset = args->offset; while (remain > 0) { struct page *page; + char *vaddr; /* Operation in this page * * shmem_page_offset = offset within page in shmem file - * data_page_index = page number in get_user_pages return - * data_page_offset = offset with data_page_index page. * page_length = bytes to copy for this page */ shmem_page_offset = offset_in_page(offset); - data_page_index = data_ptr / PAGE_SIZE - first_data_page; - data_page_offset = offset_in_page(data_ptr); - page_length = remain; if ((shmem_page_offset + page_length) > PAGE_SIZE) page_length = PAGE_SIZE - shmem_page_offset; - if ((data_page_offset + page_length) > PAGE_SIZE) - page_length = PAGE_SIZE - data_page_offset; page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) { @@ -471,36 +419,38 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, goto out; } - if (do_bit17_swizzling) { - slow_shmem_bit17_copy(page, - shmem_page_offset, - user_pages[data_page_index], - data_page_offset, - page_length, - 1); - } else { - slow_shmem_copy(user_pages[data_page_index], - data_page_offset, - page, - shmem_page_offset, - page_length); - } + page_do_bit17_swizzling = obj_do_bit17_swizzling && + (page_to_phys(page) & (1 << 17)) != 0; + + vaddr = kmap(page); + if (page_do_bit17_swizzling) + ret = __copy_to_user_swizzled(user_data, + vaddr, shmem_page_offset, + page_length); + else + ret = __copy_to_user(user_data, + vaddr + shmem_page_offset, + page_length); + kunmap(page); mark_page_accessed(page); page_cache_release(page); + if (ret) { + ret = -EFAULT; + goto out; + } + remain -= page_length; - data_ptr += page_length; + user_data += page_length; offset += page_length; } out: - for (i = 0; i < pinned_pages; i++) { - SetPageDirty(user_pages[i]); - mark_page_accessed(user_pages[i]); - page_cache_release(user_pages[i]); - } - drm_free_large(user_pages); + mutex_lock(&dev->struct_mutex); + /* Fixup: Kill any reinstated backing storage pages */ + if (obj->madv == __I915_MADV_PURGED) + i915_gem_object_truncate(obj); return ret; } @@ -841,71 +791,36 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev, struct drm_file *file) { struct address_space *mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping; - struct mm_struct *mm = current->mm; - struct page **user_pages; ssize_t remain; - loff_t offset, pinned_pages, i; - loff_t first_data_page, last_data_page, num_pages; - int shmem_page_offset; - int data_page_index, data_page_offset; - int page_length; - int ret; - uint64_t data_ptr = args->data_ptr; - int do_bit17_swizzling; + loff_t offset; + char __user *user_data; + int shmem_page_offset, page_length, ret; + int obj_do_bit17_swizzling, page_do_bit17_swizzling; + user_data = (char __user *) (uintptr_t) args->data_ptr; remain = args->size; - /* Pin the user pages containing the data. We can't fault while - * holding the struct mutex, and all of the pwrite implementations - * want to hold it while dereferencing the user data. - */ - first_data_page = data_ptr / PAGE_SIZE; - last_data_page = (data_ptr + args->size - 1) / PAGE_SIZE; - num_pages = last_data_page - first_data_page + 1; - - user_pages = drm_malloc_ab(num_pages, sizeof(struct page *)); - if (user_pages == NULL) - return -ENOMEM; - - mutex_unlock(&dev->struct_mutex); - down_read(&mm->mmap_sem); - pinned_pages = get_user_pages(current, mm, (uintptr_t)args->data_ptr, - num_pages, 0, 0, user_pages, NULL); - up_read(&mm->mmap_sem); - mutex_lock(&dev->struct_mutex); - if (pinned_pages < num_pages) { - ret = -EFAULT; - goto out; - } - - ret = i915_gem_object_set_to_cpu_domain(obj, 1); - if (ret) - goto out; - - do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); + obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj); offset = args->offset; obj->dirty = 1; + mutex_unlock(&dev->struct_mutex); + while (remain > 0) { struct page *page; + char *vaddr; /* Operation in this page * * shmem_page_offset = offset within page in shmem file - * data_page_index = page number in get_user_pages return - * data_page_offset = offset with data_page_index page. * page_length = bytes to copy for this page */ shmem_page_offset = offset_in_page(offset); - data_page_index = data_ptr / PAGE_SIZE - first_data_page; - data_page_offset = offset_in_page(data_ptr); page_length = remain; if ((shmem_page_offset + page_length) > PAGE_SIZE) page_length = PAGE_SIZE - shmem_page_offset; - if ((data_page_offset + page_length) > PAGE_SIZE) - page_length = PAGE_SIZE - data_page_offset; page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) { @@ -913,34 +828,45 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev, goto out; } - if (do_bit17_swizzling) { - slow_shmem_bit17_copy(page, - shmem_page_offset, - user_pages[data_page_index], - data_page_offset, - page_length, - 0); - } else { - slow_shmem_copy(page, - shmem_page_offset, - user_pages[data_page_index], - data_page_offset, - page_length); - } + page_do_bit17_swizzling = obj_do_bit17_swizzling && + (page_to_phys(page) & (1 << 17)) != 0; + + vaddr = kmap(page); + if (page_do_bit17_swizzling) + ret = __copy_from_user_swizzled(vaddr, shmem_page_offset, + user_data, + page_length); + else + ret = __copy_from_user(vaddr + shmem_page_offset, + user_data, + page_length); + kunmap(page); set_page_dirty(page); mark_page_accessed(page); page_cache_release(page); + if (ret) { + ret = -EFAULT; + goto out; + } + remain -= page_length; - data_ptr += page_length; + user_data += page_length; offset += page_length; } out: - for (i = 0; i < pinned_pages; i++) - page_cache_release(user_pages[i]); - drm_free_large(user_pages); + mutex_lock(&dev->struct_mutex); + /* Fixup: Kill any reinstated backing storage pages */ + if (obj->madv == __I915_MADV_PURGED) + i915_gem_object_truncate(obj); + /* and flush dirty cachelines in case the object isn't in the cpu write + * domain anymore. */ + if (obj->base.write_domain != I915_GEM_DOMAIN_CPU) { + i915_gem_clflush_object(obj); + intel_gtt_chipset_flush(); + } return ret; } @@ -996,10 +922,13 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, * pread/pwrite currently are reading and writing from the CPU * perspective, requiring manual detiling by the client. */ - if (obj->phys_obj) + if (obj->phys_obj) { ret = i915_gem_phys_pwrite(dev, obj, args, file); - else if (obj->gtt_space && - obj->base.write_domain != I915_GEM_DOMAIN_CPU) { + goto out; + } + + if (obj->gtt_space && + obj->base.write_domain != I915_GEM_DOMAIN_CPU) { ret = i915_gem_object_pin(obj, 0, true); if (ret) goto out; @@ -1018,18 +947,24 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, out_unpin: i915_gem_object_unpin(obj); - } else { - ret = i915_gem_object_set_to_cpu_domain(obj, 1); - if (ret) - goto out; - ret = -EFAULT; - if (!i915_gem_object_needs_bit17_swizzle(obj)) - ret = i915_gem_shmem_pwrite_fast(dev, obj, args, file); - if (ret == -EFAULT) - ret = i915_gem_shmem_pwrite_slow(dev, obj, args, file); + if (ret != -EFAULT) + goto out; + /* Fall through to the shmfs paths because the gtt paths might + * fail with non-page-backed user pointers (e.g. gtt mappings + * when moving data between textures). */ } + ret = i915_gem_object_set_to_cpu_domain(obj, 1); + if (ret) + goto out; + + ret = -EFAULT; + if (!i915_gem_object_needs_bit17_swizzle(obj)) + ret = i915_gem_shmem_pwrite_fast(dev, obj, args, file); + if (ret == -EFAULT) + ret = i915_gem_shmem_pwrite_slow(dev, obj, args, file); + out: drm_gem_object_unreference(&obj->base); unlock: @@ -1141,7 +1076,6 @@ int i915_gem_mmap_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { - struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_mmap *args = data; struct drm_gem_object *obj; unsigned long addr; @@ -1153,11 +1087,6 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, if (obj == NULL) return -ENOENT; - if (obj->size > dev_priv->mm.gtt_mappable_end) { - drm_gem_object_unreference_unlocked(obj); - return -E2BIG; - } - down_write(¤t->mm->mmap_sem); addr = do_mmap(obj->filp, 0, args->size, PROT_READ | PROT_WRITE, MAP_SHARED, @@ -1647,6 +1576,28 @@ i915_gem_process_flushing_list(struct intel_ring_buffer *ring, } } +static u32 +i915_gem_get_seqno(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + u32 seqno = dev_priv->next_seqno; + + /* reserve 0 for non-seqno */ + if (++dev_priv->next_seqno == 0) + dev_priv->next_seqno = 1; + + return seqno; +} + +u32 +i915_gem_next_request_seqno(struct intel_ring_buffer *ring) +{ + if (ring->outstanding_lazy_request == 0) + ring->outstanding_lazy_request = i915_gem_get_seqno(ring->dev); + + return ring->outstanding_lazy_request; +} + int i915_add_request(struct intel_ring_buffer *ring, struct drm_file *file, @@ -1654,10 +1605,19 @@ i915_add_request(struct intel_ring_buffer *ring, { drm_i915_private_t *dev_priv = ring->dev->dev_private; uint32_t seqno; + u32 request_ring_position; int was_empty; int ret; BUG_ON(request == NULL); + seqno = i915_gem_next_request_seqno(ring); + + /* Record the position of the start of the request so that + * should we detect the updated seqno part-way through the + * GPU processing the request, we never over-estimate the + * position of the head. + */ + request_ring_position = intel_ring_get_tail(ring); ret = ring->add_request(ring, &seqno); if (ret) @@ -1667,6 +1627,7 @@ i915_add_request(struct intel_ring_buffer *ring, request->seqno = seqno; request->ring = ring; + request->tail = request_ring_position; request->emitted_jiffies = jiffies; was_empty = list_empty(&ring->request_list); list_add_tail(&request->list, &ring->request_list); @@ -1681,7 +1642,7 @@ i915_add_request(struct intel_ring_buffer *ring, spin_unlock(&file_priv->mm.lock); } - ring->outstanding_lazy_request = false; + ring->outstanding_lazy_request = 0; if (!dev_priv->mm.suspended) { if (i915_enable_hangcheck) { @@ -1803,7 +1764,7 @@ void i915_gem_reset(struct drm_device *dev) /** * This function clears the request list as sequence numbers are passed. */ -static void +void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) { uint32_t seqno; @@ -1831,6 +1792,12 @@ i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) break; trace_i915_gem_request_retire(ring, request->seqno); + /* We know the GPU must have read the request to have + * sent us the seqno + interrupt, so use the position + * of tail of the request to update the last known position + * of the GPU head. + */ + ring->last_retired_head = request->tail; list_del(&request->list); i915_gem_request_remove_from_client(request); @@ -1943,7 +1910,8 @@ i915_gem_retire_work_handler(struct work_struct *work) */ int i915_wait_request(struct intel_ring_buffer *ring, - uint32_t seqno) + uint32_t seqno, + bool do_retire) { drm_i915_private_t *dev_priv = ring->dev->dev_private; u32 ier; @@ -2017,17 +1985,12 @@ i915_wait_request(struct intel_ring_buffer *ring, if (atomic_read(&dev_priv->mm.wedged)) ret = -EAGAIN; - if (ret && ret != -ERESTARTSYS) - DRM_ERROR("%s returns %d (awaiting %d at %d, next %d)\n", - __func__, ret, seqno, ring->get_seqno(ring), - dev_priv->next_seqno); - /* Directly dispatch request retiring. While we have the work queue * to handle this, the waiter on a request often wants an associated * buffer to have made it to the inactive list, and we would need * a separate wait queue to handle that. */ - if (ret == 0) + if (ret == 0 && do_retire) i915_gem_retire_requests_ring(ring); return ret; @@ -2051,7 +2014,8 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj) * it. */ if (obj->active) { - ret = i915_wait_request(obj->ring, obj->last_rendering_seqno); + ret = i915_wait_request(obj->ring, obj->last_rendering_seqno, + true); if (ret) return ret; } @@ -2089,6 +2053,7 @@ static void i915_gem_object_finish_gtt(struct drm_i915_gem_object *obj) int i915_gem_object_unbind(struct drm_i915_gem_object *obj) { + drm_i915_private_t *dev_priv = obj->base.dev->dev_private; int ret = 0; if (obj->gtt_space == NULL) @@ -2133,6 +2098,11 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj) trace_i915_gem_object_unbind(obj); i915_gem_gtt_unbind_object(obj); + if (obj->has_aliasing_ppgtt_mapping) { + i915_ppgtt_unbind_object(dev_priv->mm.aliasing_ppgtt, obj); + obj->has_aliasing_ppgtt_mapping = 0; + } + i915_gem_object_put_pages_gtt(obj); list_del_init(&obj->gtt_list); @@ -2172,7 +2142,7 @@ i915_gem_flush_ring(struct intel_ring_buffer *ring, return 0; } -static int i915_ring_idle(struct intel_ring_buffer *ring) +static int i915_ring_idle(struct intel_ring_buffer *ring, bool do_retire) { int ret; @@ -2186,18 +2156,18 @@ static int i915_ring_idle(struct intel_ring_buffer *ring) return ret; } - return i915_wait_request(ring, i915_gem_next_request_seqno(ring)); + return i915_wait_request(ring, i915_gem_next_request_seqno(ring), + do_retire); } -int -i915_gpu_idle(struct drm_device *dev) +int i915_gpu_idle(struct drm_device *dev, bool do_retire) { drm_i915_private_t *dev_priv = dev->dev_private; int ret, i; /* Flush everything onto the inactive list. */ for (i = 0; i < I915_NUM_RINGS; i++) { - ret = i915_ring_idle(&dev_priv->ring[i]); + ret = i915_ring_idle(&dev_priv->ring[i], do_retire); if (ret) return ret; } @@ -2400,7 +2370,8 @@ i915_gem_object_flush_fence(struct drm_i915_gem_object *obj, if (!ring_passed_seqno(obj->last_fenced_ring, obj->last_fenced_seqno)) { ret = i915_wait_request(obj->last_fenced_ring, - obj->last_fenced_seqno); + obj->last_fenced_seqno, + true); if (ret) return ret; } @@ -2432,6 +2403,8 @@ i915_gem_object_put_fence(struct drm_i915_gem_object *obj) if (obj->fence_reg != I915_FENCE_REG_NONE) { struct drm_i915_private *dev_priv = obj->base.dev->dev_private; + + WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count); i915_gem_clear_fence_reg(obj->base.dev, &dev_priv->fence_regs[obj->fence_reg]); @@ -2456,7 +2429,7 @@ i915_find_fence_reg(struct drm_device *dev, if (!reg->obj) return reg; - if (!reg->obj->pin_count) + if (!reg->pin_count) avail = reg; } @@ -2466,7 +2439,7 @@ i915_find_fence_reg(struct drm_device *dev, /* None available, try to steal one or wait for a user to finish */ avail = first = NULL; list_for_each_entry(reg, &dev_priv->mm.fence_list, lru_list) { - if (reg->obj->pin_count) + if (reg->pin_count) continue; if (first == NULL) @@ -2541,7 +2514,8 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj, if (!ring_passed_seqno(obj->last_fenced_ring, reg->setup_seqno)) { ret = i915_wait_request(obj->last_fenced_ring, - reg->setup_seqno); + reg->setup_seqno, + true); if (ret) return ret; } @@ -2560,7 +2534,7 @@ i915_gem_object_get_fence(struct drm_i915_gem_object *obj, reg = i915_find_fence_reg(dev, pipelined); if (reg == NULL) - return -ENOSPC; + return -EDEADLK; ret = i915_gem_object_flush_fence(obj, pipelined); if (ret) @@ -2660,6 +2634,7 @@ i915_gem_clear_fence_reg(struct drm_device *dev, list_del_init(®->lru_list); reg->obj = NULL; reg->setup_seqno = 0; + reg->pin_count = 0; } /** @@ -2946,6 +2921,8 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write) int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, enum i915_cache_level cache_level) { + struct drm_device *dev = obj->base.dev; + drm_i915_private_t *dev_priv = dev->dev_private; int ret; if (obj->cache_level == cache_level) @@ -2974,6 +2951,9 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj, } i915_gem_gtt_rebind_object(obj, cache_level); + if (obj->has_aliasing_ppgtt_mapping) + i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt, + obj, cache_level); } if (cache_level == I915_CACHE_NONE) { @@ -3084,10 +3064,13 @@ i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj) return ret; } + ret = i915_gem_object_wait_rendering(obj); + if (ret) + return ret; + /* Ensure that we invalidate the GPU's caches and TLBs. */ obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS; - - return i915_gem_object_wait_rendering(obj); + return 0; } /** @@ -3619,8 +3602,8 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, obj->base.write_domain = I915_GEM_DOMAIN_CPU; obj->base.read_domains = I915_GEM_DOMAIN_CPU; - if (IS_GEN6(dev) || IS_GEN7(dev)) { - /* On Gen6, we can have the GPU use the LLC (the CPU + if (HAS_LLC(dev)) { + /* On some devices, we can have the GPU use the LLC (the CPU * cache) for about a 10% performance improvement * compared to uncached. Graphics requests other than * display scanout are coherent with the CPU in @@ -3710,7 +3693,7 @@ i915_gem_idle(struct drm_device *dev) return 0; } - ret = i915_gpu_idle(dev); + ret = i915_gpu_idle(dev, true); if (ret) { mutex_unlock(&dev->struct_mutex); return ret; @@ -3745,12 +3728,71 @@ i915_gem_idle(struct drm_device *dev) return 0; } +void i915_gem_init_swizzling(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + + if (INTEL_INFO(dev)->gen < 5 || + dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE) + return; + + I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) | + DISP_TILE_SURFACE_SWIZZLING); + + if (IS_GEN5(dev)) + return; + + I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_SWZCTL); + if (IS_GEN6(dev)) + I915_WRITE(ARB_MODE, ARB_MODE_ENABLE(ARB_MODE_SWIZZLE_SNB)); + else + I915_WRITE(ARB_MODE, ARB_MODE_ENABLE(ARB_MODE_SWIZZLE_IVB)); +} + +void i915_gem_init_ppgtt(struct drm_device *dev) +{ + drm_i915_private_t *dev_priv = dev->dev_private; + uint32_t pd_offset; + struct intel_ring_buffer *ring; + int i; + + if (!dev_priv->mm.aliasing_ppgtt) + return; + + pd_offset = dev_priv->mm.aliasing_ppgtt->pd_offset; + pd_offset /= 64; /* in cachelines, */ + pd_offset <<= 16; + + if (INTEL_INFO(dev)->gen == 6) { + uint32_t ecochk = I915_READ(GAM_ECOCHK); + I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT | + ECOCHK_PPGTT_CACHE64B); + I915_WRITE(GFX_MODE, GFX_MODE_ENABLE(GFX_PPGTT_ENABLE)); + } else if (INTEL_INFO(dev)->gen >= 7) { + I915_WRITE(GAM_ECOCHK, ECOCHK_PPGTT_CACHE64B); + /* GFX_MODE is per-ring on gen7+ */ + } + + for (i = 0; i < I915_NUM_RINGS; i++) { + ring = &dev_priv->ring[i]; + + if (INTEL_INFO(dev)->gen >= 7) + I915_WRITE(RING_MODE_GEN7(ring), + GFX_MODE_ENABLE(GFX_PPGTT_ENABLE)); + + I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G); + I915_WRITE(RING_PP_DIR_BASE(ring), pd_offset); + } +} + int -i915_gem_init_ringbuffer(struct drm_device *dev) +i915_gem_init_hw(struct drm_device *dev) { drm_i915_private_t *dev_priv = dev->dev_private; int ret; + i915_gem_init_swizzling(dev); + ret = intel_init_render_ring_buffer(dev); if (ret) return ret; @@ -3769,6 +3811,8 @@ i915_gem_init_ringbuffer(struct drm_device *dev) dev_priv->next_seqno = 1; + i915_gem_init_ppgtt(dev); + return 0; cleanup_bsd_ring: @@ -3806,7 +3850,7 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data, mutex_lock(&dev->struct_mutex); dev_priv->mm.suspended = 0; - ret = i915_gem_init_ringbuffer(dev); + ret = i915_gem_init_hw(dev); if (ret != 0) { mutex_unlock(&dev->struct_mutex); return ret; @@ -4201,7 +4245,7 @@ rescan: * This has a dramatic impact to reduce the number of * OOM-killer events whilst running the GPU aggressively. */ - if (i915_gpu_idle(dev) == 0) + if (i915_gpu_idle(dev, true) == 0) goto rescan; } mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index ead5d00f91b..21a82710f4b 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -36,7 +36,6 @@ static bool mark_free(struct drm_i915_gem_object *obj, struct list_head *unwind) { list_add(&obj->exec_list, unwind); - drm_gem_object_reference(&obj->base); return drm_mm_scan_add_block(obj->gtt_space); } @@ -49,21 +48,6 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, struct drm_i915_gem_object *obj; int ret = 0; - i915_gem_retire_requests(dev); - - /* Re-check for free space after retiring requests */ - if (mappable) { - if (drm_mm_search_free_in_range(&dev_priv->mm.gtt_space, - min_size, alignment, 0, - dev_priv->mm.gtt_mappable_end, - 0)) - return 0; - } else { - if (drm_mm_search_free(&dev_priv->mm.gtt_space, - min_size, alignment, 0)) - return 0; - } - trace_i915_gem_evict(dev, min_size, alignment, mappable); /* @@ -139,7 +123,6 @@ i915_gem_evict_something(struct drm_device *dev, int min_size, BUG_ON(ret); list_del_init(&obj->exec_list); - drm_gem_object_unreference(&obj->base); } /* We expect the caller to unpin, evict all and try again, or give up. @@ -158,10 +141,10 @@ found: exec_list); if (drm_mm_scan_remove_block(obj->gtt_space)) { list_move(&obj->exec_list, &eviction_list); + drm_gem_object_reference(&obj->base); continue; } list_del_init(&obj->exec_list); - drm_gem_object_unreference(&obj->base); } /* Unbinding will emit any required flushes */ @@ -195,7 +178,7 @@ i915_gem_evict_everything(struct drm_device *dev, bool purgeable_only) trace_i915_gem_evict_everything(dev, purgeable_only); /* Flush everything (on to the inactive lists) and evict */ - ret = i915_gpu_idle(dev); + ret = i915_gpu_idle(dev, true); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 65e1f0043f9..81687af0089 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -203,9 +203,9 @@ i915_gem_object_set_to_gpu_domain(struct drm_i915_gem_object *obj, cd->invalidate_domains |= invalidate_domains; cd->flush_domains |= flush_domains; if (flush_domains & I915_GEM_GPU_DOMAINS) - cd->flush_rings |= obj->ring->id; + cd->flush_rings |= intel_ring_flag(obj->ring); if (invalidate_domains & I915_GEM_GPU_DOMAINS) - cd->flush_rings |= ring->id; + cd->flush_rings |= intel_ring_flag(ring); } struct eb_objects { @@ -287,14 +287,14 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, * exec_object list, so it should have a GTT space bound by now. */ if (unlikely(target_offset == 0)) { - DRM_ERROR("No GTT space found for object %d\n", + DRM_DEBUG("No GTT space found for object %d\n", reloc->target_handle); return ret; } /* Validate that the target is in a valid r/w GPU domain */ if (unlikely(reloc->write_domain & (reloc->write_domain - 1))) { - DRM_ERROR("reloc with multiple write domains: " + DRM_DEBUG("reloc with multiple write domains: " "obj %p target %d offset %d " "read %08x write %08x", obj, reloc->target_handle, @@ -303,8 +303,9 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, reloc->write_domain); return ret; } - if (unlikely((reloc->write_domain | reloc->read_domains) & I915_GEM_DOMAIN_CPU)) { - DRM_ERROR("reloc with read/write CPU domains: " + if (unlikely((reloc->write_domain | reloc->read_domains) + & ~I915_GEM_GPU_DOMAINS)) { + DRM_DEBUG("reloc with read/write non-GPU domains: " "obj %p target %d offset %d " "read %08x write %08x", obj, reloc->target_handle, @@ -315,7 +316,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, } if (unlikely(reloc->write_domain && target_obj->pending_write_domain && reloc->write_domain != target_obj->pending_write_domain)) { - DRM_ERROR("Write domain conflict: " + DRM_DEBUG("Write domain conflict: " "obj %p target %d offset %d " "new %08x old %08x\n", obj, reloc->target_handle, @@ -336,7 +337,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, /* Check that the relocation address is valid... */ if (unlikely(reloc->offset > obj->base.size - 4)) { - DRM_ERROR("Relocation beyond object bounds: " + DRM_DEBUG("Relocation beyond object bounds: " "obj %p target %d offset %d size %d.\n", obj, reloc->target_handle, (int) reloc->offset, @@ -344,7 +345,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, return ret; } if (unlikely(reloc->offset & 3)) { - DRM_ERROR("Relocation not 4-byte aligned: " + DRM_DEBUG("Relocation not 4-byte aligned: " "obj %p target %d offset %d.\n", obj, reloc->target_handle, (int) reloc->offset); @@ -461,11 +462,60 @@ i915_gem_execbuffer_relocate(struct drm_device *dev, return ret; } +#define __EXEC_OBJECT_HAS_FENCE (1<<31) + +static int +pin_and_fence_object(struct drm_i915_gem_object *obj, + struct intel_ring_buffer *ring) +{ + struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; + bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4; + bool need_fence, need_mappable; + int ret; + + need_fence = + has_fenced_gpu_access && + entry->flags & EXEC_OBJECT_NEEDS_FENCE && + obj->tiling_mode != I915_TILING_NONE; + need_mappable = + entry->relocation_count ? true : need_fence; + + ret = i915_gem_object_pin(obj, entry->alignment, need_mappable); + if (ret) + return ret; + + if (has_fenced_gpu_access) { + if (entry->flags & EXEC_OBJECT_NEEDS_FENCE) { + if (obj->tiling_mode) { + ret = i915_gem_object_get_fence(obj, ring); + if (ret) + goto err_unpin; + + entry->flags |= __EXEC_OBJECT_HAS_FENCE; + i915_gem_object_pin_fence(obj); + } else { + ret = i915_gem_object_put_fence(obj); + if (ret) + goto err_unpin; + } + } + obj->pending_fenced_gpu_access = need_fence; + } + + entry->offset = obj->gtt_offset; + return 0; + +err_unpin: + i915_gem_object_unpin(obj); + return ret; +} + static int i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, struct drm_file *file, struct list_head *objects) { + drm_i915_private_t *dev_priv = ring->dev->dev_private; struct drm_i915_gem_object *obj; int ret, retry; bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4; @@ -518,6 +568,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, list_for_each_entry(obj, objects, exec_list) { struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; bool need_fence, need_mappable; + if (!obj->gtt_space) continue; @@ -532,58 +583,55 @@ 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_object_pin(obj, - entry->alignment, - need_mappable); + ret = pin_and_fence_object(obj, ring); if (ret) goto err; - - entry++; } /* Bind fresh objects */ list_for_each_entry(obj, objects, exec_list) { - struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; - bool need_fence; + if (obj->gtt_space) + continue; - need_fence = - has_fenced_gpu_access && - entry->flags & EXEC_OBJECT_NEEDS_FENCE && - obj->tiling_mode != I915_TILING_NONE; + ret = pin_and_fence_object(obj, ring); + if (ret) { + int ret_ignore; + + /* This can potentially raise a harmless + * -EINVAL if we failed to bind in the above + * call. It cannot raise -EINTR since we know + * that the bo is freshly bound and so will + * not need to be flushed or waited upon. + */ + ret_ignore = i915_gem_object_unbind(obj); + (void)ret_ignore; + WARN_ON(obj->gtt_space); + break; + } + } - if (!obj->gtt_space) { - bool need_mappable = - entry->relocation_count ? true : need_fence; + /* Decrement pin count for bound objects */ + list_for_each_entry(obj, objects, exec_list) { + struct drm_i915_gem_exec_object2 *entry; - ret = i915_gem_object_pin(obj, - entry->alignment, - need_mappable); - if (ret) - break; - } + if (!obj->gtt_space) + continue; - if (has_fenced_gpu_access) { - if (need_fence) { - ret = i915_gem_object_get_fence(obj, ring); - if (ret) - break; - } else if (entry->flags & EXEC_OBJECT_NEEDS_FENCE && - obj->tiling_mode == I915_TILING_NONE) { - /* XXX pipelined! */ - ret = i915_gem_object_put_fence(obj); - if (ret) - break; - } - obj->pending_fenced_gpu_access = need_fence; + entry = obj->exec_entry; + if (entry->flags & __EXEC_OBJECT_HAS_FENCE) { + i915_gem_object_unpin_fence(obj); + entry->flags &= ~__EXEC_OBJECT_HAS_FENCE; } - entry->offset = obj->gtt_offset; - } + i915_gem_object_unpin(obj); - /* Decrement pin count for bound objects */ - list_for_each_entry(obj, objects, exec_list) { - if (obj->gtt_space) - i915_gem_object_unpin(obj); + /* ... and ensure ppgtt mapping exist if needed. */ + if (dev_priv->mm.aliasing_ppgtt && !obj->has_aliasing_ppgtt_mapping) { + i915_ppgtt_bind_object(dev_priv->mm.aliasing_ppgtt, + obj, obj->cache_level); + + obj->has_aliasing_ppgtt_mapping = 1; + } } if (ret != -ENOSPC || retry > 1) @@ -600,16 +648,19 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, } while (1); err: - obj = list_entry(obj->exec_list.prev, - struct drm_i915_gem_object, - exec_list); - while (objects != &obj->exec_list) { - if (obj->gtt_space) - i915_gem_object_unpin(obj); + list_for_each_entry_continue_reverse(obj, objects, exec_list) { + struct drm_i915_gem_exec_object2 *entry; + + if (!obj->gtt_space) + continue; + + entry = obj->exec_entry; + if (entry->flags & __EXEC_OBJECT_HAS_FENCE) { + i915_gem_object_unpin_fence(obj); + entry->flags &= ~__EXEC_OBJECT_HAS_FENCE; + } - obj = list_entry(obj->exec_list.prev, - struct drm_i915_gem_object, - exec_list); + i915_gem_object_unpin(obj); } return ret; @@ -682,7 +733,7 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, obj = to_intel_bo(drm_gem_object_lookup(dev, file, exec[i].handle)); if (&obj->base == NULL) { - DRM_ERROR("Invalid object handle %d at index %d\n", + DRM_DEBUG("Invalid object handle %d at index %d\n", exec[i].handle, i); ret = -ENOENT; goto err; @@ -1013,7 +1064,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, int ret, mode, i; if (!i915_gem_check_execbuffer(args)) { - DRM_ERROR("execbuf with invalid offset/length\n"); + DRM_DEBUG("execbuf with invalid offset/length\n"); return -EINVAL; } @@ -1028,20 +1079,20 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, break; case I915_EXEC_BSD: if (!HAS_BSD(dev)) { - DRM_ERROR("execbuf with invalid ring (BSD)\n"); + DRM_DEBUG("execbuf with invalid ring (BSD)\n"); return -EINVAL; } ring = &dev_priv->ring[VCS]; break; case I915_EXEC_BLT: if (!HAS_BLT(dev)) { - DRM_ERROR("execbuf with invalid ring (BLT)\n"); + DRM_DEBUG("execbuf with invalid ring (BLT)\n"); return -EINVAL; } ring = &dev_priv->ring[BCS]; break; default: - DRM_ERROR("execbuf with unknown ring: %d\n", + DRM_DEBUG("execbuf with unknown ring: %d\n", (int)(args->flags & I915_EXEC_RING_MASK)); return -EINVAL; } @@ -1067,18 +1118,18 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } break; default: - DRM_ERROR("execbuf with unknown constants: %d\n", mode); + DRM_DEBUG("execbuf with unknown constants: %d\n", mode); return -EINVAL; } if (args->buffer_count < 1) { - DRM_ERROR("execbuf with %d buffers\n", args->buffer_count); + DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count); return -EINVAL; } if (args->num_cliprects != 0) { if (ring != &dev_priv->ring[RCS]) { - DRM_ERROR("clip rectangles are only valid with the render ring\n"); + DRM_DEBUG("clip rectangles are only valid with the render ring\n"); return -EINVAL; } @@ -1123,7 +1174,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, obj = to_intel_bo(drm_gem_object_lookup(dev, file, exec[i].handle)); if (&obj->base == NULL) { - DRM_ERROR("Invalid object handle %d at index %d\n", + DRM_DEBUG("Invalid object handle %d at index %d\n", exec[i].handle, i); /* prevent error path from reading uninitialized data */ ret = -ENOENT; @@ -1131,7 +1182,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } if (!list_empty(&obj->exec_list)) { - DRM_ERROR("Object %p [handle %d, index %d] appears more than once in object list\n", + DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n", obj, exec[i].handle, i); ret = -EINVAL; goto err; @@ -1169,7 +1220,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, /* Set the pending read domains for the batch buffer to COMMAND */ if (batch_obj->base.pending_write_domain) { - DRM_ERROR("Attempting to use self-modifying batch buffer\n"); + DRM_DEBUG("Attempting to use self-modifying batch buffer\n"); ret = -EINVAL; goto err; } @@ -1186,7 +1237,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, * so every billion or so execbuffers, we need to stall * the GPU in order to reset the counters. */ - ret = i915_gpu_idle(dev); + ret = i915_gpu_idle(dev, true); if (ret) goto err; @@ -1274,7 +1325,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, int ret, i; if (args->buffer_count < 1) { - DRM_ERROR("execbuf with %d buffers\n", args->buffer_count); + DRM_DEBUG("execbuf with %d buffers\n", args->buffer_count); return -EINVAL; } @@ -1282,7 +1333,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, exec_list = drm_malloc_ab(sizeof(*exec_list), args->buffer_count); exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count); if (exec_list == NULL || exec2_list == NULL) { - DRM_ERROR("Failed to allocate exec list for %d buffers\n", + DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); drm_free_large(exec_list); drm_free_large(exec2_list); @@ -1293,7 +1344,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, (uintptr_t) args->buffers_ptr, sizeof(*exec_list) * args->buffer_count); if (ret != 0) { - DRM_ERROR("copy %d exec entries failed %d\n", + DRM_DEBUG("copy %d exec entries failed %d\n", args->buffer_count, ret); drm_free_large(exec_list); drm_free_large(exec2_list); @@ -1334,7 +1385,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data, sizeof(*exec_list) * args->buffer_count); if (ret) { ret = -EFAULT; - DRM_ERROR("failed to copy %d exec entries " + DRM_DEBUG("failed to copy %d exec entries " "back to user (%d)\n", args->buffer_count, ret); } @@ -1354,7 +1405,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, int ret; if (args->buffer_count < 1) { - DRM_ERROR("execbuf2 with %d buffers\n", args->buffer_count); + DRM_DEBUG("execbuf2 with %d buffers\n", args->buffer_count); return -EINVAL; } @@ -1364,7 +1415,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, exec2_list = drm_malloc_ab(sizeof(*exec2_list), args->buffer_count); if (exec2_list == NULL) { - DRM_ERROR("Failed to allocate exec list for %d buffers\n", + DRM_DEBUG("Failed to allocate exec list for %d buffers\n", args->buffer_count); return -ENOMEM; } @@ -1373,7 +1424,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, (uintptr_t) args->buffers_ptr, sizeof(*exec2_list) * args->buffer_count); if (ret != 0) { - DRM_ERROR("copy %d exec entries failed %d\n", + DRM_DEBUG("copy %d exec entries failed %d\n", args->buffer_count, ret); drm_free_large(exec2_list); return -EFAULT; @@ -1388,7 +1439,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data, sizeof(*exec2_list) * args->buffer_count); if (ret) { ret = -EFAULT; - DRM_ERROR("failed to copy %d exec entries " + DRM_DEBUG("failed to copy %d exec entries " "back to user (%d)\n", args->buffer_count, ret); } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 6042c5e6d27..2eacd78bb93 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -29,6 +29,279 @@ #include "i915_trace.h" #include "intel_drv.h" +/* PPGTT support for Sandybdrige/Gen6 and later */ +static void i915_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt, + unsigned first_entry, + unsigned num_entries) +{ + uint32_t *pt_vaddr; + uint32_t scratch_pte; + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES; + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; + unsigned last_pte, i; + + scratch_pte = GEN6_PTE_ADDR_ENCODE(ppgtt->scratch_page_dma_addr); + scratch_pte |= GEN6_PTE_VALID | GEN6_PTE_CACHE_LLC; + + while (num_entries) { + last_pte = first_pte + num_entries; + if (last_pte > I915_PPGTT_PT_ENTRIES) + last_pte = I915_PPGTT_PT_ENTRIES; + + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]); + + for (i = first_pte; i < last_pte; i++) + pt_vaddr[i] = scratch_pte; + + kunmap_atomic(pt_vaddr); + + num_entries -= last_pte - first_pte; + first_pte = 0; + act_pd++; + } +} + +int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_hw_ppgtt *ppgtt; + uint32_t pd_entry; + unsigned first_pd_entry_in_global_pt; + uint32_t __iomem *pd_addr; + int i; + int ret = -ENOMEM; + + /* ppgtt PDEs reside in the global gtt pagetable, which has 512*1024 + * entries. For aliasing ppgtt support we just steal them at the end for + * now. */ + first_pd_entry_in_global_pt = 512*1024 - I915_PPGTT_PD_ENTRIES; + + ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL); + if (!ppgtt) + return ret; + + ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES; + ppgtt->pt_pages = kzalloc(sizeof(struct page *)*ppgtt->num_pd_entries, + GFP_KERNEL); + if (!ppgtt->pt_pages) + goto err_ppgtt; + + for (i = 0; i < ppgtt->num_pd_entries; i++) { + ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL); + if (!ppgtt->pt_pages[i]) + goto err_pt_alloc; + } + + if (dev_priv->mm.gtt->needs_dmar) { + ppgtt->pt_dma_addr = kzalloc(sizeof(dma_addr_t) + *ppgtt->num_pd_entries, + GFP_KERNEL); + if (!ppgtt->pt_dma_addr) + goto err_pt_alloc; + } + + pd_addr = dev_priv->mm.gtt->gtt + first_pd_entry_in_global_pt; + for (i = 0; i < ppgtt->num_pd_entries; i++) { + dma_addr_t pt_addr; + if (dev_priv->mm.gtt->needs_dmar) { + pt_addr = pci_map_page(dev->pdev, ppgtt->pt_pages[i], + 0, 4096, + PCI_DMA_BIDIRECTIONAL); + + if (pci_dma_mapping_error(dev->pdev, + pt_addr)) { + ret = -EIO; + goto err_pd_pin; + + } + ppgtt->pt_dma_addr[i] = pt_addr; + } else + pt_addr = page_to_phys(ppgtt->pt_pages[i]); + + pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr); + pd_entry |= GEN6_PDE_VALID; + + writel(pd_entry, pd_addr + i); + } + readl(pd_addr); + + ppgtt->scratch_page_dma_addr = dev_priv->mm.gtt->scratch_page_dma; + + i915_ppgtt_clear_range(ppgtt, 0, + ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES); + + ppgtt->pd_offset = (first_pd_entry_in_global_pt)*sizeof(uint32_t); + + dev_priv->mm.aliasing_ppgtt = ppgtt; + + return 0; + +err_pd_pin: + if (ppgtt->pt_dma_addr) { + for (i--; i >= 0; i--) + pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i], + 4096, PCI_DMA_BIDIRECTIONAL); + } +err_pt_alloc: + kfree(ppgtt->pt_dma_addr); + for (i = 0; i < ppgtt->num_pd_entries; i++) { + if (ppgtt->pt_pages[i]) + __free_page(ppgtt->pt_pages[i]); + } + kfree(ppgtt->pt_pages); +err_ppgtt: + kfree(ppgtt); + + return ret; +} + +void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; + int i; + + if (!ppgtt) + return; + + if (ppgtt->pt_dma_addr) { + for (i = 0; i < ppgtt->num_pd_entries; i++) + pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i], + 4096, PCI_DMA_BIDIRECTIONAL); + } + + kfree(ppgtt->pt_dma_addr); + for (i = 0; i < ppgtt->num_pd_entries; i++) + __free_page(ppgtt->pt_pages[i]); + kfree(ppgtt->pt_pages); + kfree(ppgtt); +} + +static void i915_ppgtt_insert_sg_entries(struct i915_hw_ppgtt *ppgtt, + struct scatterlist *sg_list, + unsigned sg_len, + unsigned first_entry, + uint32_t pte_flags) +{ + uint32_t *pt_vaddr, pte; + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES; + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; + unsigned i, j, m, segment_len; + dma_addr_t page_addr; + struct scatterlist *sg; + + /* init sg walking */ + sg = sg_list; + i = 0; + segment_len = sg_dma_len(sg) >> PAGE_SHIFT; + m = 0; + + while (i < sg_len) { + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]); + + for (j = first_pte; j < I915_PPGTT_PT_ENTRIES; j++) { + page_addr = sg_dma_address(sg) + (m << PAGE_SHIFT); + pte = GEN6_PTE_ADDR_ENCODE(page_addr); + pt_vaddr[j] = pte | pte_flags; + + /* grab the next page */ + m++; + if (m == segment_len) { + sg = sg_next(sg); + i++; + if (i == sg_len) + break; + + segment_len = sg_dma_len(sg) >> PAGE_SHIFT; + m = 0; + } + } + + kunmap_atomic(pt_vaddr); + + first_pte = 0; + act_pd++; + } +} + +static void i915_ppgtt_insert_pages(struct i915_hw_ppgtt *ppgtt, + unsigned first_entry, unsigned num_entries, + struct page **pages, uint32_t pte_flags) +{ + uint32_t *pt_vaddr, pte; + unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES; + unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES; + unsigned last_pte, i; + dma_addr_t page_addr; + + while (num_entries) { + last_pte = first_pte + num_entries; + last_pte = min_t(unsigned, last_pte, I915_PPGTT_PT_ENTRIES); + + pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]); + + for (i = first_pte; i < last_pte; i++) { + page_addr = page_to_phys(*pages); + pte = GEN6_PTE_ADDR_ENCODE(page_addr); + pt_vaddr[i] = pte | pte_flags; + + pages++; + } + + kunmap_atomic(pt_vaddr); + + num_entries -= last_pte - first_pte; + first_pte = 0; + act_pd++; + } +} + +void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_object *obj, + enum i915_cache_level cache_level) +{ + struct drm_device *dev = obj->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t pte_flags = GEN6_PTE_VALID; + + switch (cache_level) { + case I915_CACHE_LLC_MLC: + pte_flags |= GEN6_PTE_CACHE_LLC_MLC; + break; + case I915_CACHE_LLC: + pte_flags |= GEN6_PTE_CACHE_LLC; + break; + case I915_CACHE_NONE: + pte_flags |= GEN6_PTE_UNCACHED; + break; + default: + BUG(); + } + + if (dev_priv->mm.gtt->needs_dmar) { + BUG_ON(!obj->sg_list); + + i915_ppgtt_insert_sg_entries(ppgtt, + obj->sg_list, + obj->num_sg, + obj->gtt_space->start >> PAGE_SHIFT, + pte_flags); + } else + i915_ppgtt_insert_pages(ppgtt, + obj->gtt_space->start >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT, + obj->pages, + pte_flags); +} + +void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt, + struct drm_i915_gem_object *obj) +{ + i915_ppgtt_clear_range(ppgtt, + obj->gtt_space->start >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT); +} + /* XXX kill agp_type! */ static unsigned int cache_level_to_agp_type(struct drm_device *dev, enum i915_cache_level cache_level) @@ -55,7 +328,7 @@ static bool do_idling(struct drm_i915_private *dev_priv) if (unlikely(dev_priv->mm.gtt->do_idle_maps)) { dev_priv->mm.interruptible = false; - if (i915_gpu_idle(dev_priv->dev)) { + if (i915_gpu_idle(dev_priv->dev, false)) { DRM_ERROR("Couldn't idle GPU\n"); /* Wait a bit, in hopes it avoids the hang */ udelay(10); diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 31d334d9d9d..1a930666598 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -93,8 +93,23 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev) uint32_t swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN; if (INTEL_INFO(dev)->gen >= 6) { - swizzle_x = I915_BIT_6_SWIZZLE_NONE; - swizzle_y = I915_BIT_6_SWIZZLE_NONE; + uint32_t dimm_c0, dimm_c1; + dimm_c0 = I915_READ(MAD_DIMM_C0); + dimm_c1 = I915_READ(MAD_DIMM_C1); + dimm_c0 &= MAD_DIMM_A_SIZE_MASK | MAD_DIMM_B_SIZE_MASK; + dimm_c1 &= MAD_DIMM_A_SIZE_MASK | MAD_DIMM_B_SIZE_MASK; + /* Enable swizzling when the channels are populated with + * identically sized dimms. We don't need to check the 3rd + * channel because no cpu with gpu attached ships in that + * configuration. Also, swizzling only makes sense for 2 + * channels anyway. */ + if (dimm_c0 == dimm_c1) { + swizzle_x = I915_BIT_6_SWIZZLE_9_10; + swizzle_y = I915_BIT_6_SWIZZLE_9; + } else { + swizzle_x = I915_BIT_6_SWIZZLE_NONE; + swizzle_y = I915_BIT_6_SWIZZLE_NONE; + } } else if (IS_GEN5(dev)) { /* On Ironlake whatever DRAM config, GPU always do * same swizzling setup. @@ -107,10 +122,10 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev) */ swizzle_x = I915_BIT_6_SWIZZLE_NONE; swizzle_y = I915_BIT_6_SWIZZLE_NONE; - } else if (IS_MOBILE(dev)) { + } else if (IS_MOBILE(dev) || (IS_GEN3(dev) && !IS_G33(dev))) { uint32_t dcc; - /* On mobile 9xx chipsets, channel interleave by the CPU is + /* On 9xx chipsets, channel interleave by the CPU is * determined by DCC. For single-channel, neither the CPU * nor the GPU do swizzling. For dual channel interleaved, * the GPU's interleave is bit 9 and 10 for X tiled, and bit diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 5bd4361ea84..afd4e03e337 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -720,7 +720,6 @@ i915_error_object_create(struct drm_i915_private *dev_priv, reloc_offset = src->gtt_offset; for (page = 0; page < page_count; page++) { unsigned long flags; - void __iomem *s; void *d; d = kmalloc(PAGE_SIZE, GFP_ATOMIC); @@ -728,10 +727,29 @@ i915_error_object_create(struct drm_i915_private *dev_priv, goto unwind; local_irq_save(flags); - s = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, - reloc_offset); - memcpy_fromio(d, s, PAGE_SIZE); - io_mapping_unmap_atomic(s); + if (reloc_offset < dev_priv->mm.gtt_mappable_end) { + void __iomem *s; + + /* Simply ignore tiling or any overlapping fence. + * It's part of the error state, and this hopefully + * captures what the GPU read. + */ + + s = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping, + reloc_offset); + memcpy_fromio(d, s, PAGE_SIZE); + io_mapping_unmap_atomic(s); + } else { + void *s; + + drm_clflush_pages(&src->pages[page], 1); + + s = kmap_atomic(src->pages[page]); + memcpy(d, s, PAGE_SIZE); + kunmap_atomic(s); + + drm_clflush_pages(&src->pages[page], 1); + } local_irq_restore(flags); dst->pages[page] = d; @@ -770,11 +788,11 @@ i915_error_state_free(struct drm_device *dev, { int i; - for (i = 0; i < ARRAY_SIZE(error->batchbuffer); i++) - i915_error_object_free(error->batchbuffer[i]); - - for (i = 0; i < ARRAY_SIZE(error->ringbuffer); i++) - i915_error_object_free(error->ringbuffer[i]); + for (i = 0; i < ARRAY_SIZE(error->ring); i++) { + i915_error_object_free(error->ring[i].batchbuffer); + i915_error_object_free(error->ring[i].ringbuffer); + kfree(error->ring[i].requests); + } kfree(error->active_bo); kfree(error->overlay); @@ -804,7 +822,7 @@ static u32 capture_bo_list(struct drm_i915_error_buffer *err, err->tiling = obj->tiling_mode; err->dirty = obj->dirty; err->purgeable = obj->madv != I915_MADV_WILLNEED; - err->ring = obj->ring ? obj->ring->id : 0; + err->ring = obj->ring ? obj->ring->id : -1; err->cache_level = obj->cache_level; if (++i == count) @@ -876,6 +894,92 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv, return NULL; } +static void i915_record_ring_state(struct drm_device *dev, + struct drm_i915_error_state *error, + struct intel_ring_buffer *ring) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + if (INTEL_INFO(dev)->gen >= 6) { + error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base)); + error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring)); + error->semaphore_mboxes[ring->id][0] + = I915_READ(RING_SYNC_0(ring->mmio_base)); + error->semaphore_mboxes[ring->id][1] + = I915_READ(RING_SYNC_1(ring->mmio_base)); + } + + if (INTEL_INFO(dev)->gen >= 4) { + error->ipeir[ring->id] = I915_READ(RING_IPEIR(ring->mmio_base)); + error->ipehr[ring->id] = I915_READ(RING_IPEHR(ring->mmio_base)); + error->instdone[ring->id] = I915_READ(RING_INSTDONE(ring->mmio_base)); + error->instps[ring->id] = I915_READ(RING_INSTPS(ring->mmio_base)); + if (ring->id == RCS) { + error->instdone1 = I915_READ(INSTDONE1); + error->bbaddr = I915_READ64(BB_ADDR); + } + } else { + error->ipeir[ring->id] = I915_READ(IPEIR); + error->ipehr[ring->id] = I915_READ(IPEHR); + error->instdone[ring->id] = I915_READ(INSTDONE); + } + + error->instpm[ring->id] = I915_READ(RING_INSTPM(ring->mmio_base)); + error->seqno[ring->id] = ring->get_seqno(ring); + error->acthd[ring->id] = intel_ring_get_active_head(ring); + error->head[ring->id] = I915_READ_HEAD(ring); + error->tail[ring->id] = I915_READ_TAIL(ring); + + error->cpu_ring_head[ring->id] = ring->head; + error->cpu_ring_tail[ring->id] = ring->tail; +} + +static void i915_gem_record_rings(struct drm_device *dev, + struct drm_i915_error_state *error) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_request *request; + int i, count; + + for (i = 0; i < I915_NUM_RINGS; i++) { + struct intel_ring_buffer *ring = &dev_priv->ring[i]; + + if (ring->obj == NULL) + continue; + + i915_record_ring_state(dev, error, ring); + + error->ring[i].batchbuffer = + i915_error_first_batchbuffer(dev_priv, ring); + + error->ring[i].ringbuffer = + i915_error_object_create(dev_priv, ring->obj); + + count = 0; + list_for_each_entry(request, &ring->request_list, list) + count++; + + error->ring[i].num_requests = count; + error->ring[i].requests = + kmalloc(count*sizeof(struct drm_i915_error_request), + GFP_ATOMIC); + if (error->ring[i].requests == NULL) { + error->ring[i].num_requests = 0; + continue; + } + + count = 0; + list_for_each_entry(request, &ring->request_list, list) { + struct drm_i915_error_request *erq; + + erq = &error->ring[i].requests[count++]; + erq->seqno = request->seqno; + erq->jiffies = request->emitted_jiffies; + erq->tail = request->tail; + } + } +} + /** * i915_capture_error_state - capture an error record for later analysis * @dev: drm device @@ -900,7 +1004,7 @@ static void i915_capture_error_state(struct drm_device *dev) return; /* Account for pipe specific data like PIPE*STAT */ - error = kmalloc(sizeof(*error), GFP_ATOMIC); + error = kzalloc(sizeof(*error), GFP_ATOMIC); if (!error) { DRM_DEBUG_DRIVER("out of memory, not capturing error state\n"); return; @@ -909,59 +1013,18 @@ static void i915_capture_error_state(struct drm_device *dev) DRM_INFO("capturing error event; look for more information in /debug/dri/%d/i915_error_state\n", dev->primary->index); - error->seqno = dev_priv->ring[RCS].get_seqno(&dev_priv->ring[RCS]); error->eir = I915_READ(EIR); error->pgtbl_er = I915_READ(PGTBL_ER); for_each_pipe(pipe) error->pipestat[pipe] = I915_READ(PIPESTAT(pipe)); - error->instpm = I915_READ(INSTPM); - error->error = 0; + if (INTEL_INFO(dev)->gen >= 6) { error->error = I915_READ(ERROR_GEN6); - - error->bcs_acthd = I915_READ(BCS_ACTHD); - error->bcs_ipehr = I915_READ(BCS_IPEHR); - error->bcs_ipeir = I915_READ(BCS_IPEIR); - error->bcs_instdone = I915_READ(BCS_INSTDONE); - error->bcs_seqno = 0; - if (dev_priv->ring[BCS].get_seqno) - error->bcs_seqno = dev_priv->ring[BCS].get_seqno(&dev_priv->ring[BCS]); - - error->vcs_acthd = I915_READ(VCS_ACTHD); - error->vcs_ipehr = I915_READ(VCS_IPEHR); - error->vcs_ipeir = I915_READ(VCS_IPEIR); - error->vcs_instdone = I915_READ(VCS_INSTDONE); - error->vcs_seqno = 0; - if (dev_priv->ring[VCS].get_seqno) - error->vcs_seqno = dev_priv->ring[VCS].get_seqno(&dev_priv->ring[VCS]); + error->done_reg = I915_READ(DONE_REG); } - if (INTEL_INFO(dev)->gen >= 4) { - error->ipeir = I915_READ(IPEIR_I965); - error->ipehr = I915_READ(IPEHR_I965); - error->instdone = I915_READ(INSTDONE_I965); - error->instps = I915_READ(INSTPS); - error->instdone1 = I915_READ(INSTDONE1); - error->acthd = I915_READ(ACTHD_I965); - error->bbaddr = I915_READ64(BB_ADDR); - } else { - error->ipeir = I915_READ(IPEIR); - error->ipehr = I915_READ(IPEHR); - error->instdone = I915_READ(INSTDONE); - error->acthd = I915_READ(ACTHD); - error->bbaddr = 0; - } - i915_gem_record_fences(dev, error); - - /* Record the active batch and ring buffers */ - for (i = 0; i < I915_NUM_RINGS; i++) { - error->batchbuffer[i] = - i915_error_first_batchbuffer(dev_priv, - &dev_priv->ring[i]); - error->ringbuffer[i] = - i915_error_object_create(dev_priv, - dev_priv->ring[i].obj); - } + i915_gem_record_fences(dev, error); + i915_gem_record_rings(dev, error); /* Record buffers on the active and pinned lists. */ error->active_bo = NULL; @@ -1017,11 +1080,12 @@ void i915_destroy_error_state(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_error_state *error; + unsigned long flags; - spin_lock(&dev_priv->error_lock); + spin_lock_irqsave(&dev_priv->error_lock, flags); error = dev_priv->first_error; dev_priv->first_error = NULL; - spin_unlock(&dev_priv->error_lock); + spin_unlock_irqrestore(&dev_priv->error_lock, flags); if (error) i915_error_state_free(dev, error); @@ -1698,6 +1762,7 @@ void i915_hangcheck_elapsed(unsigned long data) dev_priv->last_instdone1 == instdone1) { if (dev_priv->hangcheck_count++ > 1) { DRM_ERROR("Hangcheck timer elapsed... GPU hung\n"); + i915_handle_error(dev, true); if (!IS_GEN2(dev)) { /* Is the chip hanging on a WAIT_FOR_EVENT? @@ -1705,7 +1770,6 @@ void i915_hangcheck_elapsed(unsigned long data) * and break the hang. This should work on * all but the second generation chipsets. */ - if (kick_ring(&dev_priv->ring[RCS])) goto repeat; @@ -1718,7 +1782,6 @@ void i915_hangcheck_elapsed(unsigned long data) goto repeat; } - i915_handle_error(dev, true); return; } } else { @@ -1752,18 +1815,6 @@ static void ironlake_irq_preinstall(struct drm_device *dev) I915_WRITE(HWSTAM, 0xeffe); - if (IS_GEN6(dev)) { - /* Workaround stalls observed on Sandy Bridge GPUs by - * making the blitter command streamer generate a - * write to the Hardware Status Page for - * MI_USER_INTERRUPT. This appears to serialize the - * previous seqno write out before the interrupt - * happens. - */ - I915_WRITE(GEN6_BLITTER_HWSTAM, ~GEN6_BLITTER_USER_INTERRUPT); - I915_WRITE(GEN6_BSD_HWSTAM, ~GEN6_BSD_USER_INTERRUPT); - } - /* XXX hotplug from PCH */ I915_WRITE(DEIMR, 0xffffffff); diff --git a/drivers/gpu/drm/i915/i915_mem.c