From a9c1f90c8e1792127f8348c1cc2565b79b2ef20a Mon Sep 17 00:00:00 2001 From: Mika Kuoppala Date: Thu, 22 Aug 2013 21:09:00 +0300 Subject: drm/i915: Don't mask EI UP interrupt on IVB|SNB Submitting a batchbuffer which simulates a gpu hang by doing MI_BATCH_BUFFER_START into itself, to test hangcheck, started to hard hang the whole box (IVB). Bisecting lead to this commit: commit 664b422c2966cd39b8f67e8d53a566ea8c877cd6 Author: Vinit Azad Date: Wed Aug 14 13:34:33 2013 -0700 drm/i915: Only unmask required PM interrupts Experimenting with the mask register showed that unmasking EI UP will prevent the hard hang in IVB and SNB. HSW doesn't hang with EI UP masked. Considering we are just disabling interrupts that aren't even delivered to driver, this change is more likely to paper over some weirdness in gpu's internal state machine. But until better explanation can be found, let's trade little bit of power for stability on these architectures. v2: - Unmask EI_EXPIRED directly in I915_WRITE (Vinit) v3: - Only unmask on SNB and IVB Cc: Vinit Azad Signed-off-by: Mika Kuoppala Acked-by: Vinit Azad Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_pm.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 46056820d1d2..6b1d00389952 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3447,14 +3447,24 @@ int intel_enable_rc6(const struct drm_device *dev) static void gen6_enable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + u32 enabled_intrs; spin_lock_irq(&dev_priv->irq_lock); WARN_ON(dev_priv->rps.pm_iir); snb_enable_pm_irq(dev_priv, GEN6_PM_RPS_EVENTS); I915_WRITE(GEN6_PMIIR, GEN6_PM_RPS_EVENTS); spin_unlock_irq(&dev_priv->irq_lock); + /* only unmask PM interrupts we need. Mask all others. */ - I915_WRITE(GEN6_PMINTRMSK, ~GEN6_PM_RPS_EVENTS); + enabled_intrs = GEN6_PM_RPS_EVENTS; + + /* IVB and SNB hard hangs on looping batchbuffer + * if GEN6_PM_UP_EI_EXPIRED is masked. + */ + if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) + enabled_intrs |= GEN6_PM_RP_UP_EI_EXPIRED; + + I915_WRITE(GEN6_PMINTRMSK, ~enabled_intrs); } static void gen6_enable_rps(struct drm_device *dev) -- cgit v1.2.3-70-g09d2 From 521198a2e7095c8c7daa8d7d3a76a110c346be6f Mon Sep 17 00:00:00 2001 From: Mika Kuoppala Date: Fri, 23 Aug 2013 16:52:30 +0300 Subject: drm/i915: sanitize forcewake registers on reset In reset we try to restore the forcewake state to pre reset state, using forcewake_count. The reset doesn't seem to clear the forcewake bits so we get warn on forcewake ack register not clearing. Use same mechanism as intel_uncore_sanitize() does when loading driver to reset the forcewake bits, right after the chip has been reset. Reviewed-by: Chris Wilson Signed-off-by: Mika Kuoppala Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_uncore.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 8f5bc869c023..8649f1c36b00 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -261,7 +261,7 @@ void intel_uncore_init(struct drm_device *dev) } } -void intel_uncore_sanitize(struct drm_device *dev) +static void intel_uncore_forcewake_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -272,6 +272,11 @@ void intel_uncore_sanitize(struct drm_device *dev) if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) __gen6_gt_force_wake_mt_reset(dev_priv); } +} + +void intel_uncore_sanitize(struct drm_device *dev) +{ + intel_uncore_forcewake_reset(dev); /* BIOS often leaves RC6 enabled, but disable it for hw init */ intel_disable_gt_powersave(dev); @@ -549,6 +554,8 @@ static int gen6_do_reset(struct drm_device *dev) /* Spin waiting for the device to ack the reset request */ ret = wait_for((__raw_i915_read32(dev_priv, GEN6_GDRST) & GEN6_GRDOM_FULL) == 0, 500); + intel_uncore_forcewake_reset(dev); + /* If reset with a user forcewake, try to restore, otherwise turn it off */ if (dev_priv->uncore.forcewake_count) dev_priv->uncore.funcs.force_wake_get(dev_priv); -- cgit v1.2.3-70-g09d2 From 97e4eed7dc532e20208b0bdf7ad1136569da2f35 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 26 Aug 2013 16:18:54 +0100 Subject: drm/i915: Adjust available RPS information through sysfs for vlv Valleyview has its own render power state implementation with different capability knobs - it has no RP0,RP1,RPn but rather RPe. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=67734 Signed-off-by: Chris Wilson Tested-by: kobe.qin@intel.com Reviewed-by: Jani Nikula Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_sysfs.c | 36 +++++++++++++++++++++++++++++++----- 1 file changed, 31 insertions(+), 5 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index a777e7f3b0df..c8c4112de110 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -224,6 +224,18 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev, return snprintf(buf, PAGE_SIZE, "%d\n", ret); } +static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev, + struct device_attribute *attr, char *buf) +{ + struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev); + struct drm_device *dev = minor->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + return snprintf(buf, PAGE_SIZE, "%d\n", + vlv_gpu_freq(dev_priv->mem_freq, + dev_priv->rps.rpe_delay)); +} + static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf) { struct drm_minor *minor = container_of(kdev, struct drm_minor, kdev); @@ -366,6 +378,7 @@ static DEVICE_ATTR(gt_cur_freq_mhz, S_IRUGO, gt_cur_freq_mhz_show, NULL); static DEVICE_ATTR(gt_max_freq_mhz, S_IRUGO | S_IWUSR, gt_max_freq_mhz_show, gt_max_freq_mhz_store); static DEVICE_ATTR(gt_min_freq_mhz, S_IRUGO | S_IWUSR, gt_min_freq_mhz_show, gt_min_freq_mhz_store); +static DEVICE_ATTR(vlv_rpe_freq_mhz, S_IRUGO, vlv_rpe_freq_mhz_show, NULL); static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf); static DEVICE_ATTR(gt_RP0_freq_mhz, S_IRUGO, gt_rp_mhz_show, NULL); @@ -409,6 +422,14 @@ static const struct attribute *gen6_attrs[] = { NULL, }; +static const struct attribute *vlv_attrs[] = { + &dev_attr_gt_cur_freq_mhz.attr, + &dev_attr_gt_max_freq_mhz.attr, + &dev_attr_gt_min_freq_mhz.attr, + &dev_attr_vlv_rpe_freq_mhz.attr, + NULL, +}; + static ssize_t error_state_read(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) @@ -492,11 +513,13 @@ void i915_setup_sysfs(struct drm_device *dev) DRM_ERROR("l3 parity sysfs setup failed\n"); } - if (INTEL_INFO(dev)->gen >= 6) { + ret = 0; + if (IS_VALLEYVIEW(dev)) + ret = sysfs_create_files(&dev->primary->kdev.kobj, vlv_attrs); + else if (INTEL_INFO(dev)->gen >= 6) ret = sysfs_create_files(&dev->primary->kdev.kobj, gen6_attrs); - if (ret) - DRM_ERROR("gen6 sysfs setup failed\n"); - } + if (ret) + DRM_ERROR("RPS sysfs setup failed\n"); ret = sysfs_create_bin_file(&dev->primary->kdev.kobj, &error_state_attr); @@ -507,7 +530,10 @@ void i915_setup_sysfs(struct drm_device *dev) void i915_teardown_sysfs(struct drm_device *dev) { sysfs_remove_bin_file(&dev->primary->kdev.kobj, &error_state_attr); - sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs); + if (IS_VALLEYVIEW(dev)) + sysfs_remove_files(&dev->primary->kdev.kobj, vlv_attrs); + else + sysfs_remove_files(&dev->primary->kdev.kobj, gen6_attrs); device_remove_bin_file(&dev->primary->kdev, &dpf_attrs); #ifdef CONFIG_PM sysfs_unmerge_group(&dev->primary->kdev.kobj, &rc6_attr_group); -- cgit v1.2.3-70-g09d2 From 10603caacf599297c7da0c4f4db440d015b8131a Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 26 Aug 2013 19:51:06 -0300 Subject: drm/i915: Apply the force-detect VGA w/a to Valleyview It appears that Valleyview shares its VGA encoder with more recent siblings and requires the same forced detection cycle after a hardware reset before we can rely on hotplugging. Reported-and-tested-by: kobeqin Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=67733 Tested-by: kobeqin Signed-off-by: Chris Wilson [danvet: Check for gen >= 5 insted, acked by Chris.] Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_crt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index b5a3875f22c7..ea9022ef15d5 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -688,7 +688,7 @@ static void intel_crt_reset(struct drm_connector *connector) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crt *crt = intel_attached_crt(connector); - if (HAS_PCH_SPLIT(dev)) { + if (INTEL_INFO(dev)->gen >= 5) { u32 adpa; adpa = I915_READ(crt->adpa_reg); -- cgit v1.2.3-70-g09d2 From 8e8c06cd34dbd68d36b0c561b8850478ddc5fb84 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 26 Aug 2013 19:51:01 -0300 Subject: drm/i915: Report requested frequency alongside current frequency in debugfs It can be useful to compare at times the current vs requested frequency of the GPU, so provide the contents of RPNSWREQ alonside CAGF. Signed-off-by: Chris Wilson Reviewed-by: Rodrigo Vivi Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_debugfs.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 55ab9246e1b9..a6f4cb5af185 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -857,7 +857,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS); u32 rp_state_limits = I915_READ(GEN6_RP_STATE_LIMITS); u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP); - u32 rpstat, cagf; + u32 rpstat, cagf, reqf; u32 rpupei, rpcurup, rpprevup; u32 rpdownei, rpcurdown, rpprevdown; int max_freq; @@ -869,6 +869,14 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) gen6_gt_force_wake_get(dev_priv); + reqf = I915_READ(GEN6_RPNSWREQ); + reqf &= ~GEN6_TURBO_DISABLE; + if (IS_HASWELL(dev)) + reqf >>= 24; + else + reqf >>= 25; + reqf *= GT_FREQUENCY_MULTIPLIER; + rpstat = I915_READ(GEN6_RPSTAT1); rpupei = I915_READ(GEN6_RP_CUR_UP_EI); rpcurup = I915_READ(GEN6_RP_CUR_UP); @@ -893,6 +901,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused) gt_perf_status & 0xff); seq_printf(m, "Render p-state limit: %d\n", rp_state_limits & 0xff); + seq_printf(m, "RPNSWREQ: %dMHz\n", reqf); seq_printf(m, "CAGF: %dMHz\n", cagf); seq_printf(m, "RP CUR UP EI: %dus\n", rpupei & GEN6_CURICONT_MASK); -- cgit v1.2.3-70-g09d2 From b8d88d1d40c18d42e3fedc289832e28d14bc1f00 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 28 Aug 2013 10:57:59 +0200 Subject: drm/i915: tune down hangcheck noise We already have a big splashing *ERROR* for all the relevant cases of hangs, so this one here is redudant. And it results in an unclean dmesg when running with simulated hangs. Regression has been introduced in commit 05407ff889ceebe383aa5907219f86582ef96b72 Author: Mika Kuoppala Date: Thu May 30 09:04:29 2013 +0300 drm/i915: detect hang using per ring hangcheck_score Cc: Mika Kuoppala Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68641 Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_irq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index a03b445ceb5f..4c6853f57d62 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2027,9 +2027,9 @@ static void i915_hangcheck_elapsed(unsigned long data) for_each_ring(ring, dev_priv, i) { if (ring->hangcheck.score > FIRE) { - DRM_ERROR("%s on %s\n", - stuck[i] ? "stuck" : "no progress", - ring->name); + DRM_INFO("%s on %s\n", + stuck[i] ? "stuck" : "no progress", + ring->name); rings_hung++; } } -- cgit v1.2.3-70-g09d2 From a52690e445637dda7f71878965d64d9b6a15a2b7 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Tue, 27 Aug 2013 12:24:09 +0300 Subject: drm/i915: fix lvds/dp panel fitter setting If need to enable the panel fitter, the crtc timings have to be programmed according to the panel's native (fixed) mode. This isn't the case atm, since after the encoder changes adjusted_mode to fixed mode the crtc_* timing fields of adjusted_mode will stay at their original non-native values that the user passed in. This results in a corrupted output. One exception is when we have a second pass of computing encoder configs due to bandwidth limitation, since then we'll set adjusted_mode.crtc_* fields to the fixed mode values set in the first pass; so in this case things will work out. Fix this by updating the adjusted_mode.crtc_* fields when we set the fixed panel mode. This regression has been introduced in commit 135c81b8c3c9a70d7b55758c9c2a247a4abb7b64 Author: Daniel Vetter Date: Sun Jul 21 21:37:09 2013 +0200 drm/i915: clean up crtc timings computation Signed-off-by: Imre Deak Reviewed-by: Mika Kuoppala Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_panel.