b/drivers/gpu/drm/i915/i915_mem.c deleted file mode 100644 index cc8f6d49cf2..00000000000 --- a/drivers/gpu/drm/i915/i915_mem.c +++ /dev/null @@ -1,387 +0,0 @@ -/* i915_mem.c -- Simple agp/fb memory manager for i915 -*- linux-c -*- - */ -/* - * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas. - * All Rights Reserved. - * - * 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 "drmP.h" -#include "drm.h" -#include "i915_drm.h" -#include "i915_drv.h" - -/* This memory manager is integrated into the global/local lru - * mechanisms used by the clients. Specifically, it operates by - * setting the 'in_use' fields of the global LRU to indicate whether - * this region is privately allocated to a client. - * - * This does require the client to actually respect that field. - * - * Currently no effort is made to allocate 'private' memory in any - * clever way - the LRU information isn't used to determine which - * block to allocate, and the ring is drained prior to allocations -- - * in other words allocation is expensive. - */ -static void mark_block(struct drm_device * dev, struct mem_block *p, int in_use) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv; - drm_i915_sarea_t *sarea_priv = master_priv->sarea_priv; - struct drm_tex_region *list; - unsigned shift, nr; - unsigned start; - unsigned end; - unsigned i; - int age; - - shift = dev_priv->tex_lru_log_granularity; - nr = I915_NR_TEX_REGIONS; - - start = p->start >> shift; - end = (p->start + p->size - 1) >> shift; - - age = ++sarea_priv->texAge; - list = sarea_priv->texList; - - /* Mark the regions with the new flag and update their age. Move - * them to head of list to preserve LRU semantics. - */ - for (i = start; i <= end; i++) { - list[i].in_use = in_use; - list[i].age = age; - - /* remove_from_list(i) - */ - list[(unsigned)list[i].next].prev = list[i].prev; - list[(unsigned)list[i].prev].next = list[i].next; - - /* insert_at_head(list, i) - */ - list[i].prev = nr; - list[i].next = list[nr].next; - list[(unsigned)list[nr].next].prev = i; - list[nr].next = i; - } -} - -/* Very simple allocator for agp memory, working on a static range - * already mapped into each client's address space. - */ - -static struct mem_block *split_block(struct mem_block *p, int start, int size, - struct drm_file *file_priv) -{ - /* Maybe cut off the start of an existing block */ - if (start > p->start) { - struct mem_block *newblock = kmalloc(sizeof(*newblock), - GFP_KERNEL); - if (!newblock) - goto out; - newblock->start = start; - newblock->size = p->size - (start - p->start); - newblock->file_priv = NULL; - newblock->next = p->next; - newblock->prev = p; - p->next->prev = newblock; - p->next = newblock; - p->size -= newblock->size; - p = newblock; - } - - /* Maybe cut off the end of an existing block */ - if (size < p->size) { - struct mem_block *newblock = kmalloc(sizeof(*newblock), - GFP_KERNEL); - if (!newblock) - goto out; - newblock->start = start + size; - newblock->size = p->size - size; - newblock->file_priv = NULL; - newblock->next = p->next; - newblock->prev = p; - p->next->prev = newblock; - p->next = newblock; - p->size = size; - } - - out: - /* Our block is in the middle */ - p->file_priv = file_priv; - return p; -} - -static struct mem_block *alloc_block(struct mem_block *heap, int size, - int align2, struct drm_file *file_priv) -{ - struct mem_block *p; - int mask = (1 << align2) - 1; - - for (p = heap->next; p != heap; p = p->next) { - int start = (p->start + mask) & ~mask; - if (p->file_priv == NULL && start + size <= p->start + p->size) - return split_block(p, start, size, file_priv); - } - - return NULL; -} - -static struct mem_block *find_block(struct mem_block *heap, int start) -{ - struct mem_block *p; - - for (p = heap->next; p != heap; p = p->next) - if (p->start == start) - return p; - - return NULL; -} - -static void free_block(struct mem_block *p) -{ - p->file_priv = NULL; - - /* Assumes a single contiguous range. Needs a special file_priv in - * 'heap' to stop it being subsumed. - */ - if (p->next->file_priv == NULL) { - struct mem_block *q = p->next; - p->size += q->size; - p->next = q->next; - p->next->prev = p; - kfree(q); - } - - if (p->prev->file_priv == NULL) { - struct mem_block *q = p->prev; - q->size += p->size; - q->next = p->next; - q->next->prev = q; - kfree(p); - } -} - -/* Initialize. How to check for an uninitialized heap? - */ -static int init_heap(struct mem_block **heap, int start, int size) -{ - struct mem_block *blocks = kmalloc(sizeof(*blocks), GFP_KERNEL); - - if (!blocks) - return -ENOMEM; - - *heap = kmalloc(sizeof(**heap), GFP_KERNEL); - if (!*heap) { - kfree(blocks); - return -ENOMEM; - } - - blocks->start = start; - blocks->size = size; - blocks->file_priv = NULL; - blocks->next = blocks->prev = *heap; - - memset(*heap, 0, sizeof(**heap)); - (*heap)->file_priv = (struct drm_file *) -1; - (*heap)->next = (*heap)->prev = blocks; - return 0; -} - -/* Free all blocks associated with the releasing file. - */ -void i915_mem_release(struct drm_device * dev, struct drm_file *file_priv, - struct mem_block *heap) -{ - struct mem_block *p; - - if (!heap || !heap->next) - return; - - for (p = heap->next; p != heap; p = p->next) { - if (p->file_priv == file_priv) { - p->file_priv = NULL; - mark_block(dev, p, 0); - } - } - - /* Assumes a single contiguous range. Needs a special file_priv in - * 'heap' to stop it being subsumed. - */ - for (p = heap->next; p != heap; p = p->next) { - while (p->file_priv == NULL && p->next->file_priv == NULL) { - struct mem_block *q = p->next; - p->size += q->size; - p->next = q->next; - p->next->prev = p; - kfree(q); - } - } -} - -/* Shutdown. - */ -void i915_mem_takedown(struct mem_block **heap) -{ - struct mem_block *p; - - if (!*heap) - return; - - for (p = (*heap)->next; p != *heap;) { - struct mem_block *q = p; - p = p->next; - kfree(q); - } - - kfree(*heap); - *heap = NULL; -} - -static struct mem_block **get_heap(drm_i915_private_t * dev_priv, int region) -{ - switch (region) { - case I915_MEM_REGION_AGP: - return &dev_priv->agp_heap; - default: - return NULL; - } -} - -/* IOCTL HANDLERS */ - -int i915_mem_alloc(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - drm_i915_mem_alloc_t *alloc = data; - struct mem_block *block, **heap; - - if (!dev_priv) { - DRM_ERROR("called with no initialization\n"); - return -EINVAL; - } - - heap = get_heap(dev_priv, alloc->region); - if (!heap || !*heap) - return -EFAULT; - - /* Make things easier on ourselves: all allocations at least - * 4k aligned. - */ - if (alloc->alignment < 12) - alloc->alignment = 12; - - block = alloc_block(*heap, alloc->size, alloc->alignment, file_priv); - - if (!block) - return -ENOMEM; - - mark_block(dev, block, 1); - - if (DRM_COPY_TO_USER(alloc->region_offset, &block->start, - sizeof(int))) { - DRM_ERROR("copy_to_user\n"); - return -EFAULT; - } - - return 0; -} - -int i915_mem_free(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - drm_i915_mem_free_t *memfree = data; - struct mem_block *block, **heap; - - if (!dev_priv) { - DRM_ERROR("called with no initialization\n"); - return -EINVAL; - } - - heap = get_heap(dev_priv, memfree->region); - if (!heap || !*heap) - return -EFAULT; - - block = find_block(*heap, memfree->region_offset); - if (!block) - return -EFAULT; - - if (block->file_priv != file_priv) - return -EPERM; - - mark_block(dev, block, 0); - free_block(block); - return 0; -} - -int i915_mem_init_heap(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - drm_i915_mem_init_heap_t *initheap = data; - struct mem_block **heap; - - if (!dev_priv) { - DRM_ERROR("called with no initialization\n"); - return -EINVAL; - } - - heap = get_heap(dev_priv, initheap->region); - if (!heap) - return -EFAULT; - - if (*heap) { - DRM_ERROR("heap already initialized?"); - return -EFAULT; - } - - return init_heap(heap, initheap->start, initheap->size); -} - -int i915_mem_destroy_heap(struct drm_device *dev, void *data, - struct drm_file *file_priv) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - drm_i915_mem_destroy_heap_t *destroyheap = data; - struct mem_block **heap; - - if (!dev_priv) { - DRM_ERROR("called with no initialization\n"); - return -EINVAL; - } - - heap = get_heap(dev_priv, destroyheap->region); - if (!heap) { - DRM_ERROR("get_heap failed"); - return -EFAULT; - } - - if (!*heap) { - DRM_ERROR("heap not initialized?"); - return -EFAULT; - } - - i915_mem_takedown(heap); - return 0; -} diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 558ac716a32..3886cf051ba 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -86,12 +86,45 @@ #define GEN6_MBC_SNPCR_LOW (2<<21) #define GEN6_MBC_SNPCR_MIN (3<<21) /* only 1/16th of the cache is shared */ +#define GEN6_MBCTL 0x0907c +#define GEN6_MBCTL_ENABLE_BOOT_FETCH (1 << 4) +#define GEN6_MBCTL_CTX_FETCH_NEEDED (1 << 3) +#define GEN6_MBCTL_BME_UPDATE_ENABLE (1 << 2) +#define GEN6_MBCTL_MAE_UPDATE_ENABLE (1 << 1) +#define GEN6_MBCTL_BOOT_FETCH_MECH (1 << 0) + #define GEN6_GDRST 0x941c #define GEN6_GRDOM_FULL (1 << 0) #define GEN6_GRDOM_RENDER (1 << 1) #define GEN6_GRDOM_MEDIA (1 << 2) #define GEN6_GRDOM_BLT (1 << 3) +/* PPGTT stuff */ +#define GEN6_GTT_ADDR_ENCODE(addr) ((addr) | (((addr) >> 28) & 0xff0)) + +#define GEN6_PDE_VALID (1 << 0) +#define GEN6_PDE_LARGE_PAGE (2 << 0) /* use 32kb pages */ +/* gen6+ has bit 11-4 for physical addr bit 39-32 */ +#define GEN6_PDE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) + +#define GEN6_PTE_VALID (1 << 0) +#define GEN6_PTE_UNCACHED (1 << 1) +#define GEN6_PTE_CACHE_LLC (2 << 1) +#define GEN6_PTE_CACHE_LLC_MLC (3 << 1) +#define GEN6_PTE_CACHE_BITS (3 << 1) +#define GEN6_PTE_GFDT (1 << 3) +#define GEN6_PTE_ADDR_ENCODE(addr) GEN6_GTT_ADDR_ENCODE(addr) + +#define RING_PP_DIR_BASE(ring) ((ring)->mmio_base+0x228) +#define RING_PP_DIR_BASE_READ(ring) ((ring)->mmio_base+0x518) +#define RING_PP_DIR_DCLV(ring) ((ring)->mmio_base+0x220) +#define PP_DIR_DCLV_2G 0xffffffff + +#define GAM_ECOCHK 0x4090 +#define ECOCHK_SNB_BIT (1<<10) +#define ECOCHK_PPGTT_CACHE64B (0x3<<3) +#define ECOCHK_PPGTT_CACHE4B (0x0<<3) + /* VGA stuff */ #define VGA_ST01_MDA 0x3ba @@ -295,6 +328,12 @@ #define FENCE_REG_SANDYBRIDGE_0 0x100000 #define SANDYBRIDGE_FENCE_PITCH_SHIFT 32 +/* control register for cpu gtt access */ +#define TILECTL 0x101000 +#define TILECTL_SWZCTL (1 << 0) +#define TILECTL_TLB_PREFETCH_DIS (1 << 2) +#define TILECTL_BACKSNOOP_DIS (1 << 3) + /* * Instruction and interrupt control regs */ @@ -318,7 +357,14 @@ #define RING_MAX_IDLE(base) ((base)+0x54) #define RING_HWS_PGA(base) ((base)+0x80) #define RING_HWS_PGA_GEN6(base) ((base)+0x2080) +#define ARB_MODE 0x04030 +#define ARB_MODE_SWIZZLE_SNB (1<<4) +#define ARB_MODE_SWIZZLE_IVB (1<<5) +#define ARB_MODE_ENABLE(x) GFX_MODE_ENABLE(x) +#define ARB_MODE_DISABLE(x) GFX_MODE_DISABLE(x) #define RENDER_HWS_PGA_GEN7 (0x04080) +#define RING_FAULT_REG(ring) (0x4094 + 0x100*(ring)->id) +#define DONE_REG 0x40b0 #define BSD_HWS_PGA_GEN7 (0x04180) #define BLT_HWS_PGA_GEN7 (0x04280) #define RING_ACTHD(base) ((base)+0x74) @@ -352,6 +398,12 @@ #define IPEIR_I965 0x02064 #define IPEHR_I965 0x02068 #define INSTDONE_I965 0x0206c +#define RING_IPEIR(base) ((base)+0x64) +#define RING_IPEHR(base) ((base)+0x68) +#define RING_INSTDONE(base) ((base)+0x6c) +#define RING_INSTPS(base) ((base)+0x70) +#define RING_DMA_FADD(base) ((base)+0x78) +#define RING_INSTPM(base) ((base)+0xc0) #define INSTPS 0x02070 /* 965+ only */ #define INSTDONE1 0x0207c /* 965+ only */ #define ACTHD_I965 0x02074 @@ -365,14 +417,6 @@ #define INSTDONE 0x02090 #define NOPID 0x02094 #define HWSTAM 0x02098 -#define VCS_INSTDONE 0x1206C -#define VCS_IPEIR 0x12064 -#define VCS_IPEHR 0x12068 -#define VCS_ACTHD 0x12074 -#define BCS_INSTDONE 0x2206C -#define BCS_IPEIR 0x22064 -#define BCS_IPEHR 0x22068 -#define BCS_ACTHD 0x22074 #define ERROR_GEN6 0x040a0 @@ -391,10 +435,11 @@ #define MI_MODE 0x0209c # define VS_TIMER_DISPATCH (1 << 6) -# define MI_FLUSH_ENABLE (1 << 11) +# define MI_FLUSH_ENABLE (1 << 12) #define GFX_MODE 0x02520 #define GFX_MODE_GEN7 0x0229c +#define RING_MODE_GEN7(ring) ((ring)->mmio_base+0x29c) #define GFX_RUN_LIST_ENABLE (1<<15) #define GFX_TLB_INVALIDATE_ALWAYS (1<<13) #define GFX_SURFACE_FAULT_ENABLE (1<<12) @@ -1037,6 +1082,29 @@ #define C0DRB3 0x10206 #define C1DRB3 0x10606 +/** snb MCH registers for reading the DRAM channel configuration */ +#define MAD_DIMM_C0 (MCHBAR_MIRROR_BASE_SNB + 0x5004) +#define MAD_DIMM_C1 (MCHBAR_MIRROR_BASE_SNB + 0x5008) +#define MAD_DIMM_C2 (MCHBAR_MIRROR_BASE_SNB + 0x500C) +#define MAD_DIMM_ECC_MASK (0x3 << 24) +#define MAD_DIMM_ECC_OFF (0x0 << 24) +#define MAD_DIMM_ECC_IO_ON_LOGIC_OFF (0x1 << 24) +#define MAD_DIMM_ECC_IO_OFF_LOGIC_ON (0x2 << 24) +#define MAD_DIMM_ECC_ON (0x3 << 24) +#define MAD_DIMM_ENH_INTERLEAVE (0x1 << 22) +#define MAD_DIMM_RANK_INTERLEAVE (0x1 << 21) +#define MAD_DIMM_B_WIDTH_X16 (0x1 << 20) /* X8 chips if unset */ +#define MAD_DIMM_A_WIDTH_X16 (0x1 << 19) /* X8 chips if unset */ +#define MAD_DIMM_B_DUAL_RANK (0x1 << 18) +#define MAD_DIMM_A_DUAL_RANK (0x1 << 17) +#define MAD_DIMM_A_SELECT (0x1 << 16) +/* DIMM sizes are in multiples of 256mb. */ +#define MAD_DIMM_B_SIZE_SHIFT 8 +#define MAD_DIMM_B_SIZE_MASK (0xff << MAD_DIMM_B_SIZE_SHIFT) +#define MAD_DIMM_A_SIZE_SHIFT 0 +#define MAD_DIMM_A_SIZE_MASK (0xff << MAD_DIMM_A_SIZE_SHIFT) + + /* Clocking configuration register */ #define CLKCFG 0x10c00 #define CLKCFG_FSB_400 (5 << 0) /* hrawclk 100 */ @@ -1316,6 +1384,7 @@ #define _VSYNC_A 0x60014 #define _PIPEASRC 0x6001c #define _BCLRPAT_A 0x60020 +#define _VSYNCSHIFT_A 0x60028 /* Pipe B timing regs */ #define _HTOTAL_B 0x61000 @@ -1326,6 +1395,8 @@ #define _VSYNC_B 0x61014 #define _PIPEBSRC 0x6101c #define _BCLRPAT_B 0x61020 +#define _VSYNCSHIFT_B 0x61028 + #define HTOTAL(pipe) _PIPE(pipe, _HTOTAL_A, _HTOTAL_B) #define HBLANK(pipe) _PIPE(pipe, _HBLANK_A, _HBLANK_B) @@ -1334,6 +1405,7 @@ #define VBLANK(pipe) _PIPE(pipe, _VBLANK_A, _VBLANK_B) #define VSYNC(pipe) _PIPE(pipe, _VSYNC_A, _VSYNC_B) #define BCLRPAT(pipe) _PIPE(pipe, _BCLRPAT_A, _BCLRPAT_B) +#define VSYNCSHIFT(pipe) _PIPE(pipe, _VSYNCSHIFT_A, _VSYNCSHIFT_B) /* VGA port control */ #define ADPA 0x61100 @@ -2319,10 +2391,21 @@ #define PIPECONF_PALETTE 0 #define PIPECONF_GAMMA (1<<24) #define PIPECONF_FORCE_BORDER (1<<25) -#define PIPECONF_PROGRESSIVE (0 << 21) -#define PIPECONF_INTERLACE_W_FIELD_INDICATION (6 << 21) -#define PIPECONF_INTERLACE_FIELD_0_ONLY (7 << 21) #define PIPECONF_INTERLACE_MASK (7 << 21) +/* Note that pre-gen3 does not support interlaced display directly. Panel + * fitting must be disabled on pre-ilk for interlaced. */ +#define PIPECONF_PROGRESSIVE (0 << 21) +#define PIPECONF_INTERLACE_W_SYNC_SHIFT_PANEL (4 << 21) /* gen4 only */ +#define PIPECONF_INTERLACE_W_SYNC_SHIFT (5 << 21) /* gen4 only */ +#define PIPECONF_INTERLACE_W_FIELD_INDICATION (6 << 21) +#define PIPECONF_INTERLACE_FIELD_0_ONLY (7 << 21) /* gen3 only */ +/* Ironlake and later have a complete new set of values for interlaced. PFIT + * means panel fitter required, PF means progressive fetch, DBL means power + * saving pixel doubling. */ +#define PIPECONF_PFIT_PF_INTERLACED_ILK (1 << 21) +#define PIPECONF_INTERLACED_ILK (3 << 21) +#define PIPECONF_INTERLACED_DBL_ILK (4 << 21) /* ilk/snb only */ +#define PIPECONF_PFIT_PF_INTERLACED_DBL_ILK (5 << 21) /* ilk/snb only */ #define PIPECONF_CXSR_DOWNCLOCK (1<<16) #define PIPECONF_BPP_MASK (0x000000e0) #define PIPECONF_BPP_8 (0<<5) @@ -3219,6 +3302,7 @@ #define _TRANS_VSYNC_A 0xe0014 #define TRANS_VSYNC_END_SHIFT 16 #define TRANS_VSYNC_START_SHIFT 0 +#define _TRANS_VSYNCSHIFT_A 0xe0028 #define _TRANSA_DATA_M1 0xe0030 #define _TRANSA_DATA_N1 0xe0034 @@ -3249,6 +3333,7 @@ #define _TRANS_VTOTAL_B 0xe100c #define _TRANS_VBLANK_B 0xe1010 #define _TRANS_VSYNC_B 0xe1014 +#define _TRANS_VSYNCSHIFT_B 0xe1028 #define TRANS_HTOTAL(pipe) _PIPE(pipe, _TRANS_HTOTAL_A, _TRANS_HTOTAL_B) #define TRANS_HBLANK(pipe) _PIPE(pipe, _TRANS_HBLANK_A, _TRANS_HBLANK_B) @@ -3256,6 +3341,8 @@ #define TRANS_VTOTAL(pipe) _PIPE(pipe, _TRANS_VTOTAL_A, _TRANS_VTOTAL_B) #define TRANS_VBLANK(pipe) _PIPE(pipe, _TRANS_VBLANK_A, _TRANS_VBLANK_B) #define TRANS_VSYNC(pipe) _PIPE(pipe, _TRANS_VSYNC_A, _TRANS_VSYNC_B) +#define TRANS_VSYNCSHIFT(pipe) _PIPE(pipe, _TRANS_VSYNCSHIFT_A, \ + _TRANS_VSYNCSHIFT_B) #define _TRANSB_DATA_M1 0xe1030 #define _TRANSB_DATA_N1 0xe1034 @@ -3289,7 +3376,10 @@ #define TRANS_FSYNC_DELAY_HB4 (3<<27) #define TRANS_DP_AUDIO_ONLY (1<<26) #define TRANS_DP_VIDEO_AUDIO (0<<26) +#define TRANS_INTERLACE_MASK (7<<21) #define TRANS_PROGRESSIVE (0<<21) +#define TRANS_INTERLACED (3<<21) +#define TRANS_LEGACY_INTERLACED_ILK (2<<21) #define TRANS_8BPC (0<<5) #define TRANS_10BPC (1<<5) #define TRANS_6BPC (2<<5) @@ -3628,6 +3718,12 @@ #define ECOBUS 0xa180 #define FORCEWAKE_MT_ENABLE (1<<5) +#define GTFIFODBG 0x120000 +#define GT_FIFO_CPU_ERROR_MASK 7 +#define GT_FIFO_OVFERR (1<<2) +#define GT_FIFO_IAWRERR (1<<1) +#define GT_FIFO_IARDERR (1<<0) + #define GT_FIFO_FREE_ENTRIES 0x120008 #define GT_FIFO_NUM_RESERVED_ENTRIES 20 @@ -3757,4 +3853,16 @@ */ #define GEN7_SO_WRITE_OFFSET(n) (0x5280 + (n) * 4) +#define IBX_AUD_CONFIG_A 0xe2000 +#define CPT_AUD_CONFIG_A 0xe5000 +#define AUD_CONFIG_N_VALUE_INDEX (1 << 29) +#define AUD_CONFIG_N_PROG_ENABLE (1 << 28) +#define AUD_CONFIG_UPPER_N_SHIFT 20 +#define AUD_CONFIG_UPPER_N_VALUE (0xff << 20) +#define AUD_CONFIG_LOWER_N_SHIFT 4 +#define AUD_CONFIG_LOWER_N_VALUE (0xfff << 4) +#define AUD_CONFIG_PIXEL_CLOCK_HDMI_SHIFT 16 +#define AUD_CONFIG_PIXEL_CLOCK_HDMI (0xf << 16) +#define AUD_CONFIG_DISABLE_NCTS (1 << 3) + #endif /* _I915_REG_H_ */ diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c index cb912106d1a..bae3edf956a 100644 --- a/drivers/gpu/drm/i915/intel_acpi.c +++ b/drivers/gpu/drm/i915/intel_acpi.c @@ -208,7 +208,7 @@ static bool intel_dsm_pci_probe(struct pci_dev *pdev) ret = intel_dsm(dhandle, INTEL_DSM_FN_SUPPORTED_FUNCTIONS, 0); if (ret < 0) { - DRM_ERROR("failed to get supported _DSM functions\n"); + DRM_DEBUG_KMS("failed to get supported _DSM functions\n"); return false; } diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 63880e2e5cf..8168d8f8a63 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -572,7 +572,7 @@ parse_device_mapping(struct drm_i915_private *dev_priv, DRM_DEBUG_KMS("no child dev is parsed from VBT\n"); return; } - dev_priv->child_dev = kzalloc(sizeof(*p_child) * count, GFP_KERNEL); + dev_priv->child_dev = kcalloc(count, sizeof(*p_child), GFP_KERNEL); if (!dev_priv->child_dev) { DRM_DEBUG_KMS("No memory space for child device\n"); return; @@ -669,7 +669,7 @@ intel_parse_bios(struct drm_device *dev) } if (!vbt) { - DRM_ERROR("VBT signature missing\n"); + DRM_DEBUG_DRIVER("VBT signature missing\n"); pci_unmap_rom(pdev, bios); return -1; } diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index dd729d46a61..4d3d736a4f5 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -594,7 +594,10 @@ void intel_crt_init(struct drm_device *dev) 1 << INTEL_ANALOG_CLONE_BIT | 1 << INTEL_SDVO_LVDS_CLONE_BIT); crt->base.crtc_mask = (1 << 0) | (1 << 1); - connector->interlace_allowed = 1; + if (IS_GEN2(dev)) + connector->interlace_allowed = 0; + else + connector->interlace_allowed = 1; connector->doublescan_allowed = 0; drm_encoder_helper_add(&crt->base.base, &intel_crt_helper_funcs); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 397087cf689..d514719f65e 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -75,7 +75,7 @@ struct intel_limit { intel_range_t dot, vco, n, m, m1, m2, p, p1; intel_p2_t p2; bool (* find_pll)(const intel_limit_t *, struct drm_crtc *, - int, int, intel_clock_t *); + int, int, intel_clock_t *, intel_clock_t *); }; /* FDI */ @@ -83,17 +83,21 @@ struct intel_limit { static bool intel_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, - int target, int refclk, intel_clock_t *best_clock); + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock); static bool intel_g4x_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, - int target, int refclk, intel_clock_t *best_clock); + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock); static bool intel_find_pll_g4x_dp(const intel_limit_t *, struct drm_crtc *crtc, - int target, int refclk, intel_clock_t *best_clock); + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock); static bool intel_find_pll_ironlake_dp(const intel_limit_t *, struct drm_crtc *crtc, - int target, int refclk, intel_clock_t *best_clock); + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock); static inline u32 /* units of 100MHz */ intel_fdi_link_freq(struct drm_device *dev) @@ -515,7 +519,8 @@ static bool intel_PLL_is_valid(struct drm_device *dev, static bool intel_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, - int target, int refclk, intel_clock_t *best_clock) + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock) { struct drm_device *dev = crtc->dev; @@ -562,6 +567,9 @@ intel_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, if (!intel_PLL_is_valid(dev, limit, &clock)) continue; + if (match_clock && + clock.p != match_clock->p) + continue; this_err = abs(clock.dot - target); if (this_err < err) { @@ -578,7 +586,8 @@ intel_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, static bool intel_g4x_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, - int target, int refclk, intel_clock_t *best_clock) + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -625,6 +634,9 @@ intel_g4x_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, if (!intel_PLL_is_valid(dev, limit, &clock)) continue; + if (match_clock && + clock.p != match_clock->p) + continue; this_err = abs(clock.dot - target); if (this_err < err_most) { @@ -642,7 +654,8 @@ intel_g4x_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, static bool intel_find_pll_ironlake_dp(const intel_limit_t *limit, struct drm_crtc *crtc, - int target, int refclk, intel_clock_t *best_clock) + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock) { struct drm_device *dev = crtc->dev; intel_clock_t clock; @@ -668,7 +681,8 @@ intel_find_pll_ironlake_dp(const intel_limit_t *limit, struct drm_crtc *crtc, /* DisplayPort has only two frequencies, 162MHz and 270MHz */ static bool intel_find_pll_g4x_dp(const intel_limit_t *limit, struct drm_crtc *crtc, - int target, int refclk, intel_clock_t *best_clock) + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock) { intel_clock_t clock; if (target < 200000) { @@ -922,6 +936,10 @@ void assert_pipe(struct drm_i915_private *dev_priv, u32 val; bool cur_state; + /* if we need the pipe A quirk it must be always on */ + if (pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) + state = true; + reg = PIPECONF(pipe); val = I915_READ(reg); cur_state = !!(val & PIPECONF_ENABLE); @@ -930,19 +948,24 @@ void assert_pipe(struct drm_i915_private *dev_priv, pipe_name(pipe), state_string(state), state_string(cur_state)); } -static void assert_plane_enabled(struct drm_i915_private *dev_priv, - enum plane plane) +static void assert_plane(struct drm_i915_private *dev_priv, + enum plane plane, bool state) { int reg; u32 val; + bool cur_state; reg = DSPCNTR(plane); val = I915_READ(reg); - WARN(!(val & DISPLAY_PLANE_ENABLE), - "plane %c assertion failure, should be active but is disabled\n", - plane_name(plane)); + cur_state = !!(val & DISPLAY_PLANE_ENABLE); + WARN(cur_state != state, + "plane %c assertion failure (expected %s, current %s)\n", + plane_name(plane), state_string(state), state_string(cur_state)); } +#define assert_plane_enabled(d, p) assert_plane(d, p, true) +#define assert_plane_disabled(d, p) assert_plane(d, p, false) + static void assert_planes_disabled(struct drm_i915_private *dev_priv, enum pipe pipe) { @@ -951,8 +974,14 @@ static void assert_planes_disabled(struct drm_i915_private *dev_priv, int cur_pipe; /* Planes are fixed to pipes on ILK+ */ - if (HAS_PCH_SPLIT(dev_priv->dev)) + if (HAS_PCH_SPLIT(dev_priv->dev)) { + reg = DSPCNTR(pipe); + val = I915_READ(reg); + WARN((val & DISPLAY_PLANE_ENABLE), + "plane %c assertion failure, should be disabled but not\n", + plane_name(pipe)); return; + } /* Need to check both planes against the pipe */ for (i = 0; i < 2; i++) { @@ -1071,7 +1100,7 @@ static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv, { u32 val = I915_READ(reg); WARN(hdmi_pipe_enabled(dev_priv, val, pipe), - "PCH DP (0x%08x) enabled on transcoder %c, should be disabled\n", + "PCH HDMI (0x%08x) enabled on transcoder %c, should be disabled\n", reg, pipe_name(pipe)); } @@ -1237,7 +1266,8 @@ static void intel_enable_transcoder(struct drm_i915_private *dev_priv, enum pipe pipe) { int reg; - u32 val; + u32 val, pipeconf_val; + struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; /* PCH only available on ILK+ */ BUG_ON(dev_priv->info->gen < 5); @@ -1251,6 +1281,7 @@ static void intel_enable_transcoder(struct drm_i915_private *dev_priv, reg = TRANSCONF(pipe); val = I915_READ(reg); + pipeconf_val = I915_READ(PIPECONF(pipe)); if (HAS_PCH_IBX(dev_priv->dev)) { /* @@ -1258,8 +1289,19 @@ static void intel_enable_transcoder(struct drm_i915_private *dev_priv, * that in pipeconf reg. */ val &= ~PIPE_BPC_MASK; - val |= I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK; + val |= pipeconf_val & PIPE_BPC_MASK; } + + val &= ~TRANS_INTERLACE_MASK; + if ((pipeconf_val & PIPECONF_INTERLACE_MASK) == PIPECONF_INTERLACED_ILK) + if (HAS_PCH_IBX(dev_priv->dev) && + intel_pipe_has_type(crtc, INTEL_OUTPUT_SDVO)) + val |= TRANS_LEGACY_INTERLACED_ILK; + else + val |= TRANS_INTERLACED; + else + val |= TRANS_PROGRESSIVE; + I915_WRITE(reg, val | TRANS_ENABLE); if (wait_for(I915_READ(reg) & TRANS_STATE_ENABLE, 100)) DRM_ERROR("failed to enable transcoder %d\n", pipe); @@ -2012,6 +2054,8 @@ intel_pin_and_fence_fb_obj(struct drm_device *dev, ret = i915_gem_object_get_fence(obj, pipelined); if (ret) goto err_unpin; + + i915_gem_object_pin_fence(obj); } dev_priv->mm.interruptible = true; @@ -2024,6 +2068,12 @@ err_interruptible: return ret; } +void intel_unpin_fb_obj(struct drm_i915_gem_object *obj) +{ + i915_gem_object_unpin_fence(obj); + i915_gem_object_unpin(obj); +} + static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb, int x, int y) { @@ -2255,7 +2305,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, ret = intel_pipe_set_base_atomic(crtc, crtc->fb, x, y, LEAVE_ATOMIC_MODE_SET); if (ret) { - i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj); + intel_unpin_fb_obj(to_intel_framebuffer(crtc->fb)->obj); mutex_unlock(&dev->struct_mutex); DRM_ERROR("failed to update base address\n"); return ret; @@ -2263,7 +2313,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, if (old_fb) { intel_wait_for_vblank(dev, intel_crtc->pipe); - i915_gem_object_unpin(to_intel_framebuffer(old_fb)->obj); + intel_unpin_fb_obj(to_intel_framebuffer(old_fb)->obj); } mutex_unlock(&dev->struct_mutex); @@ -2936,6 +2986,7 @@ static void ironlake_pch_enable(struct drm_crtc *crtc) I915_WRITE(TRANS_VTOTAL(pipe), I915_READ(VTOTAL(pipe))); I915_WRITE(TRANS_VBLANK(pipe), I915_READ(VBLANK(pipe))); I915_WRITE(TRANS_VSYNC(pipe), I915_READ(VSYNC(pipe))); + I915_WRITE(TRANS_VSYNCSHIFT(pipe), I915_READ(VSYNCSHIFT(pipe))); intel_fdi_normal_train(crtc); @@ -3321,10 +3372,12 @@ static void intel_crtc_disable(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF); + assert_plane_disabled(dev->dev_private, to_intel_crtc(crtc)->plane); + assert_pipe_disabled(dev->dev_private, to_intel_crtc(crtc)->pipe); if (crtc->fb) { mutex_lock(&dev->struct_mutex); - i915_gem_object_unpin(to_intel_framebuffer(crtc->fb)->obj); + intel_unpin_fb_obj(to_intel_framebuffer(crtc->fb)->obj); mutex_unlock(&dev->struct_mutex); } } @@ -3398,11 +3451,8 @@ static bool intel_crtc_mode_fixup(struct drm_crtc *crtc, return false; } - /* XXX some encoders set the crtcinfo, others don't. - * Obviously we need some form of conflict resolution here... - */ - if (adjusted_mode->crtc_htotal == 0) - drm_mode_set_crtcinfo(adjusted_mode, 0); + /* All interlaced capable intel hw wants timings in frames. */ + drm_mode_set_crtcinfo(adjusted_mode, 0); return true; } @@ -4521,6 +4571,7 @@ void sandybridge_update_wm(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; int latency = SNB_READ_WM0_LATENCY() * 100; /* In unit 0.1us */ + u32 val; int fbc_wm, plane_wm, cursor_wm; unsigned int enabled; @@ -4529,8 +4580,10 @@ void sandybridge_update_wm(struct drm_device *dev) &sandybridge_display_wm_info, latency, &sandybridge_cursor_wm_info, latency, &plane_wm, &cursor_wm)) { - I915_WRITE(WM0_PIPEA_ILK, - (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm); + val = I915_READ(WM0_PIPEA_ILK); + val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK); + I915_WRITE(WM0_PIPEA_ILK, val | + ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm)); DRM_DEBUG_KMS("FIFO watermarks For pipe A -" " plane %d, " "cursor: %d\n", plane_wm, cursor_wm); @@ -4541,8 +4594,10 @@ void sandybridge_update_wm(struct drm_device *dev) &sandybridge_display_wm_info, latency, &sandybridge_cursor_wm_info, latency, &plane_wm, &cursor_wm)) { - I915_WRITE(WM0_PIPEB_ILK, - (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm); + val = I915_READ(WM0_PIPEB_ILK); + val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK); + I915_WRITE(WM0_PIPEB_ILK, val | + ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm)); DRM_DEBUG_KMS("FIFO watermarks For pipe B -" " plane %d, cursor: %d\n", plane_wm, cursor_wm); @@ -4555,8 +4610,10 @@ void sandybridge_update_wm(struct drm_device *dev) &sandybridge_display_wm_info, latency, &sandybridge_cursor_wm_info, latency, &plane_wm, &cursor_wm)) { - I915_WRITE(WM0_PIPEC_IVB, - (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm); + val = I915_READ(WM0_PIPEC_IVB); + val &= ~(WM0_PIPE_PLANE_MASK | WM0_PIPE_CURSOR_MASK); + I915_WRITE(WM0_PIPEC_IVB, val | + ((plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm)); DRM_DEBUG_KMS("FIFO watermarks For pipe C -" " plane %d, cursor: %d\n", plane_wm, cursor_wm); @@ -4709,6 +4766,7 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe, { struct drm_i915_private *dev_priv = dev->dev_private; int latency = SNB_READ_WM0_LATENCY() * 100; /* In unit 0.1us */ + u32 val; int sprite_wm, reg; int ret; @@ -4735,7 +4793,9 @@ static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe, return; } - I915_WRITE(reg, I915_READ(reg) | (sprite_wm << WM0_PIPE_SPRITE_SHIFT)); + val = I915_READ(reg); + val &= ~WM0_PIPE_SPRITE_MASK; + I915_WRITE(reg, val | (sprite_wm << WM0_PIPE_SPRITE_SHIFT)); DRM_DEBUG_KMS("sprite watermarks For pipe %d - %d\n", pipe, sprite_wm); @@ -4977,6 +5037,82 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc, return display_bpc != bpc; } +static int i9xx_get_refclk(struct drm_crtc *crtc, int num_connectors) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int refclk; + + if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) && + intel_panel_use_ssc(dev_priv) && num_connectors < 2) { + refclk = dev_priv->lvds_ssc_freq * 1000; + DRM_DEBUG_KMS("using SSC reference clock of %d MHz\n", + refclk / 1000); + } else if (!IS_GEN2(dev)) { + refclk = 96000; + } else { + refclk = 48000; + } + + return refclk; +} + +static void i9xx_adjust_sdvo_tv_clock(struct drm_display_mode *adjusted_mode, + intel_clock_t *clock) +{ + /* SDVO TV has fixed PLL values depend on its clock range, + this mirrors vbios setting. */ + if (adjusted_mode->clock >= 100000 + && adjusted_mode->clock < 140500) { + clock->p1 = 2; + clock->p2 = 10; + clock->n = 3; + clock->m1 = 16; + clock->m2 = 8; + } else if (adjusted_mode->clock >= 140500 + && adjusted_mode->clock <= 200000) { + clock->p1 = 1; + clock->p2 = 10; + clock->n = 6; + clock->m1 = 12; + clock->m2 = 8; + } +} + +static void i9xx_update_pll_dividers(struct drm_crtc *crtc, + intel_clock_t *clock, + intel_clock_t *reduced_clock) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + int pipe = intel_crtc->pipe; + u32 fp, fp2 = 0; + + if (IS_PINEVIEW(dev)) { + fp = (1 << clock->n) << 16 | clock->m1 << 8 | clock->m2; + if (reduced_clock) + fp2 = (1 << reduced_clock->n) << 16 | + reduced_clock->m1 << 8 | reduced_clock->m2; + } else { + fp = clock->n << 16 | clock->m1 << 8 | clock->m2; + if (reduced_clock) + fp2 = reduced_clock->n << 16 | reduced_clock->m1 << 8 | + reduced_clock->m2; + } + + I915_WRITE(FP0(pipe), fp); + + intel_crtc->lowfreq_avail = false; + if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) && + reduced_clock && i915_powersave) { + I915_WRITE(FP1(pipe), fp2); + intel_crtc->lowfreq_avail = true; + } else { + I915_WRITE(FP1(pipe), fp); + } +} + static int i9xx_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode, @@ -4990,7 +5126,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, int plane = intel_crtc->plane; int refclk, num_connectors = 0; intel_clock_t clock, reduced_clock; - u32 dpll, fp = 0, fp2 = 0, dspcntr, pipeconf; + u32 dpll, dspcntr, pipeconf, vsyncshift; bool ok, has_reduced_clock = false, is_sdvo = false, is_dvo = false; bool is_crt = false, is_lvds = false, is_tv = false, is_dp = false; struct drm_mode_config *mode_config = &dev->mode_config; @@ -5031,15 +5167,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, num_connectors++; } - if (is_lvds && intel_panel_use_ssc(dev_priv) && num_connectors < 2) { - refclk = dev_priv->lvds_ssc_freq * 1000; - DRM_DEBUG_KMS("using SSC reference clock of %d MHz\n", - refclk / 1000); - } else if (!IS_GEN2(dev)) { - refclk = 96000; - } else { - refclk = 48000; - } + refclk = i9xx_get_refclk(crtc, num_connectors); /* * Returns a set of divisors for the desired target clock with the given @@ -5047,7 +5175,8 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, * reflck * (5 * (m1 + 2) + (m2 + 2)) / (n + 2) / p1 / p2. */ limit = intel_limit(crtc, refclk); - ok = limit->find_pll(limit, crtc, adjusted_mode->clock, refclk, &clock); + ok = limit->find_pll(limit, crtc, adjusted_mode->clock, refclk, NULL, + &clock); if (!ok) { DRM_ERROR("Couldn't find PLL settings for mode!