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index a43c33bc4a35..913cb9d7fd32 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -50,6 +50,8 @@ intel_fixed_panel_mode(struct drm_display_mode *fixed_mode, adjusted_mode->vtotal = fixed_mode->vtotal; adjusted_mode->clock = fixed_mode->clock; + + drm_mode_set_crtcinfo(adjusted_mode, 0); } /* adjusted_mode has been preset to be the panel's fixed mode */ -- cgit v1.2.3-70-g09d2 From 0d1aacac36530fce058d7a0db3da7befd5765417 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 26 Aug 2013 20:58:11 +0100 Subject: drm/i915: Embed the ring->private within the struct intel_ring_buffer We now have more devices using ring->private than not, and they all want the same structure. Worse, I would like to use a scratch page from outside of intel_ringbuffer.c and so for convenience would like to reuse ring->private. Embed the object into the struct intel_ringbuffer so that we can keep the code clean. Signed-off-by: Chris Wilson Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gpu_error.c | 2 +- drivers/gpu/drm/i915/intel_ringbuffer.c | 99 ++++++++++----------------------- drivers/gpu/drm/i915/intel_ringbuffer.h | 6 +- 3 files changed, 35 insertions(+), 72 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 558e568d5b45..aba9d7498996 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -641,7 +641,7 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv, if (WARN_ON(ring->id != RCS)) return NULL; - obj = ring->private; + obj = ring->scratch.obj; if (acthd >= i915_gem_obj_ggtt_offset(obj) && acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size) return i915_error_object_create(dev_priv, obj); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index f05cceac5a52..460ee1026fca 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -33,16 +33,6 @@ #include "i915_trace.h" #include "intel_drv.h" -/* - * 965+ support PIPE_CONTROL commands, which provide finer grained control - * over cache flushing. - */ -struct pipe_control { - struct drm_i915_gem_object *obj; - volatile u32 *cpu_page; - u32 gtt_offset; -}; - static inline int ring_space(struct intel_ring_buffer *ring) { int space = (ring->head & HEAD_ADDR) - (ring->tail + I915_RING_FREE_SPACE); @@ -175,8 +165,7 @@ gen4_render_ring_flush(struct intel_ring_buffer *ring, static int intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring) { - struct pipe_control *pc = ring->private; - u32 scratch_addr = pc->gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 128; int ret; @@ -213,8 +202,7 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring, u32 invalidate_domains, u32 flush_domains) { u32 flags = 0; - struct pipe_control *pc = ring->private; - u32 scratch_addr = pc->gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 128; int ret; /* Force SNB workarounds for PIPE_CONTROL flushes */ @@ -306,8 +294,7 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring, u32 invalidate_domains, u32 flush_domains) { u32 flags = 0; - struct pipe_control *pc = ring->private; - u32 scratch_addr = pc->gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 128; int ret; /* @@ -481,68 +468,43 @@ out: static int init_pipe_control(struct intel_ring_buffer *ring) { - struct pipe_control *pc; - struct drm_i915_gem_object *obj; int ret; - if (ring->private) + if (ring->scratch.obj) return 0; - pc = kmalloc(sizeof(*pc), GFP_KERNEL); - if (!pc) - return -ENOMEM; - - obj = i915_gem_alloc_object(ring->dev, 4096); - if (obj == NULL) { + ring->scratch.obj = i915_gem_alloc_object(ring->dev, 4096); + if (ring->scratch.obj == NULL) { DRM_ERROR("Failed to allocate seqno page\n"); ret = -ENOMEM; goto err; } - i915_gem_object_set_cache_level(obj, I915_CACHE_LLC); + i915_gem_object_set_cache_level(ring->scratch.obj, I915_CACHE_LLC); - ret = i915_gem_obj_ggtt_pin(obj, 4096, true, false); + ret = i915_gem_obj_ggtt_pin(ring->scratch.obj, 4096, true, false); if (ret) goto err_unref; - pc->gtt_offset = i915_gem_obj_ggtt_offset(obj); - pc->cpu_page = kmap(sg_page(obj->pages->sgl)); - if (pc->cpu_page == NULL) { + ring->scratch.gtt_offset = i915_gem_obj_ggtt_offset(ring->scratch.obj); + ring->scratch.cpu_page = kmap(sg_page(ring->scratch.obj->pages->sgl)); + if (ring->scratch.cpu_page == NULL) { ret = -ENOMEM; goto err_unpin; } DRM_DEBUG_DRIVER("%s pipe control offset: 0x%08x\n", - ring->name, pc->gtt_offset); - - pc->obj = obj; - ring->private = pc; + ring->name, ring->scratch.gtt_offset); return 0; err_unpin: - i915_gem_object_unpin(obj); + i915_gem_object_unpin(ring->scratch.obj); err_unref: - drm_gem_object_unreference(&obj->base); + drm_gem_object_unreference(&ring->scratch.obj->base); err: - kfree(pc); return ret; } -static void -cleanup_pipe_control(struct intel_ring_buffer *ring) -{ - struct pipe_control *pc = ring->private; - struct drm_i915_gem_object *obj; - - obj = pc->obj; - - kunmap(sg_page(obj->pages->sgl)); - i915_gem_object_unpin(obj); - drm_gem_object_unreference(&obj->base); - - kfree(pc); -} - static int init_render_ring(struct intel_ring_buffer *ring) { struct drm_device *dev = ring->dev; @@ -607,16 +569,16 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring) { struct drm_device *dev = ring->dev; - if (!ring->private) + if (ring->scratch.obj == NULL) return; - if (HAS_BROKEN_CS_TLB(dev)) - drm_gem_object_unreference(to_gem_object(ring->private)); - - if (INTEL_INFO(dev)->gen >= 5) - cleanup_pipe_control(ring); + if (INTEL_INFO(dev)->gen >= 5) { + kunmap(sg_page(ring->scratch.obj->pages->sgl)); + i915_gem_object_unpin(ring->scratch.obj); + } - ring->private = NULL; + drm_gem_object_unreference(&ring->scratch.obj->base); + ring->scratch.obj = NULL; } static void @@ -742,8 +704,7 @@ do { \ static int pc_render_add_request(struct intel_ring_buffer *ring) { - struct pipe_control *pc = ring->private; - u32 scratch_addr = pc->gtt_offset + 128; + u32 scratch_addr = ring->scratch.gtt_offset + 128; int ret; /* For Ironlake, MI_USER_INTERRUPT was deprecated and apparently @@ -761,7 +722,7 @@ pc_render_add_request(struct intel_ring_buffer *ring) intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_WRITE_FLUSH | PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE); - intel_ring_emit(ring, pc->gtt_offset | PIPE_CONTROL_GLOBAL_GTT); + intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT); intel_ring_emit(ring, ring->outstanding_lazy_request); intel_ring_emit(ring, 0); PIPE_CONTROL_FLUSH(ring, scratch_addr); @@ -780,7 +741,7 @@ pc_render_add_request(struct intel_ring_buffer *ring) PIPE_CONTROL_WRITE_FLUSH | PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE | PIPE_CONTROL_NOTIFY); - intel_ring_emit(ring, pc->gtt_offset | PIPE_CONTROL_GLOBAL_GTT); + intel_ring_emit(ring, ring->scratch.gtt_offset | PIPE_CONTROL_GLOBAL_GTT); intel_ring_emit(ring, ring->outstanding_lazy_request); intel_ring_emit(ring, 0); intel_ring_advance(ring); @@ -814,15 +775,13 @@ ring_set_seqno(struct intel_ring_buffer *ring, u32 seqno) static u32 pc_render_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) { - struct pipe_control *pc = ring->private; - return pc->cpu_page[0]; + return ring->scratch.cpu_page[0]; } static void pc_render_set_seqno(struct intel_ring_buffer *ring, u32 seqno) { - struct pipe_control *pc = ring->private; - pc->cpu_page[0] = seqno; + ring->scratch.cpu_page[0] = seqno; } static bool @@ -1141,8 +1100,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring, intel_ring_emit(ring, MI_NOOP); intel_ring_advance(ring); } else { - struct drm_i915_gem_object *obj = ring->private; - u32 cs_offset = i915_gem_obj_ggtt_offset(obj); + u32 cs_offset = ring->scratch.gtt_offset; if (len > I830_BATCH_LIMIT) return -ENOSPC; @@ -1835,7 +1793,8 @@ int intel_init_render_ring_buffer(struct drm_device *dev) return ret; } - ring->private = obj; + ring->scratch.obj = obj; + ring->scratch.gtt_offset = i915_gem_obj_ggtt_offset(obj); } return intel_init_ring_buffer(dev, ring); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 432ad5311ba6..68b1ca974d59 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -155,7 +155,11 @@ struct intel_ring_buffer { struct intel_ring_hangcheck hangcheck; - void *private; + struct { + struct drm_i915_gem_object *obj; + u32 gtt_offset; + volatile u32 *cpu_page; + } scratch; }; static inline bool -- cgit v1.2.3-70-g09d2 From ffe74d75502e3a9b0791240b5562bcbecc6ab8dc Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 26 Aug 2013 20:58:12 +0100 Subject: drm/i915: Use RCS flips on Ivybridge+ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RCS flips do work on Iybridge+ so long as we can unmask the messages through DERRMR. However, there are quite a few workarounds mentioned regarding unmasking more than one event or triggering more than one message through DERRMR. Those workarounds in principle prevent us from performing pipelined flips (and asynchronous flips across multiple planes) and equally apply to the "known good" BCS ring. Given that it already appears to work, and also appears to work with unmasking all 3 planes at once (and queuing flips across multiple planes), be brave. Bugzlla: https://bugs.freedesktop.org/show_bug.cgi?id=67600 Signed-off-by: Chris Wilson Lightly-tested-by: Stephane Marchesin Cc: Stephane Marchesin Cc: Ben Widawsky Tested-by: Stéphane Marchesin Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_reg.h | 18 ++++++++++++++++ drivers/gpu/drm/i915/intel_display.c | 40 ++++++++++++++++++++++++++++-------- 2 files changed, 49 insertions(+), 9 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b6a58f720f9a..b2fa2a4c4454 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -245,6 +245,7 @@ * address/value pairs. Don't overdue it, though, x <= 2^4 must hold! */ #define MI_LOAD_REGISTER_IMM(x) MI_INSTR(0x22, 2*x-1) +#define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*x-1) #define MI_FLUSH_DW MI_INSTR(0x26, 1) /* for GEN6 */ #define MI_FLUSH_DW_STORE_INDEX (1<<21) #define MI_INVALIDATE_TLB (1<<18) @@ -693,6 +694,23 @@ #define FPGA_DBG_RM_NOCLAIM (1<<31) #define DERRMR 0x44050 +#define DERRMR_PIPEA_SCANLINE (1<<0) +#define DERRMR_PIPEA_PRI_FLIP_DONE (1<<1) +#define DERRMR_PIPEA_SPR_FLIP_DONE (1<<2) +#define DERRMR_PIPEA_VBLANK (1<<3) +#define DERRMR_PIPEA_HBLANK (1<<5) +#define DERRMR_PIPEB_SCANLINE (1<<8) +#define DERRMR_PIPEB_PRI_FLIP_DONE (1<<9) +#define DERRMR_PIPEB_SPR_FLIP_DONE (1<<10) +#define DERRMR_PIPEB_VBLANK (1<<11) +#define DERRMR_PIPEB_HBLANK (1<<13) +/* Note that PIPEC is not a simple translation of PIPEA/PIPEB */ +#define DERRMR_PIPEC_SCANLINE (1<<14) +#define DERRMR_PIPEC_PRI_FLIP_DONE (1<<15) +#define DERRMR_PIPEC_SPR_FLIP_DONE (1<<20) +#define DERRMR_PIPEC_VBLANK (1<<21) +#define DERRMR_PIPEC_HBLANK (1<<22) + /* GM45+ chicken bits -- debug workaround bits that may be required * for various sorts of correct behavior. The top 16 bits of each are diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 38452d82ac7d..a98392f9894e 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -7828,12 +7828,6 @@ err: return ret; } -/* - * On gen7 we currently use the blit ring because (in early silicon at least) - * the render ring doesn't give us interrpts for page flip completion, which - * means clients will hang after the first flip is queued. Fortunately the - * blit ring generates interrupts properly, so use it instead. - */ static int intel_gen7_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, @@ -7842,9 +7836,13 @@ static int intel_gen7_queue_flip(struct drm_device *dev, { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_ring_buffer *ring = &dev_priv->ring[BCS]; + struct intel_ring_buffer *ring; uint32_t plane_bit = 0; - int ret; + int len, ret; + + ring = obj->ring; + if (ring == NULL || ring->id != RCS) + ring = &dev_priv->ring[BCS]; ret = intel_pin_and_fence_fb_obj(dev, obj, ring); if (ret) @@ -7866,10 +7864,34 @@ static int intel_gen7_queue_flip(struct drm_device *dev, goto err_unpin; } - ret = intel_ring_begin(ring, 4); + len = 4; + if (ring->id == RCS) + len += 6; + + ret = intel_ring_begin(ring, len); if (ret) goto err_unpin; + /* Unmask the flip-done completion message. Note that the bspec says that + * we should do this for both the BCS and RCS, and that we must not unmask + * more than one flip event at any time (or ensure that one flip message + * can be sent by waiting for flip-done prior to queueing new flips). + * Experimentation says that BCS works despite DERRMR masking all + * flip-done completion events and that unmasking all planes at once + * for the RCS also doesn't appear to drop events. Setting the DERRMR + * to zero does lead to lockups within MI_DISPLAY_FLIP. + */ + if (ring->id == RCS) { + intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1)); + intel_ring_emit(ring, DERRMR); + intel_ring_emit(ring, ~(DERRMR_PIPEA_PRI_FLIP_DONE | + DERRMR_PIPEB_PRI_FLIP_DONE | + DERRMR_PIPEC_PRI_FLIP_DONE)); + intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1)); + intel_ring_emit(ring, DERRMR); + intel_ring_emit(ring, ring->scratch.gtt_offset + 256); + } + intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit); intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode)); intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); -- cgit v1.2.3-70-g09d2 From fac15c108248e8d592fb8f4cbcf26d98b3485526 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 29 Aug 2013 13:11:07 -0700 Subject: i915_gem: Convert kmem_cache_alloc(...GFP_ZERO) to kmem_cache_zalloc The helper exists, might as well use it instead of __GFP_ZERO. Signed-off-by: Joe Perches Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 2d1cb10d846f..61313054fce6 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -212,7 +212,7 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, void *i915_gem_object_alloc(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - return kmem_cache_alloc(dev_priv->slab, GFP_KERNEL | __GFP_ZERO); + return kmem_cache_zalloc(dev_priv->slab, GFP_KERNEL); } void i915_gem_object_free(struct drm_i915_gem_object *obj) -- cgit v1.2.3-70-g09d2 From a0a1807544fe59b42d3760ee912ea4c6741298f5 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Fri, 26 Jul 2013 13:32:51 -0700 Subject: drm/i915: split PCI IDs out into i915_drm.h v4 For use by userspace (at some point in the future) and other kernel code. v2: move PCI IDs to uabi (Chris) move PCI IDs to drm/ (Dave) v3: fixup Quanta detection - needs to come first (Daniel) v4: fix up PCI match structure init for easier use by userspace (Chris) Signed-off-by: Jesse Barnes Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_drv.c | 164 +++++++------------------------ include/drm/i915_drm.h | 2 + include/drm/i915_pciids.h | 211 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 247 insertions(+), 130 deletions(-) create mode 100644 include/drm/i915_pciids.h (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index ccb28ead3501..69d8ed5416c3 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -157,25 +157,6 @@ MODULE_PARM_DESC(prefault_disable, static struct drm_driver driver; extern int intel_agp_enabled; -#define INTEL_VGA_DEVICE(id, info) { \ - .class = PCI_BASE_CLASS_DISPLAY << 16, \ - .class_mask = 0xff0000, \ - .vendor = 0x8086, \ - .device = id, \ - .subvendor = PCI_ANY_ID, \ - .subdevice = PCI_ANY_ID, \ - .driver_data = (unsigned long) info } - -#define INTEL_QUANTA_VGA_DEVICE(info) { \ - .class = PCI_BASE_CLASS_DISPLAY << 16, \ - .class_mask = 0xff0000, \ - .vendor = 0x8086, \ - .device = 0x16a, \ - .subvendor = 0x152d, \ - .subdevice = 0x8990, \ - .driver_data = (unsigned long) info } - - static const struct intel_device_info intel_i830_info = { .gen = 2, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2, .has_overlay = 1, .overlay_needs_physical = 1, @@ -350,118 +331,41 @@ static const struct intel_device_info intel_haswell_m_info = { .has_vebox_ring = 1, }; +/* + * Make sure any device matches here are from most specific to most + * general. For example, since the Quanta match is based on the subsystem + * and subvendor IDs, we need it to come before the more general IVB + * PCI ID matches, otherwise we'll use the wrong info struct above. + */ +#define INTEL_PCI_IDS \ + INTEL_I830_IDS(&intel_i830_info), \ + INTEL_I845G_IDS(&intel_845g_info), \ + INTEL_I85X_IDS(&intel_i85x_info), \ + INTEL_I865G_IDS(&intel_i865g_info), \ + INTEL_I915G_IDS(&intel_i915g_info), \ + INTEL_I915GM_IDS(&intel_i915gm_info), \ + INTEL_I945G_IDS(&intel_i945g_info), \ + INTEL_I945GM_IDS(&intel_i945gm_info), \ + INTEL_I965G_IDS(&intel_i965g_info), \ + INTEL_G33_IDS(&intel_g33_info), \ + INTEL_I965GM_IDS(&intel_i965gm_info), \ + INTEL_GM45_IDS(&intel_gm45_info), \ + INTEL_G45_IDS(&intel_g45_info), \ + INTEL_PINEVIEW_IDS(&intel_pineview_info), \ + INTEL_IRONLAKE_D_IDS(&intel_ironlake_d_info), \ + INTEL_IRONLAKE_M_IDS(&intel_ironlake_m_info), \ + INTEL_SNB_D_IDS(&intel_sandybridge_d_info), \ + INTEL_SNB_M_IDS(&intel_sandybridge_m_info), \ + INTEL_IVB_Q_IDS(&intel_ivybridge_q_info), /* must be first IVB */ \ + INTEL_IVB_M_IDS(&intel_ivybridge_m_info), \ + INTEL_IVB_D_IDS(&intel_ivybridge_d_info), \ + INTEL_HSW_D_IDS(&intel_haswell_d_info), \ + INTEL_HSW_M_IDS(&intel_haswell_m_info), \ + INTEL_VLV_M_IDS(&intel_valleyview_m_info), \ + INTEL_VLV_D_IDS(&intel_valleyview_d_info) + static const struct pci_device_id pciidlist[] = { /* aka */ - INTEL_VGA_DEVICE(0x3577, &intel_i830_info), /* I830_M */ - INTEL_VGA_DEVICE(0x2562, &intel_845g_info), /* 845_G */ - INTEL_VGA_DEVICE(0x3582, &intel_i85x_info), /* I855_GM */ - INTEL_VGA_DEVICE(0x358e, &intel_i85x_info), - INTEL_VGA_DEVICE(0x2572, &intel_i865g_info), /* I865_G */ - INTEL_VGA_DEVICE(0x2582, &intel_i915g_info), /* I915_G */ - INTEL_VGA_DEVICE(0x258a, &intel_i915g_info), /* E7221_G */ - INTEL_VGA_DEVICE(0x2592, &intel_i915gm_info), /* I915_GM */ - INTEL_VGA_DEVICE(0x2772, &intel_i945g_info), /* I945_G */ - INTEL_VGA_DEVICE(0x27a2, &intel_i945gm_info), /* I945_GM */ - INTEL_VGA_DEVICE(0x27ae, &intel_i945gm_info), /* I945_GME */ - INTEL_VGA_DEVICE(0x2972, &intel_i965g_info), /* I946_GZ */ - INTEL_VGA_DEVICE(0x2982, &intel_i965g_info), /* G35_G */ - INTEL_VGA_DEVICE(0x2992, &intel_i965g_info), /* I965_Q */ - INTEL_VGA_DEVICE(0x29a2, &intel_i965g_info), /* I965_G */ - INTEL_VGA_DEVICE(0x29b2, &intel_g33_info), /* Q35_G */ - INTEL_VGA_DEVICE(0x29c2, &intel_g33_info), /* G33_G */ - INTEL_VGA_DEVICE(0x29d2, &intel_g33_info), /* Q33_G */ - INTEL_VGA_DEVICE(0x2a02, &intel_i965gm_info), /* I965_GM */ - INTEL_VGA_DEVICE(0x2a12, &intel_i965gm_info), /* I965_GME */ - INTEL_VGA_DEVICE(0x2a42, &intel_gm45_info), /* GM45_G */ - INTEL_VGA_DEVICE(0x2e02, &intel_g45_info), /* IGD_E_G */ - INTEL_VGA_DEVICE(0x2e12, &intel_g45_info), /* Q45_G */ - INTEL_VGA_DEVICE(0x2e22, &intel_g45_info), /* G45_G */ - INTEL_VGA_DEVICE(0x2e32, &intel_g45_info), /* G41_G */ - INTEL_VGA_DEVICE(0x2e42, &intel_g45_info), /* B43_G */ - INTEL_VGA_DEVICE(0x2e92, &intel_g45_info), /* B43_G.1 */ - INTEL_VGA_DEVICE(0xa001, &intel_pineview_info), - INTEL_VGA_DEVICE(0xa011, &intel_pineview_info), - INTEL_VGA_DEVICE(0x0042, &intel_ironlake_d_info), - INTEL_VGA_DEVICE(0x0046, &intel_ironlake_m_info), - INTEL_VGA_DEVICE(0x0102, &intel_sandybridge_d_info), - INTEL_VGA_DEVICE(0x0112, &intel_sandybridge_d_info), - INTEL_VGA_DEVICE(0x0122, &intel_sandybridge_d_info), - INTEL_VGA_DEVICE(0x0106, &intel_sandybridge_m_info), - INTEL_VGA_DEVICE(0x0116, &intel_sandybridge_m_info), - INTEL_VGA_DEVICE(0x0126, &intel_sandybridge_m_info), - INTEL_VGA_DEVICE(0x010A, &intel_sandybridge_d_info), - INTEL_VGA_DEVICE(0x0156, &intel_ivybridge_m_info), /* GT1 mobile */ - INTEL_VGA_DEVICE(0x0166, &intel_ivybridge_m_info), /* GT2 mobile */ - INTEL_VGA_DEVICE(0x0152, &intel_ivybridge_d_info), /* GT1 desktop */ - INTEL_VGA_DEVICE(0x0162, &intel_ivybridge_d_info), /* GT2 desktop */ - INTEL_VGA_DEVICE(0x015a, &intel_ivybridge_d_info), /* GT1 server */ - INTEL_QUANTA_VGA_DEVICE(&intel_ivybridge_q_info), /* Quanta transcode */ - INTEL_VGA_DEVICE(0x016a, &intel_ivybridge_d_info), /* GT2 server */ - INTEL_VGA_DEVICE(0x0402, &intel_haswell_d_info), /* GT1 desktop */ - INTEL_VGA_DEVICE(0x0412, &intel_haswell_d_info), /* GT2 desktop */ - INTEL_VGA_DEVICE(0x0422, &intel_haswell_d_info), /* GT3 desktop */ - INTEL_VGA_DEVICE(0x040a, &intel_haswell_d_info), /* GT1 server */ - INTEL_VGA_DEVICE(0x041a, &intel_haswell_d_info), /* GT2 server */ - INTEL_VGA_DEVICE(0x042a, &intel_haswell_d_info), /* GT3 server */ - INTEL_VGA_DEVICE(0x0406, &intel_haswell_m_info), /* GT1 mobile */ - INTEL_VGA_DEVICE(0x0416, &intel_haswell_m_info), /* GT2 mobile */ - INTEL_VGA_DEVICE(0x0426, &intel_haswell_m_info), /* GT2 mobile */ - INTEL_VGA_DEVICE(0x040B, &intel_haswell_d_info), /* GT1 reserved */ - INTEL_VGA_DEVICE(0x041B, &intel_haswell_d_info), /* GT2 reserved */ - INTEL_VGA_DEVICE(0x042B, &intel_haswell_d_info), /* GT3 reserved */ - INTEL_VGA_DEVICE(0x040E, &intel_haswell_d_info), /* GT1 reserved */ - INTEL_VGA_DEVICE(0x041E, &intel_haswell_d_info), /* GT2 reserved */ - INTEL_VGA_DEVICE(0x042E, &intel_haswell_d_info), /* GT3 reserved */ - INTEL_VGA_DEVICE(0x0C02, &intel_haswell_d_info), /* SDV GT1 desktop */ - INTEL_VGA_DEVICE(0x0C12, &intel_haswell_d_info), /* SDV GT2 desktop */ - INTEL_VGA_DEVICE(0x0C22, &intel_haswell_d_info), /* SDV GT3 desktop */ - INTEL_VGA_DEVICE(0x0C0A, &intel_haswell_d_info), /* SDV GT1 server */ - INTEL_VGA_DEVICE(0x0C1A, &intel_haswell_d_info), /* SDV GT2 server */ - INTEL_VGA_DEVICE(0x0C2A, &intel_haswell_d_info), /* SDV GT3 server */ - INTEL_VGA_DEVICE(0x0C06, &intel_haswell_m_info), /* SDV GT1 mobile */ - INTEL_VGA_DEVICE(0x0C16, &intel_haswell_m_info), /* SDV GT2 mobile */ - INTEL_VGA_DEVICE(0x0C26, &intel_haswell_m_info), /* SDV GT3 mobile */ - INTEL_VGA_DEVICE(0x0C0B, &intel_haswell_d_info), /* SDV GT1 reserved */ - INTEL_VGA_DEVICE(0x0C1B, &intel_haswell_d_info), /* SDV GT2 reserved */ - INTEL_VGA_DEVICE(0x0C2B, &intel_haswell_d_info), /* SDV GT3 reserved */ - INTEL_VGA_DEVICE(0x0C0E, &intel_haswell_d_info), /* SDV GT1 reserved */ - INTEL_VGA_DEVICE(0x0C1E, &intel_haswell_d_info), /* SDV GT2 reserved */ - INTEL_VGA_DEVICE(0x0C2E, &intel_haswell_d_info), /* SDV GT3 reserved */ - INTEL_VGA_DEVICE(0x0A02, &intel_haswell_d_info), /* ULT GT1 desktop */ - INTEL_VGA_DEVICE(0x0A12, &intel_haswell_d_info), /* ULT GT2 desktop */ - INTEL_VGA_DEVICE(0x0A22, &intel_haswell_d_info), /* ULT GT3 desktop */ - INTEL_VGA_DEVICE(0x0A0A, &intel_haswell_d_info), /* ULT GT1 server */ - INTEL_VGA_DEVICE(0x0A1A, &intel_haswell_d_info), /* ULT GT2 server */ - INTEL_VGA_DEVICE(0x0A2A, &intel_haswell_d_info), /* ULT GT3 server */ - INTEL_VGA_DEVICE(0x0A06, &intel_haswell_m_info), /* ULT GT1 mobile */ - INTEL_VGA_DEVICE(0x0A16, &intel_haswell_m_info), /* ULT GT2 mobile */ - INTEL_VGA_DEVICE(0x0A26, &intel_haswell_m_info), /* ULT GT3 mobile */ - INTEL_VGA_DEVICE(0x0A0B, &intel_haswell_d_info), /* ULT GT1 reserved */ - INTEL_VGA_DEVICE(0x0A1B, &intel_haswell_d_info), /* ULT GT2 reserved */ - INTEL_VGA_DEVICE(0x0A2B, &intel_haswell_d_info), /* ULT GT3 reserved */ - INTEL_VGA_DEVICE(0x0A0E, &intel_haswell_m_info), /* ULT GT1 reserved */ - INTEL_VGA_DEVICE(0x0A1E, &intel_haswell_m_info), /* ULT GT2 reserved */ - INTEL_VGA_DEVICE(0x0A2E, &intel_haswell_m_info), /* ULT GT3 reserved */ - INTEL_VGA_DEVICE(0x0D02, &intel_haswell_d_info), /* CRW GT1 desktop */ - INTEL_VGA_DEVICE(0x0D12, &intel_haswell_d_info), /* CRW GT2 desktop */ - INTEL_VGA_DEVICE(0x0D22, &intel_haswell_d_info), /* CRW GT3 desktop */ - INTEL_VGA_DEVICE(0x0D0A, &intel_haswell_d_info), /* CRW GT1 server */ - INTEL_VGA_DEVICE(0x0D1A, &intel_haswell_d_info), /* CRW GT2 server */ - INTEL_VGA_DEVICE(0x0D2A, &intel_haswell_d_info), /* CRW GT3 server */ - INTEL_VGA_DEVICE(0x0D06, &intel_haswell_m_info), /* CRW GT1 mobile */ - INTEL_VGA_DEVICE(0x0D16, &intel_haswell_m_info), /* CRW GT2 mobile */ - INTEL_VGA_DEVICE(0x0D26, &intel_haswell_m_info), /* CRW GT3 mobile */ - INTEL_VGA_DEVICE(0x0D0B, &intel_haswell_d_info), /* CRW GT1 reserved */ - INTEL_VGA_DEVICE(0x0D1B, &intel_haswell_d_info), /* CRW GT2 reserved */ - INTEL_VGA_DEVICE(0x0D2B, &intel_haswell_d_info), /* CRW GT3 reserved */ - INTEL_VGA_DEVICE(0x0D0E, &intel_haswell_d_info), /* CRW GT1 reserved */ - INTEL_VGA_DEVICE(0x0D1E, &intel_haswell_d_info), /* CRW GT2 reserved */ - INTEL_VGA_DEVICE(0x0D2E, &intel_haswell_d_info), /* CRW GT3 reserved */ - INTEL_VGA_DEVICE(0x0f30, &intel_valleyview_m_info), - INTEL_VGA_DEVICE(0x0f31, &intel_valleyview_m_info), - INTEL_VGA_DEVICE(0x0f32, &intel_valleyview_m_info), - INTEL_VGA_DEVICE(0x0f33, &intel_valleyview_m_info), - INTEL_VGA_DEVICE(0x0157, &intel_valleyview_m_info), - INTEL_VGA_DEVICE(0x0155, &intel_valleyview_d_info), + INTEL_PCI_IDS, {0, 0, 0} }; diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index 63d609d8a3f6..7276a72710e2 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -26,6 +26,7 @@ #ifndef _I915_DRM_H_ #define _I915_DRM_H_ +#include #include /* For use by IPS driver */ @@ -34,4 +35,5 @@ extern bool i915_gpu_raise(void); extern bool i915_gpu_lower(void); extern bool i915_gpu_busy(void); extern bool i915_gpu_turbo_disable(void); + #endif /* _I915_DRM_H_ */ diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h new file mode 100644 index 000000000000..8a10f5c354e6 --- /dev/null +++ b/include/drm/i915_pciids.h @@ -0,0 +1,211 @@ +/* + * Copyright 2013 Intel Corporation + * 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 NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS 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. + */ +#ifndef _I915_PCIIDS_H +#define _I915_PCIIDS_H + +/* + * A pci_device_id struct { + * __u32 vendor, device; + * __u32 subvendor, subdevice; + * __u32 class, class_mask; + * kernel_ulong_t driver_data; + * }; + * Don't use C99 here because "class" is reserved and we want to + * give userspace flexibility. + */ +#define INTEL_VGA_DEVICE(id, info) { \ + 0x8086, id, \ + ~0, ~0, \ + 0x030000, 0xff0000, \ + (unsigned long) info } + +#define INTEL_QUANTA_VGA_DEVICE(info) { \ + 0x8086, 0x16a, \ + 0x152d, 0x8990, \ + 0x030000, 0xff0000, \ + (unsigned long) info } + +#define INTEL_I830_IDS(info) \ + INTEL_VGA_DEVICE(0x3577, info) + +#define INTEL_I845G_IDS(info) \ + INTEL_VGA_DEVICE(0x2562, info) + +#define INTEL_I85X_IDS(info) \ + INTEL_VGA_DEVICE(0x3582, info), /* I855_GM */ \ + INTEL_VGA_DEVICE(0x358e, info) + +#define INTEL_I865G_IDS(info) \ + INTEL_VGA_DEVICE(0x2572, info) /* I865_G */ + +#define INTEL_I915G_IDS(info) \ + INTEL_VGA_DEVICE(0x2582, info), /* I915_G */ \ + INTEL_VGA_DEVICE(0x258a, info) /* E7221_G */ + +#define INTEL_I915GM_IDS(info) \ + INTEL_VGA_DEVICE(0x2592, info) /* I915_GM */ + +#define INTEL_I945G_IDS(info) \ + INTEL_VGA_DEVICE(0x2772, info) /* I945_G */ + +#define INTEL_I945GM_IDS(info) \ + INTEL_VGA_DEVICE(0x27a2, info), /* I945_GM */ \ + INTEL_VGA_DEVICE(0x27ae, info) /* I945_GME */ + +#define INTEL_I965G_IDS(info) \ + INTEL_VGA_DEVICE(0x2972, info), /* I946_GZ */ \ + INTEL_VGA_DEVICE(0x2982, info), /* G35_G */ \ + INTEL_VGA_DEVICE(0x2992, info), /* I965_Q */ \ + INTEL_VGA_DEVICE(0x29a2, info) /* I965_G */ + +#define INTEL_G33_IDS(info) \ + INTEL_VGA_DEVICE(0x29b2, info), /* Q35_G */ \ + INTEL_VGA_DEVICE(0x29c2, info), /* G33_G */ \ + INTEL_VGA_DEVICE(0x29d2, info) /* Q33_G */ + +#define INTEL_I965GM_IDS(info) \ + INTEL_VGA_DEVICE(0x2a02, info), /* I965_GM */ \ + INTEL_VGA_DEVICE(0x2a12, info) /* I965_GME */ + +#define INTEL_GM45_IDS(info) \ + INTEL_VGA_DEVICE(0x2a42, info) /* GM45_G */ + +#define INTEL_G45_IDS(info) \ + INTEL_VGA_DEVICE(0x2e02, info), /* IGD_E_G */ \ + INTEL_VGA_DEVICE(0x2e12, info), /* Q45_G */ \ + INTEL_VGA_DEVICE(0x2e22, info), /* G45_G */ \ + INTEL_VGA_DEVICE(0x2e32, info), /* G41_G */ \ + INTEL_VGA_DEVICE(0x2e42, info), /* B43_G */ \ + INTEL_VGA_DEVICE(0x2e92, info) /* B43_G.1 */ + +#define INTEL_PINEVIEW_IDS(info) \ + INTEL_VGA_DEVICE(0xa001, info), \ + INTEL_VGA_DEVICE(0xa011, info) + +#define INTEL_IRONLAKE_D_IDS(info) \ + INTEL_VGA_DEVICE(0x0042, info) + +#define INTEL_IRONLAKE_M_IDS(info) \ + INTEL_VGA_DEVICE(0x0046, info) + +#define INTEL_SNB_D_IDS(info) \ + INTEL_VGA_DEVICE(0x0102, info), \ + INTEL_VGA_DEVICE(0x0112, info), \ + INTEL_VGA_DEVICE(0x0122, info), \ + INTEL_VGA_DEVICE(0x010A, info) + +#define INTEL_SNB_M_IDS(info) \ + INTEL_VGA_DEVICE(0x0106, info), \ + INTEL_VGA_DEVICE(0x0116, info), \ + INTEL_VGA_DEVICE(0x0126, info) + +#define INTEL_IVB_M_IDS(info) \ + INTEL_VGA_DEVICE(0x0156, info), /* GT1 mobile */ \ + INTEL_VGA_DEVICE(0x0166, info) /* GT2 mobile */ + +#define INTEL_IVB_D_IDS(info) \ + INTEL_VGA_DEVICE(0x0152, info), /* GT1 desktop */ \ + INTEL_VGA_DEVICE(0x0162, info), /* GT2 desktop */ \ + INTEL_VGA_DEVICE(0x015a, info), /* GT1 server */ \ + INTEL_VGA_DEVICE(0x016a, info) /* GT2 server */ + +#define INTEL_IVB_Q_IDS(info) \ + INTEL_QUANTA_VGA_DEVICE(info) /* Quanta transcode */ + +#define INTEL_HSW_D_IDS(info) \ + INTEL_VGA_DEVICE(0x0402, info), /* GT1 desktop */ \ + INTEL_VGA_DEVICE(0x0412, info), /* GT2 desktop */ \ + INTEL_VGA_DEVICE(0x0422, info), /* GT3 desktop */ \ + INTEL_VGA_DEVICE(0x040a, info), /* GT1 server */ \ + INTEL_VGA_DEVICE(0x041a, info), /* GT2 server */ \ + INTEL_VGA_DEVICE(0x042a, info), /* GT3 server */ \ + INTEL_VGA_DEVICE(0x040B, info), /* GT1 reserved */ \ + INTEL_VGA_DEVICE(0x041B, info), /* GT2 reserved */ \ + INTEL_VGA_DEVICE(0x042B, info), /* GT3 reserved */ \ + INTEL_VGA_DEVICE(0x040E, info), /* GT1 reserved */ \ + INTEL_VGA_DEVICE(0x041E, info), /* GT2 reserved */ \ + INTEL_VGA_DEVICE(0x042E, info), /* GT3 reserved */ \ + INTEL_VGA_DEVICE(0x0C02, info), /* SDV GT1 desktop */ \ + INTEL_VGA_DEVICE(0x0C12, info), /* SDV GT2 desktop */ \ + INTEL_VGA_DEVICE(0x0C22, info), /* SDV GT3 desktop */ \ + INTEL_VGA_DEVICE(0x0C0A, info), /* SDV GT1 server */ \ + INTEL_VGA_DEVICE(0x0C1A, info), /* SDV GT2 server */ \ + INTEL_VGA_DEVICE(0x0C2A, info), /* SDV GT3 server */ \ + INTEL_VGA_DEVICE(0x0C0B, info), /* SDV GT1 reserved */ \ + INTEL_VGA_DEVICE(0x0C1B, info), /* SDV GT2 reserved */ \ + INTEL_VGA_DEVICE(0x0C2B, info), /* SDV GT3 reserved */ \ + INTEL_VGA_DEVICE(0x0C0E, info), /* SDV GT1 reserved */ \ + INTEL_VGA_DEVICE(0x0C1E, info), /* SDV GT2 reserved */ \ + INTEL_VGA_DEVICE(0x0C2E, info), /* SDV GT3 reserved */ \ + INTEL_VGA_DEVICE(0x0A02, info), /* ULT GT1 desktop */ \ + INTEL_VGA_DEVICE(0x0A12, info), /* ULT GT2 desktop */ \ + INTEL_VGA_DEVICE(0x0A22, info), /* ULT GT3 desktop */ \ + INTEL_VGA_DEVICE(0x0A0A, info), /* ULT GT1 server */ \ + INTEL_VGA_DEVICE(0x0A1A, info), /* ULT GT2 server */ \ + INTEL_VGA_DEVICE(0x0A2A, info), /* ULT GT3 server */ \ + INTEL_VGA_DEVICE(0x0A0B, info), /* ULT GT1 reserved */ \ + INTEL_VGA_DEVICE(0x0A1B, info), /* ULT GT2 reserved */ \ + INTEL_VGA_DEVICE(0x0A2B, info), /* ULT GT3 reserved */ \ + INTEL_VGA_DEVICE(0x0D02, info), /* CRW GT1 desktop */ \ + INTEL_VGA_DEVICE(0x0D12, info), /* CRW GT2 desktop */ \ + INTEL_VGA_DEVICE(0x0D22, info), /* CRW GT3 desktop */ \ + INTEL_VGA_DEVICE(0x0D0A, info), /* CRW GT1 server */ \ + INTEL_VGA_DEVICE(0x0D1A, info), /* CRW GT2 server */ \ + INTEL_VGA_DEVICE(0x0D2A, info), /* CRW GT3 server */ \ + INTEL_VGA_DEVICE(0x0D0B, info), /* CRW GT1 reserved */ \ + INTEL_VGA_DEVICE(0x0D1B, info), /* CRW GT2 reserved */ \ + INTEL_VGA_DEVICE(0x0D2B, info), /* CRW GT3 reserved */ \ + INTEL_VGA_DEVICE(0x0D0E, info), /* CRW GT1 reserved */ \ + INTEL_VGA_DEVICE(0x0D1E, info), /* CRW GT2 reserved */ \ + INTEL_VGA_DEVICE(0x0D2E, info) /* CRW GT3 reserved */ \ + +#define INTEL_HSW_M_IDS(info) \ + INTEL_VGA_DEVICE(0x0406, info), /* GT1 mobile */ \ + INTEL_VGA_DEVICE(0x0416, info), /* GT2 mobile */ \ + INTEL_VGA_DEVICE(0x0426, info), /* GT2 mobile */ \ + INTEL_VGA_DEVICE(0x0C06, info), /* SDV GT1 mobile */ \ + INTEL_VGA_DEVICE(0x0C16, info), /* SDV GT2 mobile */ \ + INTEL_VGA_DEVICE(0x0C26, info), /* SDV GT3 mobile */ \ + INTEL_VGA_DEVICE(0x0A06, info), /* ULT GT1 mobile */ \ + INTEL_VGA_DEVICE(0x0A16, info), /* ULT GT2 mobile */ \ + INTEL_VGA_DEVICE(0x0A26, info), /* ULT GT3 mobile */ \ + INTEL_VGA_DEVICE(0x0A0E, info), /* ULT GT1 reserved */ \ + INTEL_VGA_DEVICE(0x0A1E, info), /* ULT GT2 reserved */ \ + INTEL_VGA_DEVICE(0x0A2E, info), /* ULT GT3 reserved */ \ + INTEL_VGA_DEVICE(0x0D06, info), /* CRW GT1 mobile */ \ + INTEL_VGA_DEVICE(0x0D16, info), /* CRW GT2 mobile */ \ + INTEL_VGA_DEVICE(0x0D26, info) /* CRW GT3 mobile */ + +#define INTEL_VLV_M_IDS(info) \ + INTEL_VGA_DEVICE(0x0f30, info), \ + INTEL_VGA_DEVICE(0x0f31, info), \ + INTEL_VGA_DEVICE(0x0f32, info), \ + INTEL_VGA_DEVICE(0x0f33, info), \ + INTEL_VGA_DEVICE(0x0157, info) + +#define INTEL_VLV_D_IDS(info) \ + INTEL_VGA_DEVICE(0x0155, info) + +#endif /* _I915_PCIIDS_H */ -- cgit v1.2.3-70-g09d2 From 814c5f1f52a4beb3710317022acd6ad34fc0b6b9 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Fri, 26 Jul 2013 13:32:52 -0700 Subject: x86: add early quirk for reserving Intel graphics stolen memory v5 Systems with Intel graphics controllers set aside memory exclusively for gfx driver use. This memory is not always marked in the E820 as reserved or as RAM, and so is subject to overlap from E820 manipulation later in the boot process. On some systems, MMIO space is allocated on top, despite the efforts of the "RAM buffer" approach, which simply rounds memory boundaries up to 64M to try to catch space that may decode as RAM and so is not suitable for MMIO. v2: use read_pci_config for 32 bit reads instead of adding a new one (Chris) add gen6 stolen size function (Chris) v3: use a function pointer (Chris) drop gen2 bits (Daniel) v4: call e820_sanitize_map after adding the region v5: fixup comments (Peter) simplify loop (Chris) Acked-by: Ingo Molnar Signed-off-by: Jesse Barnes Acked-by: H. Peter Anvin Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=66726 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=66844 Signed-off-by: Daniel Vetter --- arch/x86/kernel/early-quirks.c | 154 ++++++++++++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/i915_reg.h | 15 ---- include/drm/i915_drm.h | 32 +++++++++ 3 files changed, 186 insertions(+), 15 deletions(-) (limited to 'drivers/gpu') diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 63bdb29b2549..b3cd3ebae077 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -216,6 +217,157 @@ static void __init intel_remapping_check(int num, int slot, int func) } +/* + * Systems with Intel graphics controllers set aside memory exclusively + * for gfx driver use. This memory is not marked in the E820 as reserved + * or as RAM, and so is subject to overlap from E820 manipulation later + * in the boot process. On some systems, MMIO space is allocated on top, + * despite the efforts of the "RAM buffer" approach, which simply rounds + * memory boundaries up to 64M to try to catch space that may decode + * as RAM and so is not suitable for MMIO. + * + * And yes, so far on current devices the base addr is always under 4G. + */ +static u32 __init intel_stolen_base(int num, int slot, int func) +{ + u32 base; + + /* + * For the PCI IDs in this quirk, the stolen base is always + * in 0x5c, aka the BDSM register (yes that's really what + * it's called). + */ + base = read_pci_config(num, slot, func, 0x5c); + base &= ~((1<<20) - 1); + + return base; +} + +#define KB(x) ((x) * 1024) +#define MB(x) (KB (KB (x))) +#define GB(x) (MB (KB (x))) + +static size_t __init gen3_stolen_size(int num, int slot, int func) +{ + size_t stolen_size; + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL); + + switch (gmch_ctrl & I855_GMCH_GMS_MASK) { + case I855_GMCH_GMS_STOLEN_1M: + stolen_size = MB(1); + break; + case I855_GMCH_GMS_STOLEN_4M: + stolen_size = MB(4); + break; + case I855_GMCH_GMS_STOLEN_8M: + stolen_size = MB(8); + break; + case I855_GMCH_GMS_STOLEN_16M: + stolen_size = MB(16); + break; + case I855_GMCH_GMS_STOLEN_32M: + stolen_size = MB(32); + break; + case I915_GMCH_GMS_STOLEN_48M: + stolen_size = MB(48); + break; + case I915_GMCH_GMS_STOLEN_64M: + stolen_size = MB(64); + break; + case G33_GMCH_GMS_STOLEN_128M: + stolen_size = MB(128); + break; + case G33_GMCH_GMS_STOLEN_256M: + stolen_size = MB(256); + break; + case INTEL_GMCH_GMS_STOLEN_96M: + stolen_size = MB(96); + break; + case INTEL_GMCH_GMS_STOLEN_160M: + stolen_size = MB(160); + break; + case INTEL_GMCH_GMS_STOLEN_224M: + stolen_size = MB(224); + break; + case INTEL_GMCH_GMS_STOLEN_352M: + stolen_size = MB(352); + break; + default: + stolen_size = 0; + break; + } + + return stolen_size; +} + +static size_t __init gen6_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GMS_MASK; + + return gmch_ctrl << 25; /* 32 MB units */ +} + +typedef size_t (*stolen_size_fn)(int num, int slot, int func); + +static struct pci_device_id intel_stolen_ids[] __initdata = { + INTEL_I915G_IDS(gen3_stolen_size), + INTEL_I915GM_IDS(gen3_stolen_size), + INTEL_I945G_IDS(gen3_stolen_size), + INTEL_I945GM_IDS(gen3_stolen_size), + INTEL_VLV_M_IDS(gen3_stolen_size), + INTEL_VLV_D_IDS(gen3_stolen_size), + INTEL_PINEVIEW_IDS(gen3_stolen_size), + INTEL_I965G_IDS(gen3_stolen_size), + INTEL_G33_IDS(gen3_stolen_size), + INTEL_I965GM_IDS(gen3_stolen_size), + INTEL_GM45_IDS(gen3_stolen_size), + INTEL_G45_IDS(gen3_stolen_size), + INTEL_IRONLAKE_D_IDS(gen3_stolen_size), + INTEL_IRONLAKE_M_IDS(gen3_stolen_size), + INTEL_SNB_D_IDS(gen6_stolen_size), + INTEL_SNB_M_IDS(gen6_stolen_size), + INTEL_IVB_M_IDS(gen6_stolen_size), + INTEL_IVB_D_IDS(gen6_stolen_size), + INTEL_HSW_D_IDS(gen6_stolen_size), + INTEL_HSW_M_IDS(gen6_stolen_size), +}; + +static void __init intel_graphics_stolen(int num, int slot, int func) +{ + size_t size; + int i; + u32 start; + u16 device, subvendor, subdevice; + + device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID); + subvendor = read_pci_config_16(num, slot, func, + PCI_SUBSYSTEM_VENDOR_ID); + subdevice = read_pci_config_16(num, slot, func, PCI_SUBSYSTEM_ID); + + for (i = 0; i < ARRAY_SIZE(intel_stolen_ids); i++) { + if (intel_stolen_ids[i].device == device) { + stolen_size_fn stolen_size = + (stolen_size_fn)intel_stolen_ids[i].driver_data; + size = stolen_size(num, slot, func); + start = intel_stolen_base(num, slot, func); + if (size && start) { + /* Mark this space as reserved */ + e820_add_region(start, size, E820_RESERVED); + sanitize_e820_map(e820.map, + ARRAY_SIZE(e820.map), + &e820.nr_map); + } + return; + } + } +} + #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 #define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED) @@ -251,6 +403,8 @@ static struct chipset early_qrk[] __initdata = { PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, { PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, + { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID, + QFLAG_APPLY_ONCE, intel_graphics_stolen }, {} }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b2fa2a4c4454..dcc58ea157fe 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -33,21 +33,6 @@ #define _MASKED_BIT_ENABLE(a) (((a) << 16) | (a)) #define _MASKED_BIT_DISABLE(a) ((a) << 16) -/* - * The Bridge device's PCI config space has information about the - * fb aperture size and the amount of pre-reserved memory. - * This is all handled in the intel-gtt.ko module. i915.ko only - * cares about the vga bit for the vga rbiter. - */ -#define INTEL_GMCH_CTRL 0x52 -#define INTEL_GMCH_VGA_DISABLE (1 << 1) -#define SNB_GMCH_CTRL 0x50 -#define SNB_GMCH_GGMS_SHIFT 8 /* GTT Graphics Memory Size */ -#define SNB_GMCH_GGMS_MASK 0x3 -#define SNB_GMCH_GMS_SHIFT 3 /* Graphics Mode Select */ -#define SNB_GMCH_GMS_MASK 0x1f - - /* PCI config space */ #define HPLLCC 0xc0 /* 855 only */ diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h index 7276a72710e2..3abfa6ea226e 100644 --- a/include/drm/i915_drm.h +++ b/include/drm/i915_drm.h @@ -36,4 +36,36 @@ extern bool i915_gpu_lower(void); extern bool i915_gpu_busy(void); extern bool i915_gpu_turbo_disable(void); +/* + * The Bridge device's PCI config space has information about the + * fb aperture size and the amount of pre-reserved memory. + * This is all handled in the intel-gtt.ko module. i915.ko only + * cares about the vga bit for the vga rbiter. + */ +#define INTEL_GMCH_CTRL 0x52 +#define INTEL_GMCH_VGA_DISABLE (1 << 1) +#define SNB_GMCH_CTRL 0x50 +#define SNB_GMCH_GGMS_SHIFT 8 /* GTT Graphics Memory Size */ +#define SNB_GMCH_GGMS_MASK 0x3 +#define SNB_GMCH_GMS_SHIFT 3 /* Graphics Mode Select */ +#define SNB_GMCH_GMS_MASK 0x1f + +#define I830_GMCH_CTRL 0x52 + +#define I855_GMCH_GMS_MASK 0xF0 +#define I855_GMCH_GMS_STOLEN_0M 0x0 +#define I855_GMCH_GMS_STOLEN_1M (0x1 << 4) +#define I855_GMCH_GMS_STOLEN_4M (0x2 << 4) +#define I855_GMCH_GMS_STOLEN_8M (0x3 << 4) +#define I855_GMCH_GMS_STOLEN_16M (0x4 << 4) +#define I855_GMCH_GMS_STOLEN_32M (0x5 << 4) +#define I915_GMCH_GMS_STOLEN_48M (0x6 << 4) +#define I915_GMCH_GMS_STOLEN_64M (0x7 << 4) +#define G33_GMCH_GMS_STOLEN_128M (0x8 << 4) +#define G33_GMCH_GMS_STOLEN_256M (0x9 << 4) +#define INTEL_GMCH_GMS_STOLEN_96M (0xa << 4) +#define INTEL_GMCH_GMS_STOLEN_160M (0xb << 4) +#define INTEL_GMCH_GMS_STOLEN_224M (0xc << 4) +#define INTEL_GMCH_GMS_STOLEN_352M (0xd << 4) + #endif /* _I915_DRM_H_ */ -- cgit v1.2.3-70-g09d2 From 1f5d76dbb636c73912c9ff1c90ff46dd2273f098 Mon Sep 17 00:00:00 2001 From: Paulo Zanoni Date: Fri, 23 Aug 2013 19:51:28 -0300 Subject: drm/i915: enable trickle feed on Haswell MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We shouldn't disable the trickle feed bits on Haswell. Our documentation explicitly says the trickle feed bits of PRI_CTL and CUR_CTL should not be programmed to 1, and the hardware engineer also asked us to not program the SPR_CTL field to 1. Leaving the bits as 1 could cause underflows. Reported-by: Arthur Runyan Signed-off-by: Paulo Zanoni Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/intel_display.c | 10 +++++++--- drivers/gpu/drm/i915/intel_pm.c | 2 -- drivers/gpu/drm/i915/intel_sprite.c | 7 +++++-- 4 files changed, 13 insertions(+), 7 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index dcc58ea157fe..c159e1a6810f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3313,6 +3313,7 @@ #define MCURSOR_PIPE_A 0x00 #define MCURSOR_PIPE_B (1 << 28) #define