\n"); return -EINVAL; @@ -5057,53 +5186,24 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, intel_crtc_update_cursor(crtc, true); if (is_lvds && dev_priv->lvds_downclock_avail) { + /* + * Ensure we match the reduced clock's P to the target clock. + * If the clocks don't match, we can't switch the display clock + * by using the FP0/FP1. In such case we will disable the LVDS + * downclock feature. + */ has_reduced_clock = limit->find_pll(limit, crtc, dev_priv->lvds_downclock, refclk, + &clock, &reduced_clock); - if (has_reduced_clock && (clock.p != reduced_clock.p)) { - /* - * If the different P is found, it means that we can't - * switch the display clock by using the FP0/FP1. - * In such case we will disable the LVDS downclock - * feature. - */ - DRM_DEBUG_KMS("Different P is found for " - "LVDS clock/downclock\n"); - has_reduced_clock = 0; - } - } - /* SDVO TV has fixed PLL values depend on its clock range, - this mirrors vbios setting. */ - if (is_sdvo && is_tv) { - if (adjusted_mode->clock >= 100000 - && adjusted_mode->clock < 140500) { - clock.p1 = 2; - clock.p2 = 10; - clock.n = 3; - clock.m1 = 16; - clock.m2 = 8; - } else if (adjusted_mode->clock >= 140500 - && adjusted_mode->clock <= 200000) { - clock.p1 = 1; - clock.p2 = 10; - clock.n = 6; - clock.m1 = 12; - clock.m2 = 8; - } } - if (IS_PINEVIEW(dev)) { - fp = (1 << clock.n) << 16 | clock.m1 << 8 | clock.m2; - if (has_reduced_clock) - fp2 = (1 << reduced_clock.n) << 16 | - reduced_clock.m1 << 8 | reduced_clock.m2; - } else { - fp = clock.n << 16 | clock.m1 << 8 | clock.m2; - if (has_reduced_clock) - fp2 = reduced_clock.n << 16 | reduced_clock.m1 << 8 | - reduced_clock.m2; - } + if (is_sdvo && is_tv) + i9xx_adjust_sdvo_tv_clock(adjusted_mode, &clock); + + i9xx_update_pll_dividers(crtc, &clock, has_reduced_clock ? + &reduced_clock : NULL); dpll = DPLL_VGA_MODE_DIS; @@ -5177,8 +5277,6 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, /* Set up the display plane register */ dspcntr = DISPPLANE_GAMMA_ENABLE; - /* Ironlake's plane is forced to pipe, bit 24 is to - enable color space conversion */ if (pipe == 0) dspcntr &= ~DISPPLANE_SEL_PIPE_MASK; else @@ -5213,7 +5311,6 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, DRM_DEBUG_KMS("Mode for pipe %c:\n", pipe == 0 ? 'A' : 'B'); drm_mode_debug_printmodeline(mode); - I915_WRITE(FP0(pipe), fp); I915_WRITE(DPLL(pipe), dpll & ~DPLL_VCO_ENABLE); POSTING_READ(DPLL(pipe)); @@ -5300,34 +5397,32 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, I915_WRITE(DPLL(pipe), dpll); } - intel_crtc->lowfreq_avail = false; - if (is_lvds && has_reduced_clock && i915_powersave) { - I915_WRITE(FP1(pipe), fp2); - intel_crtc->lowfreq_avail = true; - if (HAS_PIPE_CXSR(dev)) { + if (HAS_PIPE_CXSR(dev)) { + if (intel_crtc->lowfreq_avail) { DRM_DEBUG_KMS("enabling CxSR downclocking\n"); pipeconf |= PIPECONF_CXSR_DOWNCLOCK; - } - } else { - I915_WRITE(FP1(pipe), fp); - if (HAS_PIPE_CXSR(dev)) { + } else { DRM_DEBUG_KMS("disabling CxSR downclocking\n"); pipeconf &= ~PIPECONF_CXSR_DOWNCLOCK; } } pipeconf &= ~PIPECONF_INTERLACE_MASK; - if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) { + if (!IS_GEN2(dev) && + adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) { pipeconf |= PIPECONF_INTERLACE_W_FIELD_INDICATION; /* the chip adds 2 halflines automatically */ - adjusted_mode->crtc_vdisplay -= 1; adjusted_mode->crtc_vtotal -= 1; - adjusted_mode->crtc_vblank_start -= 1; adjusted_mode->crtc_vblank_end -= 1; - adjusted_mode->crtc_vsync_end -= 1; - adjusted_mode->crtc_vsync_start -= 1; - } else + vsyncshift = adjusted_mode->crtc_hsync_start + - adjusted_mode->crtc_htotal/2; + } else { pipeconf |= PIPECONF_PROGRESSIVE; + vsyncshift = 0; + } + + if (!IS_GEN3(dev)) + I915_WRITE(VSYNCSHIFT(pipe), vsyncshift); I915_WRITE(HTOTAL(pipe), (adjusted_mode->crtc_hdisplay - 1) | @@ -5593,7 +5688,8 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, * reflck * (5 * (m1 + 2) + (m2 + 2)) / (n + 2) / p1 / p2. */ limit = intel_limit(crtc, refclk); - ok = limit->find_pll(limit, crtc, adjusted_mode->clock, refclk, &clock); + ok = limit->find_pll(limit, crtc, adjusted_mode->clock, refclk, NULL, + &clock); if (!ok) { DRM_ERROR("Couldn't find PLL settings for mode!\n"); return -EINVAL; @@ -5603,21 +5699,17 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, intel_crtc_update_cursor(crtc, true); if (is_lvds && dev_priv->lvds_downclock_avail) { + /* + * Ensure we match the reduced clock's P to the target clock. + * If the clocks don't match, we can't switch the display clock + * by using the FP0/FP1. In such case we will disable the LVDS + * downclock feature. + */ has_reduced_clock = limit->find_pll(limit, crtc, dev_priv->lvds_downclock, refclk, + &clock, &reduced_clock); - if (has_reduced_clock && (clock.p != reduced_clock.p)) { - /* - * If the different P is found, it means that we can't - * switch the display clock by using the FP0/FP1. - * In such case we will disable the LVDS downclock - * feature. - */ - DRM_DEBUG_KMS("Different P is found for " - "LVDS clock/downclock\n"); - has_reduced_clock = 0; - } } /* SDVO TV has fixed PLL values depend on its clock range, this mirrors vbios setting. */ @@ -5914,16 +6006,17 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, pipeconf &= ~PIPECONF_INTERLACE_MASK; if (adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) { - pipeconf |= PIPECONF_INTERLACE_W_FIELD_INDICATION; + pipeconf |= PIPECONF_INTERLACED_ILK; /* the chip adds 2 halflines automatically */ - adjusted_mode->crtc_vdisplay -= 1; adjusted_mode->crtc_vtotal -= 1; - adjusted_mode->crtc_vblank_start -= 1; adjusted_mode->crtc_vblank_end -= 1; - adjusted_mode->crtc_vsync_end -= 1; - adjusted_mode->crtc_vsync_start -= 1; - } else + I915_WRITE(VSYNCSHIFT(pipe), + adjusted_mode->crtc_hsync_start + - adjusted_mode->crtc_htotal/2); + } else { pipeconf |= PIPECONF_PROGRESSIVE; + I915_WRITE(VSYNCSHIFT(pipe), 0); + } I915_WRITE(HTOTAL(pipe), (adjusted_mode->crtc_hdisplay - 1) | @@ -5966,12 +6059,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, intel_wait_for_vblank(dev, pipe); - if (IS_GEN5(dev)) { - /* enable address swizzle for tiling buffer */ - temp = I915_READ(DISP_ARB_CTL); - I915_WRITE(DISP_ARB_CTL, temp | DISP_TILE_SURFACE_SWIZZLING); - } - I915_WRITE(DSPCNTR(plane), dspcntr); POSTING_READ(DSPCNTR(plane)); @@ -6086,15 +6173,18 @@ static void ironlake_write_eld(struct drm_connector *connector, uint32_t i; int len; int hdmiw_hdmiedid; + int aud_config; int aud_cntl_st; int aud_cntrl_st2; if (HAS_PCH_IBX(connector->dev)) { hdmiw_hdmiedid = IBX_HDMIW_HDMIEDID_A; + aud_config = IBX_AUD_CONFIG_A; aud_cntl_st = IBX_AUD_CNTL_ST_A; aud_cntrl_st2 = IBX_AUD_CNTL_ST2; } else { hdmiw_hdmiedid = CPT_HDMIW_HDMIEDID_A; + aud_config = CPT_AUD_CONFIG_A; aud_cntl_st = CPT_AUD_CNTL_ST_A; aud_cntrl_st2 = CPT_AUD_CNTRL_ST2; } @@ -6102,6 +6192,7 @@ static void ironlake_write_eld(struct drm_connector *connector, i = to_intel_crtc(crtc)->pipe; hdmiw_hdmiedid += i * 0x100; aud_cntl_st += i * 0x100; + aud_config += i * 0x100; DRM_DEBUG_DRIVER("ELD on pipe %c\n", pipe_name(i)); @@ -6121,7 +6212,9 @@ static void ironlake_write_eld(struct drm_connector *connector, if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) { DRM_DEBUG_DRIVER("ELD: DisplayPort detected\n"); eld[5] |= (1 << 2); /* Conn_Type, 0x1 = DisplayPort */ - } + I915_WRITE(aud_config, AUD_CONFIG_N_VALUE_INDEX); /* 0x1 = DP */ + } else + I915_WRITE(aud_config, 0); if (intel_eld_uptodate(connector, aud_cntrl_st2, eldv, @@ -6927,9 +7020,7 @@ static void intel_increase_pllclock(struct drm_crtc *crtc) if (!HAS_PIPE_CXSR(dev) && (dpll & DISPLAY_RATE_SELECT_FPA1)) { DRM_DEBUG_DRIVER("upclocking LVDS\n"); - /* Unlock panel regs */ - I915_WRITE(PP_CONTROL, - I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); + assert_panel_unlocked(dev_priv, pipe); dpll &= ~DISPLAY_RATE_SELECT_FPA1; I915_WRITE(dpll_reg, dpll); @@ -6938,9 +7029,6 @@ static void intel_increase_pllclock(struct drm_crtc *crtc) dpll = I915_READ(dpll_reg); if (dpll & DISPLAY_RATE_SELECT_FPA1) DRM_DEBUG_DRIVER("failed to upclock LVDS!\n"); - - /* ...and lock them again */ - I915_WRITE(PP_CONTROL, I915_READ(PP_CONTROL) & 0x3); } /* Schedule downclock */ @@ -6970,9 +7058,7 @@ static void intel_decrease_pllclock(struct drm_crtc *crtc) if (!HAS_PIPE_CXSR(dev) && intel_crtc->lowfreq_avail) { DRM_DEBUG_DRIVER("downclocking LVDS\n"); - /* Unlock panel regs */ - I915_WRITE(PP_CONTROL, I915_READ(PP_CONTROL) | - PANEL_UNLOCK_REGS); + assert_panel_unlocked(dev_priv, pipe); dpll |= DISPLAY_RATE_SELECT_FPA1; I915_WRITE(dpll_reg, dpll); @@ -6980,9 +7066,6 @@ static void intel_decrease_pllclock(struct drm_crtc *crtc) dpll = I915_READ(dpll_reg); if (!(dpll & DISPLAY_RATE_SELECT_FPA1)) DRM_DEBUG_DRIVER("failed to downclock LVDS!\n"); - - /* ...and lock them again */ - I915_WRITE(PP_CONTROL, I915_READ(PP_CONTROL) & 0x3); } } @@ -7097,7 +7180,7 @@ static void intel_unpin_work_fn(struct work_struct *__work) container_of(__work, struct intel_unpin_work, work); mutex_lock(&work->dev->struct_mutex); - i915_gem_object_unpin(work->old_fb_obj); + intel_unpin_fb_obj(work->old_fb_obj); drm_gem_object_unreference(&work->pending_flip_obj->base); drm_gem_object_unreference(&work->old_fb_obj->base); @@ -7247,7 +7330,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev, MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); OUT_RING(fb->pitches[0]); OUT_RING(obj->gtt_offset + offset); - OUT_RING(MI_NOOP); + OUT_RING(0); /* aux display base address, unused */ ADVANCE_LP_RING(); out: return ret; @@ -7681,10 +7764,9 @@ static void intel_setup_outputs(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_encoder *encoder; bool dpd_is_edp = false; - bool has_lvds = false; + bool has_lvds; - if (IS_MOBILE(dev) && !IS_I830(dev)) - has_lvds = intel_lvds_init(dev); + has_lvds = intel_lvds_init(dev); if (!has_lvds && !HAS_PCH_SPLIT(dev)) { /* disable the panel fitter on everything but LVDS */ I915_WRITE(PFIT_CONTROL, 0); @@ -7840,7 +7922,8 @@ int intel_framebuffer_init(struct drm_device *dev, case DRM_FORMAT_VYUY: break; default: - DRM_ERROR("unsupported pixel format\n"); + DRM_DEBUG_KMS("unsupported pixel format %u\n", + mode_cmd->pixel_format); return -EINVAL; } @@ -8162,6 +8245,7 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv) u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP); u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS); u32 pcu_mbox, rc6_mask = 0; + u32 gtfifodbg; int cur_freq, min_freq, max_freq; int i; @@ -8173,6 +8257,13 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv) */ I915_WRITE(GEN6_RC_STATE, 0); mutex_lock(&dev_priv->dev->struct_mutex); + + /* Clear the DBG now so we don't confuse earlier errors */ + if ((gtfifodbg = I915_READ(GTFIFODBG))) { + DRM_ERROR("GT fifo had a previous error %x\n", gtfifodbg); + I915_WRITE(GTFIFODBG, gtfifodbg); + } + gen6_gt_force_wake_get(dev_priv); /* disable the counters and set deterministic thresholds */ @@ -8959,8 +9050,6 @@ struct intel_quirk { }; struct intel_quirk intel_quirks[] = { - /* HP Compaq 2730p needs pipe A force quirk (LP: #291555) */ - { 0x2a42, 0x103c, 0x30eb, quirk_pipea_force }, /* HP Mini needs pipe A force quirk (LP: #322104) */ { 0x27ae, 0x103c, 0x361a, quirk_pipea_force }, @@ -9037,6 +9126,9 @@ void intel_modeset_init(struct drm_device *dev) dev->mode_config.min_width = 0; dev->mode_config.min_height = 0; + dev->mode_config.preferred_depth = 24; + dev->mode_config.prefer_shadow = 1; + dev->mode_config.funcs = (void *)&intel_mode_funcs; intel_init_quirks(dev); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 94f860cce3f..110552ff302 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -49,7 +49,7 @@ struct intel_dp { uint32_t DP; uint8_t link_configuration[DP_LINK_CONFIGURATION_SIZE]; bool has_audio; - int force_audio; + enum hdmi_force_audio force_audio; uint32_t color_range; int dpms_mode; uint8_t link_bw; @@ -352,7 +352,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp, int recv_bytes; uint32_t status; uint32_t aux_clock_divider; - int try, precharge; + int try, precharge = 5; intel_dp_check_edp(intel_dp); /* The clock divider is based off the hrawclk, @@ -368,15 +368,10 @@ intel_dp_aux_ch(struct intel_dp *intel_dp, else aux_clock_divider = 225; /* eDP input clock at 450Mhz */ } else if (HAS_PCH_SPLIT(dev)) - aux_clock_divider = 62; /* IRL input clock fixed at 125Mhz */ + aux_clock_divider = 63; /* IRL input clock fixed at 125Mhz */ else aux_clock_divider = intel_hrawclk(dev) / 2; - if (IS_GEN6(dev)) - precharge = 3; - else - precharge = 5; - /* Try to wait for any previous AUX channel activity */ for (try = 0; try < 3; try++) { status = I915_READ(ch_ctl); @@ -421,6 +416,10 @@ intel_dp_aux_ch(struct intel_dp *intel_dp, DP_AUX_CH_CTL_DONE | DP_AUX_CH_CTL_TIME_OUT_ERROR | DP_AUX_CH_CTL_RECEIVE_ERROR); + + if (status & (DP_AUX_CH_CTL_TIME_OUT_ERROR | + DP_AUX_CH_CTL_RECEIVE_ERROR)) + continue; if (status & DP_AUX_CH_CTL_DONE) break; } @@ -2117,8 +2116,8 @@ intel_dp_detect(struct drm_connector *connector, bool force) if (status != connector_status_connected) return status; - if (intel_dp->force_audio) { - intel_dp->has_audio = intel_dp->force_audio > 0; + if (intel_dp->force_audio != HDMI_AUDIO_AUTO) { + intel_dp->has_audio = (intel_dp->force_audio == HDMI_AUDIO_ON); } else { edid = intel_dp_get_edid(connector, &intel_dp->adapter); if (edid) { @@ -2218,10 +2217,10 @@ intel_dp_set_property(struct drm_connector *connector, intel_dp->force_audio = i; - if (i == 0) + if (i == HDMI_AUDIO_AUTO) has_audio = intel_dp_detect_audio(connector); else - has_audio = i > 0; + has_audio = (i == HDMI_AUDIO_ON); if (has_audio == intel_dp->has_audio) return 0; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 1348705faf6..9cec6c3937f 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -374,6 +374,7 @@ extern void intel_init_emon(struct drm_device *dev); extern int intel_pin_and_fence_fb_obj(struct drm_device *dev, struct drm_i915_gem_object *obj, struct intel_ring_buffer *pipelined); +extern void intel_unpin_fb_obj(struct drm_i915_gem_object *obj); extern int intel_framebuffer_init(struct drm_device *dev, struct intel_framebuffer *ifb, diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c index 6eda1b51c63..020a7d7f744 100644 --- a/drivers/gpu/drm/i915/intel_dvo.c +++ b/drivers/gpu/drm/i915/intel_dvo.c @@ -157,7 +157,6 @@ static bool intel_dvo_mode_fixup(struct drm_encoder *encoder, C(vsync_end); C(vtotal); C(clock); - drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V); #undef C } diff --git a/drivers/gpu/drm/i915/intel_fb.c b/drivers/gpu/drm/i915/intel_fb.c index 571375a3eef..2d876697838 100644 --- a/drivers/gpu/drm/i915/intel_fb.c +++ b/drivers/gpu/drm/i915/intel_fb.c @@ -152,11 +152,7 @@ static int intelfb_create(struct intel_fbdev *ifbdev, drm_fb_helper_fill_fix(info, fb->pitches[0], fb->depth); drm_fb_helper_fill_var(info, &ifbdev->helper, sizes->fb_width, sizes->fb_height); - info->pixmap.size = 64*1024; - info->pixmap.buf_align = 8; - info->pixmap.access_align = 32; - info->pixmap.flags = FB_PIXMAP_SYSTEM; - info->pixmap.scan_align = 1; + /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */ DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x, bo %p\n", fb->width, fb->height, diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 64541f7ef90..cae3e5f17a4 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -44,7 +44,7 @@ struct intel_hdmi { uint32_t color_range; bool has_hdmi_sink; bool has_audio; - int force_audio; + enum hdmi_force_audio force_audio; void (*write_infoframe)(struct drm_encoder *encoder, struct dip_infoframe *frame); }; @@ -339,7 +339,9 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) if (edid) { if (edid->input & DRM_EDID_INPUT_DIGITAL) { status = connector_status_connected; - intel_hdmi->has_hdmi_sink = drm_detect_hdmi_monitor(edid); + if (intel_hdmi->force_audio != HDMI_AUDIO_OFF_DVI) + intel_hdmi->has_hdmi_sink = + drm_detect_hdmi_monitor(edid); intel_hdmi->has_audio = drm_detect_monitor_audio(edid); } connector->display_info.raw_edid = NULL; @@ -347,8 +349,9 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) } if (status == connector_status_connected) { - if (intel_hdmi->force_audio) - intel_hdmi->has_audio = intel_hdmi->force_audio > 0; + if (intel_hdmi->force_audio != HDMI_AUDIO_AUTO) + intel_hdmi->has_audio = + (intel_hdmi->force_audio == HDMI_AUDIO_ON); } return status; @@ -402,7 +405,7 @@ intel_hdmi_set_property(struct drm_connector *connector, return ret; if (property == dev_priv->force_audio_property) { - int i = val; + enum hdmi_force_audio i = val; bool has_audio; if (i == intel_hdmi->force_audio) @@ -410,13 +413,13 @@ intel_hdmi_set_property(struct drm_connector *connector, intel_hdmi->force_audio = i; - if (i == 0) + if (i == HDMI_AUDIO_AUTO) has_audio = intel_hdmi_detect_audio(connector); else - has_audio = i > 0; + has_audio = (i == HDMI_AUDIO_ON); - if (has_audio == intel_hdmi->has_audio) - return 0; + if (i == HDMI_AUDIO_OFF_DVI) + intel_hdmi->has_hdmi_sink = 0; intel_hdmi->has_audio = has_audio; goto done; @@ -514,7 +517,7 @@ void intel_hdmi_init(struct drm_device *dev, int sdvox_reg) intel_encoder->type = INTEL_OUTPUT_HDMI; connector->polled = DRM_CONNECTOR_POLL_HPD; - connector->interlace_allowed = 0; + connector->interlace_allowed = 1; connector->doublescan_allowed = 0; intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index d30ccccb9d7..601c86e664a 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -37,7 +37,7 @@ /* Intel GPIO access functions */ -#define I2C_RISEFALL_TIME 20 +#define I2C_RISEFALL_TIME 10 static inline struct intel_gmbus * to_intel_gmbus(struct i2c_adapter *i2c) @@ -45,13 +45,6 @@ to_intel_gmbus(struct i2c_adapter *i2c) return container_of(i2c, struct