MCURSOR_GAMMA_ENABLE (1 << 26) +#define CURSOR_TRICKLE_FEED_DISABLE (1 << 14) #define _CURABASE (dev_priv->info->display_mmio_offset + 0x70084) #define _CURAPOS (dev_priv->info->display_mmio_offset + 0x70088) #define CURSOR_POS_MASK 0x007FF diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index a98392f9894e..a1e502b07266 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2077,8 +2077,10 @@ static int ironlake_update_plane(struct drm_crtc *crtc, else dspcntr &= ~DISPPLANE_TILED; - /* must disable */ - dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE; + if (IS_HASWELL(dev)) + dspcntr &= ~DISPPLANE_TRICKLE_FEED_DISABLE; + else + dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE; I915_WRITE(reg, dspcntr); @@ -6762,8 +6764,10 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base) cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE); cntl |= CURSOR_MODE_DISABLE; } - if (IS_HASWELL(dev)) + if (IS_HASWELL(dev)) { cntl |= CURSOR_PIPE_CSC_ENABLE; + cntl &= ~CURSOR_TRICKLE_FEED_DISABLE; + } I915_WRITE(CURCNTR_IVB(pipe), cntl); intel_crtc->cursor_visible = visible; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 6b1d00389952..0c115cc4899f 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4960,8 +4960,6 @@ static void haswell_init_clock_gating(struct drm_device *dev) I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) | GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB); - g4x_disable_trickle_feed(dev); - /* WaVSRefCountFullforceMissDisable:hsw */ gen7_setup_fixed_func_scheduler(dev_priv); diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 78b621cdd108..ad6ec4b39005 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -260,8 +260,11 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, if (obj->tiling_mode != I915_TILING_NONE) sprctl |= SPRITE_TILED; - /* must disable */ - sprctl |= SPRITE_TRICKLE_FEED_DISABLE; + if (IS_HASWELL(dev)) + sprctl &= ~SPRITE_TRICKLE_FEED_DISABLE; + else + sprctl |= SPRITE_TRICKLE_FEED_DISABLE; + sprctl |= SPRITE_ENABLE; if (IS_HASWELL(dev)) -- cgit v1.2.3-70-g09d2 From 5cfacdedb1a94efd29faeaab53f939554a3f5943 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 26 Aug 2013 19:50:55 -0300 Subject: drm/i915: Pin pages whilst mapping the dma-buf As we attempt to kmalloc after calling get_pages, there is a possibility that the shrinker may reap the pages we just acquired. To prevent this we need to increment the pages_pin_count early, so rearrange the code and error paths to make it so. Signed-off-by: Chris Wilson Reviewed-by: Damien Lespiau Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_dmabuf.c | 41 ++++++++++++++++++---------------- 1 file changed, 22 insertions(+), 19 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index e918b05fcbdd..7d5752fda5f1 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -42,27 +42,24 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme ret = i915_mutex_lock_interruptible(obj->base.dev); if (ret) - return ERR_PTR(ret); + goto err; ret = i915_gem_object_get_pages(obj); - if (ret) { - st = ERR_PTR(ret); - goto out; - } + if (ret) + goto err_unlock; + + i915_gem_object_pin_pages(obj); /* Copy sg so that we make an independent mapping */ st = kmalloc(sizeof(struct sg_table), GFP_KERNEL); if (st == NULL) { - st = ERR_PTR(-ENOMEM); - goto out; + ret = -ENOMEM; + goto err_unpin; } ret = sg_alloc_table(st, obj->pages->nents, GFP_KERNEL); - if (ret) { - kfree(st); - st = ERR_PTR(ret); - goto out; - } + if (ret) + goto err_free; src = obj->pages->sgl; dst = st->sgl; @@ -73,17 +70,23 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme } if (!dma_map_sg(attachment->dev, st->sgl, st->nents, dir)) { - sg_free_table(st); - kfree(st); - st = ERR_PTR(-ENOMEM); - goto out; + ret =-ENOMEM; + goto err_free_sg; } - i915_gem_object_pin_pages(obj); - -out: mutex_unlock(&obj->base.dev->struct_mutex); return st; + +err_free_sg: + sg_free_table(st); +err_free: + kfree(st); +err_unpin: + i915_gem_object_unpin_pages(obj); +err_unlock: + mutex_unlock(&obj->base.dev->struct_mutex); +err: + return ERR_PTR(ret); } static void i915_gem_unmap_dma_buf(struct dma_buf_attachment *attachment, -- cgit v1.2.3-70-g09d2 From f22d776f3e280e605819fc09fc35db0d802d36ce Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 15 Aug 2013 16:37:53 -0600 Subject: vgaarb: Don't disable resources that are not owned MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If a device does not own a resource then we don't need to disable it. This resolves the case where an Intel IGD device can be configured to disable decode of VGA memory but we still need the arbiter to handle VGA I/O port routing. When the IGD device is in conflict, only PCI_COMMAND_IO should be disabled since VGA memory does not require arbitration on this device. Signed-off-by: Alex Williamson Cc: Dave Airlie Acked-by: Dave Airlie Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/vga/vgaarb.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c index e893f6e1937d..ea564711bb80 100644 --- a/drivers/gpu/vga/vgaarb.c +++ b/drivers/gpu/vga/vgaarb.c @@ -257,9 +257,9 @@ static struct vga_device *__vga_tryget(struct vga_device *vgadev, if (!conflict->bridge_has_one_vga) { vga_irq_set_state(conflict, false); flags |= PCI_VGA_STATE_CHANGE_DECODES; - if (lwants & (VGA_RSRC_LEGACY_MEM|VGA_RSRC_NORMAL_MEM)) + if (match & (VGA_RSRC_LEGACY_MEM|VGA_RSRC_NORMAL_MEM)) pci_bits |= PCI_COMMAND_MEMORY; - if (lwants & (VGA_RSRC_LEGACY_IO|VGA_RSRC_NORMAL_IO)) + if (match & (VGA_RSRC_LEGACY_IO|VGA_RSRC_NORMAL_IO)) pci_bits |= PCI_COMMAND_IO; } @@ -267,11 +267,11 @@ static struct vga_device *__vga_tryget(struct vga_device *vgadev, flags |= PCI_VGA_STATE_CHANGE_BRIDGE; pci_set_vga_state(conflict->pdev, false, pci_bits, flags); - conflict->owns &= ~lwants; + conflict->owns &= ~match; /* If he also owned non-legacy, that is no longer the case */ - if (lwants & VGA_RSRC_LEGACY_MEM) + if (match & VGA_RSRC_LEGACY_MEM) conflict->owns &= ~VGA_RSRC_NORMAL_MEM; - if (lwants & VGA_RSRC_LEGACY_IO) + if (match & VGA_RSRC_LEGACY_IO) conflict->owns &= ~VGA_RSRC_NORMAL_IO; } -- cgit v1.2.3-70-g09d2 From 5c0f6ee766d7c689e71a7df5e5fa87941affd75a Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 15 Aug 2013 16:37:59 -0600 Subject: vgaarb: Fix VGA decodes changes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When VGA decodes change we need to do a bit more evaluation of exactly what has changed. We don't necessarily give up all the old owns resources and we need to account for resources with locks. The new algorithm is: If something is added, update decodes. If legacy resources were added and none were there before, we have a new participant. If something is removed, update decodes. If we previously owned it, we no longer own it. If it was previously locked, invalidate all locks and release it. If legacy resources were removed and none are left, remove the participant from VGA arbitration. Previously we updated decodes, released ownership of everything that was previously decoded, ignored all locks, and went off looking for another device to transfer VGA to. In a test case where Intel IGD removes only legacy VGA memory decoding, this left the arbiter switching to discrete graphics without actually disabling legacy VGA IO from the IGD. As a bonus, we bumped up the count of VGA arbitration participants for no good reason. Signed-off-by: Alex Williamson Cc: Dave Airlie Acked-by: Dave Airlie Reviewed-by: Ville Syrjälä [danvet: Kill now unused variables, reported by the 0-day kernel builtbot.] Signed-off-by: Daniel Vetter --- drivers/gpu/vga/vgaarb.c | 41 +++++++++++++++++------------------------ 1 file changed, 17 insertions(+), 24 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c index ea564711bb80..af0259708358 100644 --- a/drivers/gpu/vga/vgaarb.c +++ b/drivers/gpu/vga/vgaarb.c @@ -644,10 +644,12 @@ bail: static inline void vga_update_device_decodes(struct vga_device *vgadev, int new_decodes) { - int old_decodes; - struct vga_device *new_vgadev, *conflict; + int old_decodes, decodes_removed, decodes_unlocked; old_decodes = vgadev->decodes; + decodes_removed = ~new_decodes & old_decodes; + decodes_unlocked = vgadev->locks & decodes_removed; + vgadev->owns &= ~decodes_removed; vgadev->decodes = new_decodes; pr_info("vgaarb: device changed decodes: PCI:%s,olddecodes=%s,decodes=%s:owns=%s\n", @@ -656,31 +658,22 @@ static inline void vga_update_device_decodes(struct vga_device *vgadev, vga_iostate_to_str(vgadev->decodes), vga_iostate_to_str(vgadev->owns)); - - /* if we own the decodes we should move them along to - another card */ - if ((vgadev->owns & old_decodes) && (vga_count > 1)) { - /* set us to own nothing */ - vgadev->owns &= ~old_decodes; - list_for_each_entry(new_vgadev, &vga_list, list) { - if ((new_vgadev != vgadev) && - (new_vgadev->decodes & VGA_RSRC_LEGACY_MASK)) { - pr_info("vgaarb: transferring owner from PCI:%s to PCI:%s\n", pci_name(vgadev->pdev), pci_name(new_vgadev->pdev)); - conflict = __vga_tryget(new_vgadev, VGA_RSRC_LEGACY_MASK); - if (!conflict) - __vga_put(new_vgadev, VGA_RSRC_LEGACY_MASK); - break; - } - } + /* if we removed locked decodes, lock count goes to zero, and release */ + if (decodes_unlocked) { + if (decodes_unlocked & VGA_RSRC_LEGACY_IO) + vgadev->io_lock_cnt = 0; + if (decodes_unlocked & VGA_RSRC_LEGACY_MEM) + vgadev->mem_lock_cnt = 0; + __vga_put(vgadev, decodes_unlocked); } /* change decodes counter */ - if (old_decodes != new_decodes) { - if (new_decodes & (VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM)) - vga_decode_count++; - else - vga_decode_count--; - } + if (old_decodes & VGA_RSRC_LEGACY_MASK && + !(new_decodes & VGA_RSRC_LEGACY_MASK)) + vga_decode_count--; + if (!(old_decodes & VGA_RSRC_LEGACY_MASK) && + new_decodes & VGA_RSRC_LEGACY_MASK) + vga_decode_count++; pr_debug("vgaarb: decoding count now is: %d\n", vga_decode_count); } -- cgit v1.2.3-70-g09d2 From 81b5c7bc8de3e6f63419139c2fc91bf81dea8a7d Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 28 Aug 2013 09:39:08 -0600 Subject: i915: Update VGA arbiter support for newer devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is intended to add VGA arbiter support for Intel HD graphics on Core processors. The old GMCH registers no longer exist, so even though it appears that i915 participates in VGA arbitration, it doesn't work. On Intel HD graphics we already attempt to disable VGA regions of the device. This makes registering as a VGA client unnecessary since we don't intend to operate differently depending on how many VGA devices are present. We can disable VGA memory regions by clearing the memory enable bit in the VGA MSR. That only leaves VGA IO, which we update the VGA arbiter to know that we don't participate in VGA memory arbitration. We also add a hook on unload to re-enable memory and reinstate VGA memory arbitration. v3: Use explicit LEGACY_IO | LEGACY_MEM when restoring rather than LEGACY_MASK, per Ville's comments. v2: I915_READ/WRITE accessors don't work in i915_disable_vga, use inb/outb directly. Also, on the driver unbind VGA enable path, acquire legacy IO to re-enable VGA memory. Correct comment. Signed-off-by: Alex Williamson Reviewed-by: Ville Syrjälä [danvet: Add patch changelog. Also squash in a fixup to have a dummy static inline for vga_set_legacy_decoding for CONFIG_VGA_ARB=n as reported by the 0-day kernel build bot.] Signed-off-by: Daniel Vetter fixup 2 --- drivers/gpu/drm/i915/i915_dma.c | 9 ++++++--- drivers/gpu/drm/i915/intel_display.c | 25 +++++++++++++++++++++++++ include/linux/vgaarb.h | 7 +++++++ 3 files changed, 38 insertions(+), 3 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index fdaa0915ce56..3de60503378e 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1290,9 +1290,12 @@ static int i915_load_modeset_init(struct drm_device *dev) * then we do not take part in VGA arbitration and the * vga_client_register() fails with -ENODEV. */ - ret = vga_client_register(dev->pdev, dev, NULL, i915_vga_set_decode); - if (ret && ret != -ENODEV) - goto out; + if (!HAS_PCH_SPLIT(dev)) { + ret = vga_client_register(dev->pdev, dev, NULL, + i915_vga_set_decode); + if (ret && ret != -ENODEV) + goto out; + } intel_register_dsm_handler(); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index a1e502b07266..73dec62f871f 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -10041,6 +10041,15 @@ static void i915_disable_vga(struct drm_device *dev) outb(SR01, VGA_SR_INDEX); sr1 = inb(VGA_SR_DATA); outb(sr1 | 1<<5, VGA_SR_DATA); + + /* Disable VGA memory on Intel HD */ + if (HAS_PCH_SPLIT(dev)) { + outb(inb(VGA_MSR_READ) & ~VGA_MSR_MEM_EN, VGA_MSR_WRITE); + vga_set_legacy_decoding(dev->pdev, VGA_RSRC_LEGACY_IO | + VGA_RSRC_NORMAL_IO | + VGA_RSRC_NORMAL_MEM); + } + vga_put(dev->pdev, VGA_RSRC_LEGACY_IO); udelay(300); @@ -10048,6 +10057,20 @@ static void i915_disable_vga(struct drm_device *dev) POSTING_READ(vga_reg); } +static void i915_enable_vga(struct drm_device *dev) +{ + /* Enable VGA memory on Intel HD */ + if (HAS_PCH_SPLIT(dev)) { + vga_get_uninterruptible(dev->pdev, VGA_RSRC_LEGACY_IO); + outb(inb(VGA_MSR_READ) | VGA_MSR_MEM_EN, VGA_MSR_WRITE); + vga_set_legacy_decoding(dev->pdev, VGA_RSRC_LEGACY_IO | + VGA_RSRC_LEGACY_MEM | + VGA_RSRC_NORMAL_IO | + VGA_RSRC_NORMAL_MEM); + vga_put(dev->pdev, VGA_RSRC_LEGACY_IO); + } +} + void intel_modeset_init_hw(struct drm_device *dev) { intel_init_power_well(dev); @@ -10539,6 +10562,8 @@ void intel_modeset_cleanup(struct drm_device *dev) intel_disable_fbc(dev); + i915_enable_vga(dev); + intel_disable_gt_powersave(dev); ironlake_teardown_rc6(dev); diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h index 2c02f3a8d2ba..80cf8173a65b 100644 --- a/include/linux/vgaarb.h +++ b/include/linux/vgaarb.h @@ -65,8 +65,15 @@ struct pci_dev; * out of the arbitration process (and can be safe to take * interrupts at any time. */ +#if defined(CONFIG_VGA_ARB) extern void vga_set_legacy_decoding(struct pci_dev *pdev, unsigned int decodes); +#else +static inline void vga_set_legacy_decoding(struct pci_dev *pdev, + unsigned int decodes) +{ +} +#endif /** * vga_get - acquire & locks VGA resources -- cgit v1.2.3-70-g09d2 From d2933a5b8f8f11cbdf9d2e44f0c7c7abeeb64e6b Mon Sep 17 00:00:00 2001 From: Damien Lespiau Date: Fri, 30 Aug 2013 15:39:26 +0100 Subject: drm/i915: Don't call sg_free_table() if sg_alloc_table() fails One needs to call __sg_free_table() if __sg_alloc_table() fails, but sg_alloc_table() does that for us already. Signed-off-by: Damien Lespiau Reviewd-by: Chris Wilson Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 61313054fce6..f21a0c36a40b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1774,7 +1774,6 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) page_count = obj->base.size / PAGE_SIZE; if (sg_alloc_table(st, page_count, GFP_KERNEL)) { - sg_free_table(st); kfree(st); return -ENOMEM; } -- cgit v1.2.3-70-g09d2 From 4c6df4b4ca1b26f4532d403b544f649a1c801fd1 Mon Sep 17 00:00:00 2001 From: Ville Syrjälä Date: Mon, 2 Sep 2013 21:13:39 +0300 Subject: drm/i915: Fix pipe config warnings when dealing with LVDS fixed mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit intel_fixed_panel_mode() overwrote the adjusted_mode with the fixed mode only partially. Notably it forgot to copy over the sync flags. The LVDS code however programmed the hardware with the sync flags from fixed mode, and then later the pipe config comparison obviously failed as we filled out the adjusted_mode in get_config from the real registers. Just call drm_mode_copy() in intel_fixed_panel_mode() to copy over the whole thing, and then just use adjusted_mode in the LVDS code to figure out which sync settings the hardware needs. Also constify the fixed_mode argument to intel_fixed_panel_mode(). Signed-off-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_drv.h | 2 +- drivers/gpu/drm/i915/intel_lvds.c | 8 ++++---- drivers/gpu/drm/i915/intel_panel.c | 14 ++------------ 3 files changed, 7 insertions(+), 17 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 176080822a74..dbfe5f7bb3de 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -551,7 +551,7 @@ extern int intel_panel_init(struct intel_panel *panel, struct drm_display_mode *fixed_mode); extern void intel_panel_fini(struct intel_panel *panel); -extern void intel_fixed_panel_mode(struct drm_display_mode *fixed_mode, +extern void intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode, struct drm_display_mode *adjusted_mode); extern void intel_pch_panel_fitting(struct intel_crtc *crtc, struct intel_crtc_config *pipe_config, diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 4d33278e31fb..831a5c021c4b 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -128,8 +128,8 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder) struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); - struct drm_display_mode *fixed_mode = - lvds_encoder->attached_connector->base.panel.fixed_mode; + const struct drm_display_mode *adjusted_mode = + &crtc->config.adjusted_mode; int pipe = crtc->pipe; u32 temp; @@ -183,9 +183,9 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder) temp &= ~LVDS_ENABLE_DITHER; } temp &= ~(LVDS_HSYNC_POLARITY | LVDS_VSYNC_POLARITY); - if (fixed_mode->flags & DRM_MODE_FLAG_NHSYNC) + if (adjusted_mode->flags & DRM_MODE_FLAG_NHSYNC) temp |= LVDS_HSYNC_POLARITY; - if (fixed_mode->flags & DRM_MODE_FLAG_NVSYNC) + if (adjusted_mode->flags & DRM_MODE_FLAG_NVSYNC) temp |= LVDS_VSYNC_POLARITY; I915_WRITE(lvds_encoder->reg, temp); diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 913cb9d7fd32..42114ecbae0e 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -36,20 +36,10 @@ #define PCI_LBPC 0xf4 /* legacy/combination backlight modes */ void -intel_fixed_panel_mode(struct drm_display_mode *fixed_mode, +intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode, struct drm_display_mode *adjusted_mode) { - adjusted_mode->hdisplay = fixed_mode->hdisplay; - adjusted_mode->hsync_start = fixed_mode->hsync_start; - adjusted_mode->hsync_end = fixed_mode->hsync_end; - adjusted_mode->htotal = fixed_mode->htotal; - - adjusted_mode->vdisplay = fixed_mode->vdisplay; - adjusted_mode->vsync_start = fixed_mode->vsync_start; - adjusted_mode->vsync_end = fixed_mode->vsync_end; - adjusted_mode->vtotal = fixed_mode->vtotal; - - adjusted_mode->clock = fixed_mode->clock; + drm_mode_copy(adjusted_mode, fixed_mode); drm_mode_set_crtcinfo(adjusted_mode, 0); } -- cgit v1.2.3-70-g09d2 From d4d36014ca37e6fa8271b0690e678b76456faa01 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 2 Sep 2013 20:56:23 +0200 Subject: drm/i915: fix up the relocate_entry refactoring Somehow we've lost the error handling in the patch split-up between the internal and external patch. This regression has been introduced in commit 5032d871f7d300aee10c309ea004eb4f851553fe Author: Rafael Barbalho Date: Wed Aug 21 17:10:51 2013 +0100 drm/i915: Cleaning up the relocate entry function This bug is exercised by igt/gem_reloc_vs_gpu/interruptible. Cc: Rafael Barbalho Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 792c52a235ee..bf345777ae9f 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -310,6 +310,9 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, else ret = relocate_entry_gtt(obj, reloc); + if (ret) + return ret; + /* and update the user's relocation entry */ reloc->presumed_offset = target_offset; -- cgit v1.2.3-70-g09d2 From 645416f5adc87c8fae44289cdba7562f3ade8f5c Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 2 Sep 2013 16:22:25 +0200 Subject: drm/i915: fix hpd work vs. flush_work in the pageflip code deadlock Historically we've run our own driver hotplug handling in our own work-queue, which then launched the drm core hotplug handling in the system workqueue. This is important since we flush our own driver workqueue in the pageflip code while hodling modeset locks, and only the drm hotplug code grabbed these locks. But with commit 69787f7da6b2adc4054357a661aaa1701a9ca76f Author: Daniel Vetter Date: Tue Oct 23 18:23:34 2012 +0000 drm: run the hpd irq event code directly this was changed and now we could deadlock in our flip handler if there's a hotplug work blocking the progress of the crucial unpin works. So this broke the careful deadlock avoidance implemented in commit b4a98e57fc27854b5938fc8b08b68e5e68b91e1f Author: Chris Wilson Date: Thu Nov 1 09:26:26 2012 +0000 drm/i915: Flush outstanding unpin tasks before pageflipping Since the rule thus far has been that work items on our own workqueue may never grab modeset locks simply restore that rule again. v2: Add a comment to the declaration of dev_priv->wq to warn readers about the tricky implications of using it. Suggested by Chris Wilson. Cc: Chris Wilson Cc: Stuart Abercrombie Reported-by: Stuart Abercrombie References: http://permalink.gmane.org/gmane.comp.freedesktop.xorg.drivers.intel/26239 Cc: stable@vger.kernel.org Reviewed-by: Chris Wilson [danvet: Squash in a comment at the place where we schedule the work. Requested after-the-fact by Chris on irc since the hpd work isn't the only place we botch this.] Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_drv.h | 7 +++++++ drivers/gpu/drm/i915/i915_irq.c | 9 +++++++-- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 52a3785a3fdf..35874b3a86dc 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1236,6 +1236,13 @@ typedef struct drm_i915_private { unsigned int fsb_freq, mem_freq, is_ddr3; + /** + * wq - Driver workqueue for GEM. + * + * NOTE: Work items scheduled here are not allowed to grab any modeset + * locks, for otherwise the flushing done in the pageflip code will + * result in deadlocks. + */ struct workqueue_struct *wq; /* Display functions */ diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 4c6853f57d62..9e48cf27db5e 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1027,8 +1027,13 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev, dev_priv->display.hpd_irq_setup(dev); spin_unlock(&dev_priv->irq_lock); - queue_work(dev_priv->wq, - &dev_priv->hotplug_work); + /* + * Our hotplug handler can grab modeset locks (by calling down into the + * fb helpers). Hence it must not be run on our own dev-priv->wq work + * queue for otherwise the flush_work in the pageflip code will + * deadlock. + */ + schedule_work(&dev_priv->hotplug_work); } static void gmbus_irq_handler(struct drm_device *dev) -- cgit v1.2.3-70-g09d2 From eeb4793779060e0ae27fc8a85b8dac2ab3620934 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 3 Sep 2013 20:40:36 +0200 Subject: drm/i915: handle sdvo input pixel multiplier correctly again MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The sdvo input timing needs to be the actual mode, the sdvo encoder automatically adjusts for the need of pixel doubling or quadrupling. This was lost in pipe config conversion of the pixel multiplier in commit 6cc5f341b5830541a1b6945435ca90c69b1b8b21 Author: Daniel Vetter Date: Wed Mar 27 00:44:53 2013 +0100 drm/i915: add pipe_config->pixel_multiplier While at it ditch the intel_ prefix from the crtc in intel_sdvo_mode_set. Cc: Jesse Barnes Cc: Ville Syrjälä Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_sdvo.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 317e058fb3cf..85037b9d4934 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1151,11 +1151,10 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder) { struct drm_device *dev = intel_encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_crtc *crtc = intel_encoder->base.crtc; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_crtc *crtc = to_intel_crtc(intel_encoder->base.crtc); struct drm_display_mode *adjusted_mode = - &intel_crtc->config.adjusted_mode; - struct drm_display_mode *mode = &intel_crtc->config.requested_mode; + &crtc->config.adjusted_mode; + struct drm_display_mode *mode = &crtc->config.requested_mode; struct intel_sdvo *intel_sdvo = to_sdvo(intel_encoder); u32 sdvox; struct intel_sdvo_in_out_map in_out; @@ -1213,13 +1212,15 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder) * adjusted_mode. */ intel_sdvo_get_dtd_from_mode(&input_dtd, adjusted_mode); + input_dtd.part1.clock /= crtc->config.pixel_multiplier; + if (intel_sdvo->is_tv || intel_sdvo->is_lvds) input_dtd.part2.sdvo_flags = intel_sdvo->dtd_sdvo_flags; if (!intel_sdvo_set_input_timing(intel_sdvo, &input_dtd)) DRM_INFO("Setting input timings on %s failed\n", SDVO_NAME(intel_sdvo)); - switch (intel_crtc->config.pixel_multiplier) { + switch (crtc->config.pixel_multiplier) { default: WARN(1, "unknown pixel mutlipler specified\n"); case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break; @@ -1252,9 +1253,9 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder) } if (INTEL_PCH_TYPE(dev) >= PCH_CPT) - sdvox |= SDVO_PIPE_SEL_CPT(intel_crtc->pipe); + sdvox |= SDVO_PIPE_SEL_CPT(crtc->pipe); else - sdvox |= SDVO_PIPE_SEL(intel_crtc->pipe); + sdvox |= SDVO_PIPE_SEL(crtc->pipe); if (intel_sdvo->has_hdmi_audio) sdvox |= SDVO_AUDIO_ENABLE; @@ -1264,7 +1265,7 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder) } else if (IS_I945G(dev) || IS_I945GM(dev) || IS_G33(dev)) { /* done in crtc_mode_set as it lives inside the dpll register */ } else { - sdvox |= (intel_crtc->config.pixel_multiplier - 1) + sdvox |= (crtc->config.pixel_multiplier - 1) << SDVO_PORT_MULTIPLY_SHIFT; } -- cgit v1.2.3-70-g09d2 From a2dc53e7dc4d22f20aecdfa10f85004de442e4d0 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 3 Sep 2013 20:40:37 +0200 Subject: drm/i915: fix i9xx_crtc_clock_get for multiplied pixels MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The dpll actually runs at the port clock so we don't need to multiply it again with the pixel multiplier to get the adjusted_mode.clock. This is in contrast to the ironlake pixel clock readout code which uses the fdi dotclock: That one does _not_ run with multiplied pixels. This issue goes back to the original clock readout code added in commit f1f644dc66cbaf5a4c7dcde683361536b41885b9 Author: Jesse Barnes Date: Thu Jun 27 00:39:25 2013 +0300 drm/i915: get mode clock when reading the pipe config v9 Cc: Jesse Barnes Cc: Ville Syrjälä Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_display.