intel_gmbus, adapter); } -struct intel_gpio { - struct i2c_adapter adapter; - struct i2c_algo_bit_data algo; - struct drm_i915_private *dev_priv; - u32 reg; -}; - void intel_i2c_reset(struct drm_device *dev) { @@ -78,15 +71,15 @@ static void intel_i2c_quirk_set(struct drm_i915_private *dev_priv, bool enable) I915_WRITE(DSPCLK_GATE_D, val); } -static u32 get_reserved(struct intel_gpio *gpio) +static u32 get_reserved(struct intel_gmbus *bus) { - struct drm_i915_private *dev_priv = gpio->dev_priv; + struct drm_i915_private *dev_priv = bus->dev_priv; struct drm_device *dev = dev_priv->dev; u32 reserved = 0; /* On most chips, these bits must be preserved in software. */ if (!IS_I830(dev) && !IS_845G(dev)) - reserved = I915_READ_NOTRACE(gpio->reg) & + reserved = I915_READ_NOTRACE(bus->gpio_reg) & (GPIO_DATA_PULLUP_DISABLE | GPIO_CLOCK_PULLUP_DISABLE); @@ -95,29 +88,29 @@ static u32 get_reserved(struct intel_gpio *gpio) static int get_clock(void *data) { - struct intel_gpio *gpio = data; - struct drm_i915_private *dev_priv = gpio->dev_priv; - u32 reserved = get_reserved(gpio); - I915_WRITE_NOTRACE(gpio->reg, reserved | GPIO_CLOCK_DIR_MASK); - I915_WRITE_NOTRACE(gpio->reg, reserved); - return (I915_READ_NOTRACE(gpio->reg) & GPIO_CLOCK_VAL_IN) != 0; + struct intel_gmbus *bus = data; + struct drm_i915_private *dev_priv = bus->dev_priv; + u32 reserved = get_reserved(bus); + I915_WRITE_NOTRACE(bus->gpio_reg, reserved | GPIO_CLOCK_DIR_MASK); + I915_WRITE_NOTRACE(bus->gpio_reg, reserved); + return (I915_READ_NOTRACE(bus->gpio_reg) & GPIO_CLOCK_VAL_IN) != 0; } static int get_data(void *data) { - struct intel_gpio *gpio = data; - struct drm_i915_private *dev_priv = gpio->dev_priv; - u32 reserved = get_reserved(gpio); - I915_WRITE_NOTRACE(gpio->reg, reserved | GPIO_DATA_DIR_MASK); - I915_WRITE_NOTRACE(gpio->reg, reserved); - return (I915_READ_NOTRACE(gpio->reg) & GPIO_DATA_VAL_IN) != 0; + struct intel_gmbus *bus = data; + struct drm_i915_private *dev_priv = bus->dev_priv; + u32 reserved = get_reserved(bus); + I915_WRITE_NOTRACE(bus->gpio_reg, reserved | GPIO_DATA_DIR_MASK); + I915_WRITE_NOTRACE(bus->gpio_reg, reserved); + return (I915_READ_NOTRACE(bus->gpio_reg) & GPIO_DATA_VAL_IN) != 0; } static void set_clock(void *data, int state_high) { - struct intel_gpio *gpio = data; - struct drm_i915_private *dev_priv = gpio->dev_priv; - u32 reserved = get_reserved(gpio); + struct intel_gmbus *bus = data; + struct drm_i915_private *dev_priv = bus->dev_priv; + u32 reserved = get_reserved(bus); u32 clock_bits; if (state_high) @@ -126,15 +119,15 @@ static void set_clock(void *data, int state_high) clock_bits = GPIO_CLOCK_DIR_OUT | GPIO_CLOCK_DIR_MASK | GPIO_CLOCK_VAL_MASK; - I915_WRITE_NOTRACE(gpio->reg, reserved | clock_bits); - POSTING_READ(gpio->reg); + I915_WRITE_NOTRACE(bus->gpio_reg, reserved | clock_bits); + POSTING_READ(bus->gpio_reg); } static void set_data(void *data, int state_high) { - struct intel_gpio *gpio = data; - struct drm_i915_private *dev_priv = gpio->dev_priv; - u32 reserved = get_reserved(gpio); + struct intel_gmbus *bus = data; + struct drm_i915_private *dev_priv = bus->dev_priv; + u32 reserved = get_reserved(bus); u32 data_bits; if (state_high) @@ -143,13 +136,14 @@ static void set_data(void *data, int state_high) data_bits = GPIO_DATA_DIR_OUT | GPIO_DATA_DIR_MASK | GPIO_DATA_VAL_MASK; - I915_WRITE_NOTRACE(gpio->reg, reserved | data_bits); - POSTING_READ(gpio->reg); + I915_WRITE_NOTRACE(bus->gpio_reg, reserved | data_bits); + POSTING_READ(bus->gpio_reg); } -static struct i2c_adapter * -intel_gpio_create(struct drm_i915_private *dev_priv, u32 pin) +static bool +intel_gpio_setup(struct intel_gmbus *bus, u32 pin) { + struct drm_i915_private *dev_priv = bus->dev_priv; static const int map_pin_to_reg[] = { 0, GPIOB, @@ -160,65 +154,48 @@ intel_gpio_create(struct drm_i915_private *dev_priv, u32 pin) 0, GPIOF, }; - struct intel_gpio *gpio; + struct i2c_algo_bit_data *algo; if (pin >= ARRAY_SIZE(map_pin_to_reg) || !map_pin_to_reg[pin]) - return NULL; + return false; - gpio = kzalloc(sizeof(struct intel_gpio), GFP_KERNEL); - if (gpio == NULL) - return NULL; + algo = &bus->bit_algo; - gpio->reg = map_pin_to_reg[pin]; + bus->gpio_reg = map_pin_to_reg[pin]; if (HAS_PCH_SPLIT(dev_priv->dev)) - gpio->reg += PCH_GPIOA - GPIOA; - gpio->dev_priv = dev_priv; - - snprintf(gpio->adapter.name, sizeof(gpio->adapter.name), - "i915 GPIO%c", "?BACDE?F"[pin]); - gpio->adapter.owner = THIS_MODULE; - gpio->adapter.algo_data = &gpio->algo; - gpio->adapter.dev.parent = &dev_priv->dev->pdev->dev; - gpio->algo.setsda = set_data; - gpio->algo.setscl = set_clock; - gpio->algo.getsda = get_data; - gpio->algo.getscl = get_clock; - gpio->algo.udelay = I2C_RISEFALL_TIME; - gpio->algo.timeout = usecs_to_jiffies(2200); - gpio->algo.data = gpio; - - if (i2c_bit_add_bus(&gpio->adapter)) - goto out_free; - - return &gpio->adapter; - -out_free: - kfree(gpio); - return NULL; + bus->gpio_reg += PCH_GPIOA - GPIOA; + + bus->adapter.algo_data = algo; + algo->setsda = set_data; + algo->setscl = set_clock; + algo->getsda = get_data; + algo->getscl = get_clock; + algo->udelay = I2C_RISEFALL_TIME; + algo->timeout = usecs_to_jiffies(2200); + algo->data = bus; + + return true; } static int -intel_i2c_quirk_xfer(struct drm_i915_private *dev_priv, - struct i2c_adapter *adapter, +intel_i2c_quirk_xfer(struct intel_gmbus *bus, struct i2c_msg *msgs, int num) { - struct intel_gpio *gpio = container_of(adapter, - struct intel_gpio, - adapter); + struct drm_i915_private *dev_priv = bus->dev_priv; int ret; intel_i2c_reset(dev_priv->dev); intel_i2c_quirk_set(dev_priv, true); - set_data(gpio, 1); - set_clock(gpio, 1); + set_data(bus, 1); + set_clock(bus, 1); udelay(I2C_RISEFALL_TIME); - ret = adapter->algo->master_xfer(adapter, msgs, num); + ret = i2c_bit_algo.master_xfer(&bus->adapter, msgs, num); - set_data(gpio, 1); - set_clock(gpio, 1); + set_data(bus, 1); + set_clock(bus, 1); intel_i2c_quirk_set(dev_priv, false); return ret; @@ -232,12 +209,15 @@ gmbus_xfer(struct i2c_adapter *adapter, struct intel_gmbus *bus = container_of(adapter, struct intel_gmbus, adapter); - struct drm_i915_private *dev_priv = adapter->algo_data; - int i, reg_offset; + struct drm_i915_private *dev_priv = bus->dev_priv; + int i, reg_offset, ret; - if (bus->force_bit) - return intel_i2c_quirk_xfer(dev_priv, - bus->force_bit, msgs, num); + mutex_lock(&dev_priv->gmbus_mutex); + + if (bus->force_bit) { + ret = intel_i2c_quirk_xfer(bus, msgs, num); + goto out; + } reg_offset = HAS_PCH_SPLIT(dev_priv->dev) ? PCH_GMBUS0 - GMBUS0 : 0; @@ -249,7 +229,8 @@ gmbus_xfer(struct i2c_adapter *adapter, if (msgs[i].flags & I2C_M_RD) { I915_WRITE(GMBUS1 + reg_offset, - GMBUS_CYCLE_WAIT | (i + 1 == num ? GMBUS_CYCLE_STOP : 0) | + GMBUS_CYCLE_WAIT | + (i + 1 == num ? GMBUS_CYCLE_STOP : 0) | (len << GMBUS_BYTE_COUNT_SHIFT) | (msgs[i].addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_READ | GMBUS_SW_RDY); @@ -278,7 +259,8 @@ gmbus_xfer(struct i2c_adapter *adapter, I915_WRITE(GMBUS3 + reg_offset, val); I915_WRITE(GMBUS1 + reg_offset, - (i + 1 == num ? GMBUS_CYCLE_STOP : GMBUS_CYCLE_WAIT) | + GMBUS_CYCLE_WAIT | + (i + 1 == num ? GMBUS_CYCLE_STOP : 0) | (msgs[i].len << GMBUS_BYTE_COUNT_SHIFT) | (msgs[i].addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_WRITE | GMBUS_SW_RDY); @@ -317,11 +299,15 @@ clear_err: I915_WRITE(GMBUS1 + reg_offset, 0); done: - /* Mark the GMBUS interface as disabled. We will re-enable it at the - * start of the next xfer, till then let it sleep. + /* Mark the GMBUS interface as disabled after waiting for idle. + * We will re-enable it at the start of the next xfer, + * till then let it sleep. */ + if (wait_for((I915_READ(GMBUS2 + reg_offset) & GMBUS_ACTIVE) == 0, 10)) + DRM_INFO("GMBUS timed out waiting for idle\n"); I915_WRITE(GMBUS0 + reg_offset, 0); - return i; + ret = i; + goto out; timeout: DRM_INFO("GMBUS timed out, falling back to bit banging on pin %d [%s]\n", @@ -329,23 +315,21 @@ timeout: I915_WRITE(GMBUS0 + reg_offset, 0); /* Hardware may not support GMBUS over these pins? Try GPIO bitbanging instead. */ - bus->force_bit = intel_gpio_create(dev_priv, bus->reg0 & 0xff); - if (!bus->force_bit) - return -ENOMEM; - - return intel_i2c_quirk_xfer(dev_priv, bus->force_bit, msgs, num); + if (!bus->has_gpio) { + ret = -EIO; + } else { + bus->force_bit = true; + ret = intel_i2c_quirk_xfer(bus, msgs, num); + } +out: + mutex_unlock(&dev_priv->gmbus_mutex); + return ret; } static u32 gmbus_func(struct i2c_adapter *adapter) { - struct intel_gmbus *bus = container_of(adapter, - struct intel_gmbus, - adapter); - - if (bus->force_bit) - bus->force_bit->algo->functionality(bus->force_bit); - - return (I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | + return i2c_bit_algo.functionality(adapter) & + (I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | /* I2C_FUNC_10BIT_ADDR | */ I2C_FUNC_SMBUS_READ_BLOCK_DATA | I2C_FUNC_SMBUS_BLOCK_PROC_CALL); @@ -375,11 +359,13 @@ int intel_setup_gmbus(struct drm_device *dev) struct drm_i915_private *dev_priv = dev->dev_private; int ret, i; - dev_priv->gmbus = kcalloc(sizeof(struct intel_gmbus), GMBUS_NUM_PORTS, + dev_priv->gmbus = kcalloc(GMBUS_NUM_PORTS, sizeof(struct intel_gmbus), GFP_KERNEL); if (dev_priv->gmbus == NULL) return -ENOMEM; + mutex_init(&dev_priv->gmbus_mutex); + for (i = 0; i < GMBUS_NUM_PORTS; i++) { struct intel_gmbus *bus = &dev_priv->gmbus[i]; @@ -391,7 +377,7 @@ int intel_setup_gmbus(struct drm_device *dev) names[i]); bus->adapter.dev.parent = &dev->pdev->dev; - bus->adapter.algo_data = dev_priv; + bus->dev_priv = dev_priv; bus->adapter.algo = &gmbus_algorithm; ret = i2c_add_adapter(&bus->adapter); @@ -401,8 +387,11 @@ int intel_setup_gmbus(struct drm_device *dev) /* By default use a conservative clock rate */ bus->reg0 = i | GMBUS_RATE_100KHZ; + bus->has_gpio = intel_gpio_setup(bus, i); + /* XXX force bit banging until GMBUS is fully debugged */ - bus->force_bit = intel_gpio_create(dev_priv, i); + if (bus->has_gpio && IS_GEN2(dev)) + bus->force_bit = true; } intel_i2c_reset(dev_priv->dev); @@ -430,19 +419,8 @@ void intel_gmbus_force_bit(struct i2c_adapter *adapter, bool force_bit) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - if (force_bit) { - if (bus->force_bit == NULL) { - struct drm_i915_private *dev_priv = adapter->algo_data; - bus->force_bit = intel_gpio_create(dev_priv, - bus->reg0 & 0xff); - } - } else { - if (bus->force_bit) { - i2c_del_adapter(bus->force_bit); - kfree(bus->force_bit); - bus->force_bit = NULL; - } - } + if (bus->has_gpio) + bus->force_bit = force_bit; } void intel_teardown_gmbus(struct drm_device *dev) @@ -455,10 +433,6 @@ void intel_teardown_gmbus(struct drm_device *dev) for (i = 0; i < GMBUS_NUM_PORTS; i++) { struct intel_gmbus *bus = &dev_priv->gmbus[i]; - if (bus->force_bit) { - i2c_del_adapter(bus->force_bit); - kfree(bus->force_bit); - } i2c_del_adapter(&bus->adapter); } diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index aa84832b0e1..c5c0973af8a 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -739,6 +739,22 @@ static const struct dmi_system_id intel_no_lvds[] = { DMI_MATCH(DMI_BOARD_NAME, "AT5NM10T-I"), }, }, + { + .callback = intel_no_lvds_dmi_callback, + .ident = "Hewlett-Packard t5745", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_BOARD_NAME, "hp t5745"), + }, + }, + { + .callback = intel_no_lvds_dmi_callback, + .ident = "Hewlett-Packard st5747", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_BOARD_NAME, "hp st5747"), + }, + }, { } /* terminating entry */ }; @@ -844,6 +860,18 @@ static bool lvds_is_present_in_vbt(struct drm_device *dev, return false; } +static bool intel_lvds_supported(struct drm_device *dev) +{ + /* With the introduction of the PCH we gained a dedicated + * LVDS presence pin, use it. */ + if (HAS_PCH_SPLIT(dev)) + return true; + + /* Otherwise LVDS was only attached to mobile products, + * except for the inglorious 830gm */ + return IS_MOBILE(dev) && !IS_I830(dev); +} + /** * intel_lvds_init - setup LVDS connectors on this device * @dev: drm device @@ -865,6 +893,9 @@ bool intel_lvds_init(struct drm_device *dev) int pipe; u8 pin; + if (!intel_lvds_supported(dev)) + return false; + /* Skip init on machines we know falsely report LVDS */ if (dmi_check_system(intel_no_lvds)) return false; diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c index be2c6fe07d1..d1928e79d9b 100644 --- a/drivers/gpu/drm/i915/intel_modes.c +++ b/drivers/gpu/drm/i915/intel_modes.c @@ -28,6 +28,7 @@ #include <linux/fb.h> #include <drm/drm_edid.h> #include "drmP.h" +#include "drm_edid.h" #include "intel_drv.h" #include "i915_drv.h" @@ -42,13 +43,13 @@ bool intel_ddc_probe(struct intel_encoder *intel_encoder, int ddc_bus) u8 buf[2]; struct i2c_msg msgs[] = { { - .addr = 0x50, + .addr = DDC_ADDR, .flags = 0, .len = 1, .buf = out_buf, }, { - .addr = 0x50, + .addr = DDC_ADDR, .flags = I2C_M_RD, .len = 1, .buf = buf, @@ -83,10 +84,11 @@ int intel_ddc_get_modes(struct drm_connector *connector, return ret; } -static const char *force_audio_names[] = { - "off", - "auto", - "on", +static const struct drm_prop_enum_list force_audio_names[] = { + { HDMI_AUDIO_OFF_DVI, "force-dvi" }, + { HDMI_AUDIO_OFF, "off" }, + { HDMI_AUDIO_AUTO, "auto" }, + { HDMI_AUDIO_ON, "on" }, }; void @@ -95,27 +97,24 @@ intel_attach_force_audio_property(struct drm_connector *connector) struct drm_device *dev = connector->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct drm_property *prop; - int i; prop = dev_priv->force_audio_property; if (prop == NULL) { - prop = drm_property_create(dev, DRM_MODE_PROP_ENUM, + prop = drm_property_create_enum(dev, 0, "audio", + force_audio_names, ARRAY_SIZE(force_audio_names)); if (prop == NULL) return; - for (i = 0; i < ARRAY_SIZE(force_audio_names); i++) - drm_property_add_enum(prop, i, i-1, force_audio_names[i]); - dev_priv->force_audio_property = prop; } drm_connector_attach_property(connector, prop, 0); } -static const char *broadcast_rgb_names[] = { - "Full", - "Limited 16:235", +static const struct drm_prop_enum_list broadcast_rgb_names[] = { + { 0, "Full" }, + { 1, "Limited 16:235" }, }; void @@ -124,19 +123,16 @@ intel_attach_broadcast_rgb_property(struct drm_connector *connector) struct drm_device *dev = connector->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct drm_property *prop; - int i; prop = dev_priv->broadcast_rgb_property; if (prop == NULL) { - prop = drm_property_create(dev, DRM_MODE_PROP_ENUM, + prop = drm_property_create_enum(dev, DRM_MODE_PROP_ENUM, "Broadcast RGB", + broadcast_rgb_names, ARRAY_SIZE(broadcast_rgb_names)); if (prop == NULL) return; - for (i = 0; i < ARRAY_SIZE(broadcast_rgb_names); i++) - drm_property_add_enum(prop, i, i, broadcast_rgb_names[i]); - dev_priv->broadcast_rgb_property = prop; } diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index cdf17d4cc1f..80b331c322f 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -25,8 +25,6 @@ * * Derived from Xorg ddx, xf86-video-intel, src/i830_video.c */ - -#include <linux/seq_file.h> #include "drmP.h" #include "drm.h" #include "i915_drm.h" @@ -227,7 +225,8 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay, } overlay->last_flip_req = request->seqno; overlay->flip_tail = tail; - ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req); + ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req, + true); if (ret) return ret; @@ -263,7 +262,7 @@ i830_activate_pipe_a(struct drm_device *dev) DRM_DEBUG_DRIVER("Enabling pipe A in order to enable overlay\n"); mode = drm_mode_duplicate(dev, &vesa_640x480); - drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V); + drm_mode_set_crtcinfo(mode, 0); if (!drm_crtc_helper_set_mode(&crtc->base, mode, crtc->base.x, crtc->base.y, crtc->base.fb)) @@ -448,7 +447,8 @@ static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay) if (overlay->last_flip_req == 0) return 0; - ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req); + ret = i915_wait_request(LP_RING(dev_priv), overlay->last_flip_req, + true); if (ret) return ret; @@ -935,10 +935,10 @@ static int check_overlay_dst(struct intel_overlay *overlay, { struct drm_display_mode *mode = &overlay->crtc->base.mode; - if (rec->dst_x < mode->crtc_hdisplay && - rec->dst_x + rec->dst_width <= mode->crtc_hdisplay && - rec->dst_y < mode->crtc_vdisplay && - rec->dst_y + rec->dst_height <= mode->crtc_vdisplay) + if (rec->dst_x < mode->hdisplay && + rec->dst_x + rec->dst_width <= mode->hdisplay && + rec->dst_y < mode->vdisplay && + rec->dst_y + rec->dst_height <= mode->vdisplay) return 0; else return -EINVAL; diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 04d79fd1dc9..230a141dbea 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -48,7 +48,7 @@ intel_fixed_panel_mode(struct drm_display_mode *fixed_mode, adjusted_mode->clock = fixed_mode->clock; - drm_mode_set_crtcinfo(adjusted_mode, CRTC_INTERLACE_HALVE_V); + drm_mode_set_crtcinfo(adjusted_mode, 0); } /* adjusted_mode has been preset to be the panel's fixed mode */ @@ -141,8 +141,8 @@ static u32 i915_read_blc_pwm_ctl(struct drm_i915_private *dev_priv) dev_priv->saveBLC_PWM_CTL2 = val; } else if (val == 0) { I915_WRITE(BLC_PWM_PCH_CTL2, - dev_priv->saveBLC_PWM_CTL); - val = dev_priv->saveBLC_PWM_CTL; + dev_priv->saveBLC_PWM_CTL2); + val = dev_priv->saveBLC_PWM_CTL2; } } else { val = I915_READ(BLC_PWM_CTL); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 536191540b0..fc66af6a944 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -52,20 +52,6 @@ static inline int ring_space(struct intel_ring_buffer *ring) return space; } -static u32 i915_gem_get_seqno(struct drm_device *dev) -{ - drm_i915_private_t *dev_priv = dev->dev_private; - u32 seqno; - - seqno = dev_priv->next_seqno; - - /* reserve 0 for non-seqno */ - if (++dev_priv->next_seqno == 0) - dev_priv->next_seqno = 1; - - return seqno; -} - static int render_ring_flush(struct intel_ring_buffer *ring, u32 invalidate_domains, @@ -399,8 +385,6 @@ static int init_render_ring(struct intel_ring_buffer *ring) if (INTEL_INFO(dev)->gen > 3) { int mode = VS_TIMER_DISPATCH << 16 | VS_TIMER_DISPATCH; - if (IS_GEN6(dev) || IS_GEN7(dev)) - mode |= MI_FLUSH_ENABLE << 16 | MI_FLUSH_ENABLE; I915_WRITE(MI_MODE, mode); if (IS_GEN7(dev)) I915_WRITE(GFX_MODE_GEN7, @@ -467,7 +451,7 @@ gen6_add_request(struct intel_ring_buffer *ring, mbox1_reg = ring->signal_mbox[0]; mbox2_reg = ring->signal_mbox[1]; - *seqno = i915_gem_get_seqno(ring->dev); + *seqno = i915_gem_next_request_seqno(ring); update_mboxes(ring, *seqno, mbox1_reg); update_mboxes(ring, *seqno, mbox2_reg); @@ -565,8 +549,7 @@ static int pc_render_add_request(struct intel_ring_buffer *ring, u32 *result) { - struct drm_device *dev = ring->dev; - u32 seqno = i915_gem_get_seqno(dev); + u32 seqno = i915_gem_next_request_seqno(ring); struct pipe_control *pc = ring->private; u32 scratch_addr = pc->gtt_offset + 128; int ret; @@ -600,6 +583,7 @@ pc_render_add_request(struct intel_ring_buffer *ring, PIPE_CONTROL_FLUSH(ring, scratch_addr); scratch_addr += 128; PIPE_CONTROL_FLUSH(ring, scratch_addr); + intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_WRITE_FLUSH | PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE | @@ -617,8 +601,7 @@ static int render_ring_add_request(struct intel_ring_buffer *ring, u32 *result) { - struct drm_device *dev = ring->dev; - u32 seqno = i915_gem_get_seqno(dev); + u32 seqno = i915_gem_next_request_seqno(ring); int ret; ret = intel_ring_begin(ring, 4); @@ -744,13 +727,13 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring) */ if (IS_GEN7(dev)) { switch (ring->id) { - case RING_RENDER: + case RCS: mmio = RENDER_HWS_PGA_GEN7; break; - case RING_BLT: + case BCS: mmio = BLT_HWS_PGA_GEN7; break; - case RING_BSD: + case VCS: mmio = BSD_HWS_PGA_GEN7; break; } @@ -792,7 +775,7 @@ ring_add_request(struct intel_ring_buffer *ring, if (ret) return ret; - seqno = i915_gem_get_seqno(ring->dev); + seqno = i915_gem_next_request_seqno(ring); intel_ring_emit(ring, MI_STORE_DWORD_INDEX); intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT); @@ -816,8 +799,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag) /* It looks like we need to prevent the gt from suspending while waiting * for an notifiy irq, otherwise irqs seem to get lost on at least the * blt/bsd rings on ivb. */ - if (IS_GEN7(dev)) - gen6_gt_force_wake_get(dev_priv); + gen6_gt_force_wake_get(dev_priv); spin_lock(&ring->irq_lock); if (ring->irq_refcount++ == 0) { @@ -844,8 +826,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag) } spin_unlock(&ring->irq_lock); - if (IS_GEN7(dev)) - gen6_gt_force_wake_put(dev_priv); + gen6_gt_force_wake_put(dev_priv); } static bool @@ -1127,11 +1108,93 @@ static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring) return 0; } +static int intel_ring_wait_seqno(struct intel_ring_buffer *ring, u32 seqno) +{ + struct drm_i915_private *dev_priv = ring->dev->dev_private; + bool was_interruptible; + int ret; + + /* XXX As we have not yet audited all the paths to check that + * they are ready for ERESTARTSYS from intel_ring_begin, do not + * allow us to be interruptible by a signal. + */ + was_interruptible = dev_priv->mm.interruptible; + dev_priv->mm.interruptible = false; + + ret = i915_wait_request(ring, seqno, true); + + dev_priv->mm.interruptible = was_interruptible; + + return ret; +} + +static int intel_ring_wait_request(struct intel_ring_buffer *ring, int n) +{ + struct drm_i915_gem_request *request; + u32 seqno = 0; + int ret; + + i915_gem_retire_requests_ring(ring); + + if (ring->last_retired_head != -1) { + ring->head = ring->last_retired_head; + ring->last_retired_head = -1; + ring->space = ring_space(ring); + if (ring->space >= n) + return 0; + } + + list_for_each_entry(request, &ring->request_list, list) { + int space; + + if (request->tail == -1) + continue; + + space = request->tail - (ring->tail + 8); + if (space < 0) + space += ring->size; + if (space >= n) { + seqno = request->seqno; + break; + } + + /* Consume this request in case we need more space than + * is available and so need to prevent a race between + * updating last_retired_head and direct reads of + * I915_RING_HEAD. It also provides a nice sanity check. + */ + request->tail = -1; + } + + if (seqno == 0) + return -ENOSPC; + + ret = intel_ring_wait_seqno(ring, seqno); + if (ret) + return ret; + + if (WARN_ON(ring->last_retired_head == -1)) + return -ENOSPC; + + ring->head = ring->last_retired_head; + ring->last_retired_head = -1; + ring->space = ring_space(ring); + if (WARN_ON(ring->space < n)) + return -ENOSPC; + + return 0; +} + int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; unsigned long end; + int ret; + + ret = intel_ring_wait_request(ring, n); + if (ret != -ENOSPC) + return ret; trace_i915_ring_wait_begin(ring); if (drm_core_check_feature(dev, DRIVER_GEM)) @@ -1200,7 +1263,7 @@ void intel_ring_advance(struct intel_ring_buffer *ring) static const struct intel_ring_buffer render_ring = { .name = "render ring", - .id = RING_RENDER, + .id = RCS, .mmio_base = RENDER_RING_BASE, .size = 32 * PAGE_SIZE, .init = init_render_ring, @@ -1223,7 +1286,7 @@ static const struct intel_ring_buffer render_ring = { static const struct intel_ring_buffer bsd_ring = { .name = "bsd ring", - .id = RING_BSD, + .id = VCS, .mmio_base = BSD_RING_BASE, .size = 32 * PAGE_SIZE, .init = init_ring_common, @@ -1333,7 +1396,7 @@ gen6_bsd_ring_put_irq(struct intel_ring_buffer *ring) /* ring buffer for Video Codec for Gen6+ */ static const struct intel_ring_buffer gen6_bsd_ring = { .name = "gen6 bsd ring", - .id = RING_BSD, + .id = VCS, .mmio_base = GEN6_BSD_RING_BASE, .size = 32 * PAGE_SIZE, .init = init_ring_common, @@ -1369,79 +1432,13 @@ blt_ring_put_irq(struct intel_ring_buffer *ring) GEN6_BLITTER_USER_INTERRUPT); } - -/* Workaround for some stepping of SNB, - * each time when BLT engine ring tail moved, - * the first command in the ring to be parsed - * should be MI_BATCH_BUFFER_START - */ -#define NEED_BLT_WORKAROUND(dev) \ - (IS_GEN6(dev) && (dev->pdev->revision < 8)) - -static inline struct drm_i915_gem_object * -to_blt_workaround(struct intel_ring_buffer *ring) -{ - return ring->private; -} - -static int blt_ring_init(struct intel_ring_buffer *ring) -{ - if (NEED_BLT_WORKAROUND(ring->dev)) { - struct drm_i915_gem_object *obj; - u32 *ptr; - int ret; - - obj = i915_gem_alloc_object(ring->dev, 4096); - if (obj == NULL) - return -ENOMEM; - - ret = i915_gem_object_pin(obj, 4096, true); - if (ret) { - drm_gem_object_unreference(&obj->base); - return ret; - } - - ptr = kmap(obj->pages[0]); - *ptr++ = MI_BATCH_BUFFER_END; - *ptr++ = MI_NOOP; - kunmap(obj->pages[0]); - - ret = i915_gem_object_set_to_gtt_domain(obj, false); - if (ret) { - i915_gem_object_unpin(obj); - drm_gem_object_unreference(&obj->base); - return ret; - } - - ring->private = obj; - } - - return init_ring_common(ring); -} - -static int blt_ring_begin(struct intel_ring_buffer *ring, - int num_dwords) -{ - if (ring->private) { - int ret = intel_ring_begin(ring, num_dwords+2); - if (ret) - return ret; - - intel_ring_emit(ring, MI_BATCH_BUFFER_START); - intel_ring_emit(ring, to_blt_workaround(ring)->gtt_offset); - - return 0; - } else - return intel_ring_begin(ring, 4); -} - static int blt_ring_flush(struct intel_ring_buffer *ring, u32 invalidate, u32 flush) { uint32_t cmd; int ret; - ret = blt_ring_begin(ring, 4); + ret = intel_ring_begin(ring, 4); if (ret) return ret; @@ -1456,22 +1453,12 @@ static int blt_ring_flush(struct intel_ring_buffer *ring, return 0; } -static void blt_ring_cleanup(struct intel_ring_buffer *ring) -{ - if (!ring->private) - return; - - i915_gem_object_unpin(ring->private); - drm_gem_object_unreference(ring->private); - ring->private = NULL; -} - static const struct intel_ring_buffer gen6_blt_ring = { .name = "blt ring", - .id = RING_BLT, + .id = BCS, .mmio_base = BLT_RING_BASE, .size = 32 * PAGE_SIZE, - .init = blt_ring_init, + .init = init_ring_common, .write_tail = ring_write_tail, .flush = blt_ring_flush, .add_request = gen6_add_request, @@ -1479,7 +1466,6 @@ static const struct intel_ring_buffer gen6_blt_ring = { .irq_get = blt_ring_get_irq, .irq_put = blt_ring_put_irq, .dispatch_execbuffer = gen6_ring_dispatch_execbuffer, - .cleanup = blt_ring_cleanup, .sync_to = gen6_blt_ring_sync_to, .semaphore_register = {MI_SEMAPHORE_SYNC_BR, MI_SEMAPHORE_SYNC_BV, diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 68281c96c55..bc0365b8fa4 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -1,13 +1,6 @@ #ifndef _INTEL_RINGBUFFER_H_ #define _INTEL_RINGBUFFER_H_ -enum { - RCS = 0x0, - VCS, - BCS, - I915_NUM_RINGS, -}; - struct intel_hw_status_page { u32 __iomem *page_addr; unsigned int gfx_addr; @@ -36,10 +29,11 @@ struct intel_hw_status_page { struct intel_ring_buffer { const char *name; enum intel_ring_id { - RING_RENDER = 0x1, - RING_BSD = 0x2, - RING_BLT = 0x4, + RCS = 0x0, + VCS, + BCS, } id; +#define I915_NUM_RINGS 3 u32 mmio_base; void __iomem *virtual_start; struct drm_device *dev; @@ -52,6 +46,16 @@ struct intel_ring_buffer { int effective_size; struct intel_hw_status_page status_page; + /** We track the position of the requests in the ring buffer, and + * when each is retired we increment last_retired_head as the GPU + * must have finished processing the request and so we know we + * can advance the ringbuffer up to that position. + * + * last_retired_head is set to -1 after the value is consumed so + * we can detect new retirements. + */ + u32 last_retired_head; + spinlock_t irq_lock; u32 irq_refcount; u32 irq_mask; @@ -119,6 +123,12 @@ struct intel_ring_buffer { void *private; }; +static inline unsigned +intel_ring_flag(struct intel_ring_buffer *ring) +{ + return 1 << ring->id; +} + static inline u32 intel_ring_sync_index(struct intel_ring_buffer *ring, struct intel_ring_buffer *other) @@ -193,6 +203,11 @@ int intel_init_blt_ring_buffer(struct drm_device *dev); u32 intel_ring_get_active_head(struct intel_ring_buffer *ring); void intel_ring_setup_status_page(struct intel_ring_buffer *ring); +static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring) +{ + return ring->tail; +} + static inline void i915_trace_irq_get(struct intel_ring_buffer *ring, u32 seqno) { if (ring->trace_irq_seqno == 0 && ring->irq_get(ring)) diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index e334ec33a47..e36b171c1e7 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -148,7 +148,7 @@ struct intel_sdvo_connector { /* Mark the type of connector */ uint16_t output_flag; - int force_audio; + enum hdmi_force_audio force_audio; /* This contains all current supported TV format */ u8 tv_format_supported[TV_FORMAT_NUM]; @@ -944,7 +944,6 @@ intel_sdvo_set_input_timings_for_mode(struct intel_sdvo *intel_sdvo, intel_sdvo_get_mode_from_dtd(adjusted_mode, &intel_sdvo->input_dtd); - drm_mode_set_crtcinfo(adjusted_mode, 0); return true; } @@ -1310,8 +1309,8 @@ intel_sdvo_tmds_sink_detect(struct drm_connector *connector) if (status == connector_status_connected) { struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); - if (intel_sdvo_connector->force_audio) - intel_sdvo->has_hdmi_audio = intel_sdvo_connector->force_audio > 0; + if (intel_sdvo_connector->force_audio != HDMI_AUDIO_AUTO) + intel_sdvo->has_hdmi_audio = (intel_sdvo_connector->force_audio == HDMI_AUDIO_ON); } return status; @@ -1684,10 +1683,10 @@ intel_sdvo_set_property(struct drm_connector *connector, intel_sdvo_connector->force_audio = i; - if (i == 0) + if (i == HDMI_AUDIO_AUTO) has_audio = intel_sdvo_detect_hdmi_audio(connector); else - has_audio = i > 0; + has_audio = (i == HDMI_AUDIO_ON); if (has_audio == intel_sdvo->has_hdmi_audio) return 0; @@ -1985,7 +1984,7 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector, drm_connector_helper_add(&connector->base.base, &intel_sdvo_connector_helper_funcs); - connector->base.base.interlace_allowed = 0; + connector->base.base.interlace_allowed = 1; connector->base.base.doublescan_allowed = 0; connector->base.base.display_info.subpixel_order = SubPixelHorizontalRGB; @@ -2277,10 +2276,8 @@ static bool intel_sdvo_tv_create_property(struct intel_sdvo *intel_sdvo, intel_sdvo_connector->max_##name = data_value[0]; \ intel_sdvo_connector->cur_##name = response; \ intel_sdvo_connector->name = \ - drm_property_create(dev, DRM_MODE_PROP_RANGE, #name, 2); \ + drm_property_create_range(dev, 0, #name, 0, data_value[0]); \ if (!intel_sdvo_connector->name) return false; \ - intel_sdvo_connector->name->values[0] = 0; \ - intel_sdvo_connector->name->values[1] = data_value[0]; \ drm_connector_attach_property(connector, \ intel_sdvo_connector->name, \ intel_sdvo_connector->cur_##name); \ @@ -2314,25 +2311,19 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, intel_sdvo_connector->left_margin = data_value[0] - response; intel_sdvo_connector->right_margin = intel_sdvo_connector->left_margin; intel_sdvo_connector->left = - drm_property_create(dev, DRM_MODE_PROP_RANGE, - "left_margin", 2); + drm_property_create_range(dev, 0, "left_margin", 0, data_value[0]); if (!intel_sdvo_connector->left) return false; - intel_sdvo_connector->left->values[0] = 0; - intel_sdvo_connector->left->values[1] = data_value[0]; drm_connector_attach_property(connector, intel_sdvo_connector->left, intel_sdvo_connector->left_margin); intel_sdvo_connector->right = - drm_property_create(dev, DRM_MODE_PROP_RANGE, - "right_margin", 2); + drm_property_create_range(dev, 0, "right_margin", 0, data_value[0]); if (!intel_sdvo_connector->right) return false; - intel_sdvo_connector->right->values[0] = 0; - intel_sdvo_connector->right->values[1] = data_value[0]; drm_connector_attach_property(connector, intel_sdvo_connector->right, intel_sdvo_connector->right_margin); @@ -2356,25 +2347,21 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, intel_sdvo_connector->top_margin = data_value[0] - response; intel_sdvo_connector->bottom_margin = intel_sdvo_connector->top_margin; intel_sdvo_connector->top = - drm_property_create(dev, DRM_MODE_PROP_RANGE, - "top_margin", 2); + drm_property_create_range(dev, 0, + "top_margin", 0, data_value[0]); if (!intel_sdvo_connector->top) return false; - intel_sdvo_connector->top->values[0] = 0; - intel_sdvo_connector->top->values[1] = data_value[0]; drm_connector_attach_property(connector, intel_sdvo_connector->top, intel_sdvo_connector->top_margin); intel_sdvo_connector->bottom = - drm_property_create(dev, DRM_MODE_PROP_RANGE, - "bottom_margin", 2); + drm_property_create_range(dev, 0, + "bottom_margin", 0, data_value[0]); if (!intel_sdvo_connector->bottom) return false; - intel_sdvo_connector->bottom->values[0] = 0; - intel_sdvo_connector->bottom->values[1] = data_value[0]; drm_connector_attach_property(connector, intel_sdvo_connector->bottom, intel_sdvo_connector->bottom_margin); @@ -2403,12 +2390,10 @@ intel_sdvo_create_enhance_property_tv(struct intel_sdvo *intel_sdvo, intel_sdvo_connector->max_dot_crawl = 1; intel_sdvo_connector->cur_dot_crawl = response & 0x1; intel_sdvo_connector->dot_crawl = - drm_property_create(dev, DRM_MODE_PROP_RANGE, "dot_crawl", 2); + drm_property_create_range(dev, 0, "dot_crawl", 0, 1); if (!intel_sdvo_connector->dot_crawl) return false; - intel_sdvo_connector->dot_crawl->values[0] = 0; - intel_sdvo_connector->dot_crawl->values[1] = 1; drm_connector_attach_property(connector, intel_sdvo_connector->dot_crawl, intel_sdvo_connector->cur_dot_crawl); diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index a0835040c86..7aa0450399a 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -501,7 +501,7 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, intel_wait_for_vblank(dev, to_intel_crtc(crtc)->pipe); mutex_lock(&dev->struct_mutex); } - i915_gem_object_unpin(old_obj); + intel_unpin_fb_obj(old_obj); } out_unlock: @@ -528,7 +528,7 @@ intel_disable_plane(struct drm_plane *plane) goto out; mutex_lock(&dev->struct_mutex); - i915_gem_object_unpin(intel_plane->obj); + intel_unpin_fb_obj(intel_plane->obj); intel_plane->obj = NULL; mutex_unlock(&dev->struct_mutex); out: diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index 1571be37ce3..05f765ef546 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1240,7 +1240,7 @@ intel_tv_detect(struct drm_connector *connector, bool force) int type; mode = reported_modes[0]; - drm_mode_set_crtcinfo(&mode, CRTC_INTERLACE_HALVE_V); + drm_mode_set_crtcinfo(&mode, 0); if (intel_tv->base.base.crtc && intel_tv->base.base.crtc->enabled) { type = intel_tv_detect_type(intel_tv, connector); |