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 73dec62f871f..0534d5b9b3e3 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -7313,8 +7313,7 @@ static void i9xx_crtc_clock_get(struct intel_crtc *crtc, } } - pipe_config->adjusted_mode.clock = clock.dot * - pipe_config->pixel_multiplier; + pipe_config->adjusted_mode.clock = clock.dot; } static void ironlake_crtc_clock_get(struct intel_crtc *crtc, -- cgit v1.2.3-70-g09d2 From 27173f1f95db5e74ceb35fe9a2f2f348ea11bac9 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Wed, 14 Aug 2013 11:38:36 +0200 Subject: drm/i915: Convert execbuf code to use vmas In order to transition more of our code over to using a VMA instead of an pair - we must have the vma accessible at execbuf time. Up until now, we've only had a VMA when actually binding an object. The previous patch helped handle the distinction on bound vs. unbound. This patch will help us catch leaks, and other issues before we actually shuffle a bunch of stuff around. This attempts to convert all the execbuf code to speak in vmas. Since the execbuf code is very self contained it was a nice isolated conversion. The meat of the code is about turning eb_objects into eb_vma, and then wiring up the rest of the code to use vmas instead of obj, vm pairs. Unfortunately, to do this, we must move the exec_list link from the obj structure. This list is reused in the eviction code, so we must also modify the eviction code to make this work. WARNING: This patch makes an already hotly profiled path slower. The cost is unavoidable. In reply to this mail, I will attach the extra data. v2: Release table lock early, and two a 2 phase vma lookup to avoid having to use a GFP_ATOMIC. (Chris) v3: s/obj_exec_list/obj_exec_link/ Updates to address commit 6d2b888569d366beb4be72cacfde41adee2c25e1 Author: Chris Wilson Date: Wed Aug 7 18:30:54 2013 +0100 drm/i915: List objects allocated from stolen memory in debugfs v4: Use obj = vma->obj for neatness in some places (Chris) need_reloc_mappable() should return false if ppgtt (Chris) Signed-off-by: Ben Widawsky [danvet: Split out prep patches. Also remove a FIXME comment which is now taken care of.] Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_drv.h | 16 +- drivers/gpu/drm/i915/i915_gem.c | 1 - drivers/gpu/drm/i915/i915_gem_execbuffer.c | 320 ++++++++++++++++------------- 3 files changed, 183 insertions(+), 154 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 35874b3a86dc..b6494b24098d 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -568,6 +568,13 @@ struct i915_vma { /** This vma's place in the batchbuffer or on the eviction list */ struct list_head exec_list; + /** + * Used for performing relocations during execbuffer insertion. + */ + struct hlist_node exec_node; + unsigned long exec_handle; + struct drm_i915_gem_exec_object2 *exec_entry; + }; struct i915_ctx_hang_stats { @@ -1398,8 +1405,6 @@ struct drm_i915_gem_object { struct list_head ring_list; /** Used in execbuf to temporarily hold a ref */ struct list_head obj_exec_link; - /** This object's place in the batchbuffer or on the eviction list */ - struct list_head exec_list; /** * This is set if the object is on the active lists (has pending @@ -1485,13 +1490,6 @@ struct drm_i915_gem_object { void *dma_buf_vmapping; int vmapping_count; - /** - * Used for performing relocations during execbuffer insertion. - */ - struct hlist_node exec_node; - unsigned long exec_handle; - struct drm_i915_gem_exec_object2 *exec_entry; - struct intel_ring_buffer *ring; /** Breadcrumb of last rendering to the buffer. */ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index f21a0c36a40b..c4c56f98d6e6 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3978,7 +3978,6 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, { INIT_LIST_HEAD(&obj->global_list); INIT_LIST_HEAD(&obj->ring_list); - INIT_LIST_HEAD(&obj->exec_list); INIT_LIST_HEAD(&obj->obj_exec_link); INIT_LIST_HEAD(&obj->vma_list); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index bf345777ae9f..5dcfd4f59f87 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -33,24 +33,24 @@ #include "intel_drv.h" #include -struct eb_objects { - struct list_head objects; +struct eb_vmas { + struct list_head vmas; int and; union { - struct drm_i915_gem_object *lut[0]; + struct i915_vma *lut[0]; struct hlist_head buckets[0]; }; }; -static struct eb_objects * -eb_create(struct drm_i915_gem_execbuffer2 *args) +static struct eb_vmas * +eb_create(struct drm_i915_gem_execbuffer2 *args, struct i915_address_space *vm) { - struct eb_objects *eb = NULL; + struct eb_vmas *eb = NULL; if (args->flags & I915_EXEC_HANDLE_LUT) { int size = args->buffer_count; - size *= sizeof(struct drm_i915_gem_object *); - size += sizeof(struct eb_objects); + size *= sizeof(struct i915_vma *); + size += sizeof(struct eb_vmas); eb = kmalloc(size, GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); } @@ -61,7 +61,7 @@ eb_create(struct drm_i915_gem_execbuffer2 *args) while (count > 2*size) count >>= 1; eb = kzalloc(count*sizeof(struct hlist_head) + - sizeof(struct eb_objects), + sizeof(struct eb_vmas), GFP_TEMPORARY); if (eb == NULL) return eb; @@ -70,64 +70,97 @@ eb_create(struct drm_i915_gem_execbuffer2 *args) } else eb->and = -args->buffer_count; - INIT_LIST_HEAD(&eb->objects); + INIT_LIST_HEAD(&eb->vmas); return eb; } static void -eb_reset(struct eb_objects *eb) +eb_reset(struct eb_vmas *eb) { if (eb->and >= 0) memset(eb->buckets, 0, (eb->and+1)*sizeof(struct hlist_head)); } static int -eb_lookup_objects(struct eb_objects *eb, - struct drm_i915_gem_exec_object2 *exec, - const struct drm_i915_gem_execbuffer2 *args, - struct drm_file *file) +eb_lookup_vmas(struct eb_vmas *eb, + struct drm_i915_gem_exec_object2 *exec, + const struct drm_i915_gem_execbuffer2 *args, + struct i915_address_space *vm, + struct drm_file *file) { - int i; + struct drm_i915_gem_object *obj; + struct list_head objects; + int i, ret = 0; + INIT_LIST_HEAD(&objects); spin_lock(&file->table_lock); + /* Grab a reference to the object and release the lock so we can lookup + * or create the VMA without using GFP_ATOMIC */ for (i = 0; i < args->buffer_count; i++) { - struct drm_i915_gem_object *obj; - obj = to_intel_bo(idr_find(&file->object_idr, exec[i].handle)); if (obj == NULL) { spin_unlock(&file->table_lock); DRM_DEBUG("Invalid object handle %d at index %d\n", exec[i].handle, i); - return -ENOENT; + ret = -ENOENT; + goto out; } - if (!list_empty(&obj->exec_list)) { + if (!list_empty(&obj->obj_exec_link)) { spin_unlock(&file->table_lock); DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n", obj, exec[i].handle, i); - return -EINVAL; + ret = -EINVAL; + goto out; } drm_gem_object_reference(&obj->base); - list_add_tail(&obj->exec_list, &eb->objects); + list_add_tail(&obj->obj_exec_link, &objects); + } + spin_unlock(&file->table_lock); - obj->exec_entry = &exec[i]; + i = 0; + list_for_each_entry(obj, &objects, obj_exec_link) { + struct i915_vma *vma; + + vma = i915_gem_obj_lookup_or_create_vma(obj, vm); + if (IS_ERR(vma)) { + /* XXX: We don't need an error path fro vma because if + * the vma was created just for this execbuf, object + * unreference should kill it off.*/ + DRM_DEBUG("Failed to lookup VMA\n"); + ret = PTR_ERR(vma); + goto out; + } + + list_add_tail(&vma->exec_list, &eb->vmas); + + vma->exec_entry = &exec[i]; if (eb->and < 0) { - eb->lut[i] = obj; + eb->lut[i] = vma; } else { uint32_t handle = args->flags & I915_EXEC_HANDLE_LUT ? i : exec[i].handle; - obj->exec_handle = handle; - hlist_add_head(&obj->exec_node, + vma->exec_handle = handle; + hlist_add_head(&vma->exec_node, &eb->buckets[handle & eb->and]); } + ++i; } - spin_unlock(&file->table_lock); - return 0; + +out: + while (!list_empty(&objects)) { + obj = list_first_entry(&objects, + struct drm_i915_gem_object, + obj_exec_link); + list_del_init(&obj->obj_exec_link); + if (ret) + drm_gem_object_unreference(&obj->base); + } + return ret; } -static struct drm_i915_gem_object * -eb_get_object(struct eb_objects *eb, unsigned long handle) +static struct i915_vma *eb_get_vma(struct eb_vmas *eb, unsigned long handle) { if (eb->and < 0) { if (handle >= -eb->and) @@ -139,27 +172,25 @@ eb_get_object(struct eb_objects *eb, unsigned long handle) head = &eb->buckets[handle & eb->and]; hlist_for_each(node, head) { - struct drm_i915_gem_object *obj; + struct i915_vma *vma; - obj = hlist_entry(node, struct drm_i915_gem_object, exec_node); - if (obj->exec_handle == handle) - return obj; + vma = hlist_entry(node, struct i915_vma, exec_node); + if (vma->exec_handle == handle) + return vma; } return NULL; } } -static void -eb_destroy(struct eb_objects *eb) -{ - while (!list_empty(&eb->objects)) { - struct drm_i915_gem_object *obj; +static void eb_destroy(struct eb_vmas *eb) { + while (!list_empty(&eb->vmas)) { + struct i915_vma *vma; - obj = list_first_entry(&eb->objects, - struct drm_i915_gem_object, + vma = list_first_entry(&eb->vmas, + struct i915_vma, exec_list); - list_del_init(&obj->exec_list); - drm_gem_object_unreference(&obj->base); + list_del_init(&vma->exec_list); + drm_gem_object_unreference(&vma->obj->base); } kfree(eb); } @@ -223,22 +254,24 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj, static int i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, - struct eb_objects *eb, + struct eb_vmas *eb, struct drm_i915_gem_relocation_entry *reloc, struct i915_address_space *vm) { struct drm_device *dev = obj->base.dev; struct drm_gem_object *target_obj; struct drm_i915_gem_object *target_i915_obj; + struct i915_vma *target_vma; uint32_t target_offset; int ret = -EINVAL; /* we've already hold a reference to all valid objects */ - target_obj = &eb_get_object(eb, reloc->target_handle)->base; - if (unlikely(target_obj == NULL)) + target_vma = eb_get_vma(eb, reloc->target_handle); + if (unlikely(target_vma == NULL)) return -ENOENT; + target_i915_obj = target_vma->obj; + target_obj = &target_vma->obj->base; - target_i915_obj = to_intel_bo(target_obj); target_offset = i915_gem_obj_ggtt_offset(target_i915_obj); /* Sandybridge PPGTT errata: We need a global gtt mapping for MI and @@ -320,14 +353,13 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj, } static int -i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj, - struct eb_objects *eb, - struct i915_address_space *vm) +i915_gem_execbuffer_relocate_vma(struct i915_vma *vma, + struct eb_vmas *eb) { #define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry)) struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)]; struct drm_i915_gem_relocation_entry __user *user_relocs; - struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; + struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; int remain, ret; user_relocs = to_user_ptr(entry->relocs_ptr); @@ -346,8 +378,8 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj, do { u64 offset = r->presumed_offset; - ret = i915_gem_execbuffer_relocate_entry(obj, eb, r, - vm); + ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, r, + vma->vm); if (ret) return ret; @@ -368,17 +400,16 @@ i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj, } static int -i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj, - struct eb_objects *eb, - struct drm_i915_gem_relocation_entry *relocs, - struct i915_address_space *vm) +i915_gem_execbuffer_relocate_vma_slow(struct i915_vma *vma, + struct eb_vmas *eb, + struct drm_i915_gem_relocation_entry *relocs) { - const struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; + const struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; int i, ret; for (i = 0; i < entry->relocation_count; i++) { - ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i], - vm); + ret = i915_gem_execbuffer_relocate_entry(vma->obj, eb, &relocs[i], + vma->vm); if (ret) return ret; } @@ -387,10 +418,10 @@ i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj, } static int -i915_gem_execbuffer_relocate(struct eb_objects *eb, +i915_gem_execbuffer_relocate(struct eb_vmas *eb, struct i915_address_space *vm) { - struct drm_i915_gem_object *obj; + struct i915_vma *vma; int ret = 0; /* This is the fast path and we cannot handle a pagefault whilst @@ -401,8 +432,8 @@ i915_gem_execbuffer_relocate(struct eb_objects *eb, * lockdep complains vehemently. */ pagefault_disable(); - list_for_each_entry(obj, &eb->objects, exec_list) { - ret = i915_gem_execbuffer_relocate_object(obj, eb, vm); + list_for_each_entry(vma, &eb->vmas, exec_list) { + ret = i915_gem_execbuffer_relocate_vma(vma, eb); if (ret) break; } @@ -415,31 +446,32 @@ i915_gem_execbuffer_relocate(struct eb_objects *eb, #define __EXEC_OBJECT_HAS_FENCE (1<<30) static int -need_reloc_mappable(struct drm_i915_gem_object *obj) +need_reloc_mappable(struct i915_vma *vma) { - struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; - return entry->relocation_count && !use_cpu_reloc(obj); + struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; + return entry->relocation_count && !use_cpu_reloc(vma->obj) && + i915_is_ggtt(vma->vm); } static int -i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring, - struct i915_address_space *vm, - bool *need_reloc) +i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, + struct intel_ring_buffer *ring, + bool *need_reloc) { - struct drm_i915_private *dev_priv = obj->base.dev->dev_private; - struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; + struct drm_i915_private *dev_priv = ring->dev->dev_private; + struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4; bool need_fence, need_mappable; + struct drm_i915_gem_object *obj = vma->obj; int ret; need_fence = has_fenced_gpu_access && entry->flags & EXEC_OBJECT_NEEDS_FENCE && obj->tiling_mode != I915_TILING_NONE; - need_mappable = need_fence || need_reloc_mappable(obj); + need_mappable = need_fence || need_reloc_mappable(vma); - ret = i915_gem_object_pin(obj, vm, entry->alignment, need_mappable, + ret = i915_gem_object_pin(obj, vma->vm, entry->alignment, need_mappable, false); if (ret) return ret; @@ -467,8 +499,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, obj->has_aliasing_ppgtt_mapping = 1; } - if (entry->offset != i915_gem_obj_offset(obj, vm)) { - entry->offset = i915_gem_obj_offset(obj, vm); + if (entry->offset != vma->node.start) { + entry->offset = vma->node.start; *need_reloc = true; } @@ -485,14 +517,15 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj, } static void -i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj) +i915_gem_execbuffer_unreserve_vma(struct i915_vma *vma) { struct drm_i915_gem_exec_object2 *entry; + struct drm_i915_gem_object *obj = vma->obj; - if (!i915_gem_obj_bound_any(obj)) + if (!drm_mm_node_allocated(&vma->node)) return; - entry = obj->exec_entry; + entry = vma->exec_entry; if (entry->flags & __EXEC_OBJECT_HAS_FENCE) i915_gem_object_unpin_fence(obj); @@ -505,41 +538,40 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj) static int i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, - struct list_head *objects, - struct i915_address_space *vm, + struct list_head *vmas, bool *need_relocs) { struct drm_i915_gem_object *obj; - struct list_head ordered_objects; + struct i915_vma *vma; + struct list_head ordered_vmas; bool has_fenced_gpu_access = INTEL_INFO(ring->dev)->gen < 4; int retry; - INIT_LIST_HEAD(&ordered_objects); - while (!list_empty(objects)) { + INIT_LIST_HEAD(&ordered_vmas); + while (!list_empty(vmas)) { struct drm_i915_gem_exec_object2 *entry; bool need_fence, need_mappable; - obj = list_first_entry(objects, - struct drm_i915_gem_object, - exec_list); - entry = obj->exec_entry; + vma = list_first_entry(vmas, struct i915_vma, exec_list); + obj = vma->obj; + entry = vma->exec_entry; need_fence = has_fenced_gpu_access && entry->flags & EXEC_OBJECT_NEEDS_FENCE && obj->tiling_mode != I915_TILING_NONE; - need_mappable = need_fence || need_reloc_mappable(obj); + need_mappable = need_fence || need_reloc_mappable(vma); if (need_mappable) - list_move(&obj->exec_list, &ordered_objects); + list_move(&vma->exec_list, &ordered_vmas); else - list_move_tail(&obj->exec_list, &ordered_objects); + list_move_tail(&vma->exec_list, &ordered_vmas); obj->base.pending_read_domains = I915_GEM_GPU_DOMAINS & ~I915_GEM_DOMAIN_COMMAND; obj->base.pending_write_domain = 0; obj->pending_fenced_gpu_access = false; } - list_splice(&ordered_objects, objects); + list_splice(&ordered_vmas, vmas); /* Attempt to pin all of the buffers into the GTT. * This is done in 3 phases: @@ -558,47 +590,47 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, int ret = 0; /* Unbind any ill-fitting objects or pin. */ - list_for_each_entry(obj, objects, exec_list) { - struct drm_i915_gem_exec_object2 *entry = obj->exec_entry; + list_for_each_entry(vma, vmas, exec_list) { + struct drm_i915_gem_exec_object2 *entry = vma->exec_entry; bool need_fence, need_mappable; - u32 obj_offset; - if (!i915_gem_obj_bound(obj, vm)) + obj = vma->obj; + + if (!drm_mm_node_allocated(&vma->node)) continue; - obj_offset = i915_gem_obj_offset(obj, vm); need_fence = has_fenced_gpu_access && entry->flags & EXEC_OBJECT_NEEDS_FENCE && obj->tiling_mode != I915_TILING_NONE; - need_mappable = need_fence || need_reloc_mappable(obj); + need_mappable = need_fence || need_reloc_mappable(vma); WARN_ON((need_mappable || need_fence) && - !i915_is_ggtt(vm)); + !i915_is_ggtt(vma->vm)); if ((entry->alignment && - obj_offset & (entry->alignment - 1)) || + vma->node.start & (entry->alignment - 1)) || (need_mappable && !obj->map_and_fenceable)) - ret = i915_vma_unbind(i915_gem_obj_to_vma(obj, vm)); + ret = i915_vma_unbind(vma); else - ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs); + ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs); if (ret) goto err; } /* Bind fresh objects */ - list_for_each_entry(obj, objects, exec_list) { - if (i915_gem_obj_bound(obj, vm)) + list_for_each_entry(vma, vmas, exec_list) { + if (drm_mm_node_allocated(&vma->node)) continue; - ret = i915_gem_execbuffer_reserve_object(obj, ring, vm, need_relocs); + ret = i915_gem_execbuffer_reserve_vma(vma, ring, need_relocs); if (ret) goto err; } err: /* Decrement pin count for bound objects */ - list_for_each_entry(obj, objects, exec_list) - i915_gem_execbuffer_unreserve_object(obj); + list_for_each_entry(vma, vmas, exec_list) + i915_gem_execbuffer_unreserve_vma(vma); if (ret != -ENOSPC || retry++) return ret; @@ -614,24 +646,27 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, struct drm_i915_gem_execbuffer2 *args, struct drm_file *file, struct intel_ring_buffer *ring, - struct eb_objects *eb, - struct drm_i915_gem_exec_object2 *exec, - struct i915_address_space *vm) + struct eb_vmas *eb, + struct drm_i915_gem_exec_object2 *exec) { struct drm_i915_gem_relocation_entry *reloc; - struct drm_i915_gem_object *obj; + struct i915_address_space *vm; + struct i915_vma *vma; bool need_relocs; int *reloc_offset; int i, total, ret; int count = args->buffer_count; + if (WARN_ON(list_empty(&eb->vmas))) + return 0; + + vm = list_first_entry(&eb->vmas, struct i915_vma, exec_list)->vm; + /* We may process another execbuffer during the unlock... */ - while (!list_empty(&eb->objects)) { - obj = list_first_entry(&eb->objects, - struct drm_i915_gem_object, - exec_list); - list_del_init(&obj->exec_list); - drm_gem_object_unreference(&obj->base); + while (!list_empty(&eb->vmas)) { + vma = list_first_entry(&eb->vmas, struct i915_vma, exec_list); + list_del_init(&vma->exec_list); + drm_gem_object_unreference(&vma->obj->base); } mutex_unlock(&dev->struct_mutex); @@ -695,20 +730,19 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev, /* reacquire the objects */ eb_reset(eb); - ret = eb_lookup_objects(eb, exec, args, file); + ret = eb_lookup_vmas(eb, exec, args, vm, file); if (ret) goto err; need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; - ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs); + ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs); if (ret) goto err; - list_for_each_entry(obj, &eb->objects, exec_list) { - int offset = obj->exec_entry - exec; - ret = i915_gem_execbuffer_relocate_object_slow(obj, eb, - reloc + reloc_offset[offset], - vm); + list_for_each_entry(vma, &eb->vmas, exec_list) { + int offset = vma->exec_entry - exec; + ret = i915_gem_execbuffer_relocate_vma_slow(vma, eb, + reloc + reloc_offset[offset]); if (ret) goto err; } @@ -727,14 +761,15 @@ err: static int i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring, - struct list_head *objects) + struct list_head *vmas) { - struct drm_i915_gem_object *obj; + struct i915_vma *vma; uint32_t flush_domains = 0; bool flush_chipset = false; int ret; - list_for_each_entry(obj, objects, exec_list) { + list_for_each_entry(vma, vmas, exec_list) { + struct drm_i915_gem_object *obj = vma->obj; ret = i915_gem_object_sync(obj, ring); if (ret) return ret; @@ -809,13 +844,13 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, } static void -i915_gem_execbuffer_move_to_active(struct list_head *objects, - struct i915_address_space *vm, +i915_gem_execbuffer_move_to_active(struct list_head *vmas, struct intel_ring_buffer *ring) { - struct drm_i915_gem_object *obj; + struct i915_vma *vma; - list_for_each_entry(obj, objects, exec_list) { + list_for_each_entry(vma, vmas, exec_list) { + struct drm_i915_gem_object *obj = vma->obj; u32 old_read = obj->base.read_domains; u32 old_write = obj->base.write_domain; @@ -825,8 +860,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *objects, obj->base.read_domains = obj->base.pending_read_domains; obj->fenced_gpu_access = obj->pending_fenced_gpu_access; - /* FIXME: This lookup gets fixed later <-- danvet */ - list_move_tail(&i915_gem_obj_to_vma(obj, vm)->mm_list, &vm->active_list); + list_move_tail(&vma->mm_list, &vma->vm->active_list); i915_gem_object_move_to_active(obj, ring); if (obj->base.write_domain) { obj->dirty = 1; @@ -885,7 +919,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct i915_address_space *vm) { drm_i915_private_t *dev_priv = dev->dev_private; - struct eb_objects *eb; + struct eb_vmas *eb; struct drm_i915_gem_object *batch_obj; struct drm_clip_rect *cliprects = NULL; struct intel_ring_buffer *ring; @@ -1025,7 +1059,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto pre_mutex_err; } - eb = eb_create(args); + eb = eb_create(args, vm); if (eb == NULL) { mutex_unlock(&dev->struct_mutex); ret = -ENOMEM; @@ -1033,18 +1067,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, } /* Look up object handles */ - ret = eb_lookup_objects(eb, exec, args, file); + ret = eb_lookup_vmas(eb, exec, args, vm, file); if (ret) goto err; /* take note of the batch buffer before we might reorder the lists */ - batch_obj = list_entry(eb->objects.prev, - struct drm_i915_gem_object, - exec_list); + batch_obj = list_entry(eb->vmas.prev, struct i915_vma, exec_list)->obj; /* Move the objects en-masse into the GTT, evicting if necessary. */ need_relocs = (args->flags & I915_EXEC_NO_RELOC) == 0; - ret = i915_gem_execbuffer_reserve(ring, &eb->objects, vm, &need_relocs); + ret = i915_gem_execbuffer_reserve(ring, &eb->vmas, &need_relocs); if (ret) goto err; @@ -1054,7 +1086,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if (ret) { if (ret == -EFAULT) { ret = i915_gem_execbuffer_relocate_slow(dev, args, file, ring, - eb, exec, vm); + eb, exec); BUG_ON(!mutex_is_locked(&dev->struct_mutex)); } if (ret) @@ -1076,7 +1108,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, if (flags & I915_DISPATCH_SECURE && !batch_obj->has_global_gtt_mapping) i915_gem_gtt_bind_object(batch_obj, batch_obj->cache_level); - ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->objects); + ret = i915_gem_execbuffer_move_to_gpu(ring, &eb->vmas); if (ret) goto err; @@ -1131,7 +1163,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, trace_i915_gem_ring_dispatch(ring, intel_ring_get_seqno(ring), flags); - i915_gem_execbuffer_move_to_active(&eb->objects, vm, ring); + i915_gem_execbuffer_move_to_active(&eb->vmas, ring); i915_gem_execbuffer_retire_commands(dev, file, ring, batch_obj); err: -- cgit v1.2.3-70-g09d2 From e656a6cba0febf12a9838882b891e1c5917c7a8b Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 14 Aug 2013 14:14:04 +0200 Subject: drm/i915: inline vma_create into lookup_or_create_vma In the execbuf code we don't clean up any vmas which ended up not getting bound for code simplicity. To make sure that we don't end up creating multiple vma for the same vm kill the somewhat dangerous vma_create function and inline it into lookup_or_create. This is just a safety measure to prevent surprises in the future. Also update the somewhat confused comment in the execbuf code and clarify what kind of magic is going on with a new one. v2: Keep the function separate as requested by Chris. But give it a __ prefix for paranoia and move it tighter together with the other vma stuff. Cc: Chris Wilson Cc: Ben Widawsky Acked-by: Chris Wilson Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_drv.h | 2 -- drivers/gpu/drm/i915/i915_gem.c | 50 +++++++++++++++--------------- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 11 +++++-- drivers/gpu/drm/i915/i915_gem_stolen.c | 2 +- 4 files changed, 34 insertions(+), 31 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index b6494b24098d..d5cff9718103 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1826,8 +1826,6 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj, struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, size_t size); void i915_gem_free_object(struct drm_gem_object *obj); -struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj, - struct i915_address_space *vm); void i915_gem_vma_destroy(struct i915_vma *vma); int __must_check i915_gem_object_pin(struct drm_i915_gem_object *obj, diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index c4c56f98d6e6..6820d0a1231f 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -4109,8 +4109,19 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) i915_gem_object_free(obj); } -struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj, +struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj, struct i915_address_space *vm) +{ + struct i915_vma *vma; + list_for_each_entry(vma, &obj->vma_list, vma_link) + if (vma->vm == vm) + return vma; + + return NULL; +} + +static struct i915_vma *__i915_gem_vma_create(struct drm_i915_gem_object *obj, + struct i915_address_space *vm) { struct i915_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL); if (vma == NULL) @@ -4131,6 +4142,19 @@ struct i915_vma *i915_gem_vma_create(struct drm_i915_gem_object *obj, return vma; } +struct i915_vma * +i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj, + struct i915_address_space *vm) +{ + struct i915_vma *vma; + + vma = i915_gem_obj_to_vma(obj, vm); + if (!vma) + vma = __i915_gem_vma_create(obj, vm); + + return vma; +} + void i915_gem_vma_destroy(struct i915_vma *vma) { WARN_ON(vma->node.allocated); @@ -4857,27 +4881,3 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o, return 0; } - -struct i915_vma *i915_gem_obj_to_vma(struct drm_i915_gem_object *obj, - struct i915_address_space *vm) -{ - struct i915_vma *vma; - list_for_each_entry(vma, &obj->vma_list, vma_link) - if (vma->vm == vm) - return vma; - - return NULL; -} - -struct i915_vma * -i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj, - struct i915_address_space *vm) -{ - struct i915_vma *vma; - - vma = i915_gem_obj_to_vma(obj, vm); - if (!vma) - vma = i915_gem_vma_create(obj, vm); - - return vma; -} diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 5dcfd4f59f87..93c8b28ff2e1 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -123,11 +123,16 @@ eb_lookup_vmas(struct eb_vmas *eb, list_for_each_entry(obj, &objects, obj_exec_link) { struct i915_vma *vma; + /* + * NOTE: We can leak any vmas created here when something fails + * later on. But that's no issue since vma_unbind can deal with + * vmas which are not actually bound. And since only + * lookup_or_create exists as an interface to get at the vma + * from the (obj, vm) we don't run the risk of creating + * duplicated vmas for the same vm. + */ vma = i915_gem_obj_lookup_or_create_vma(obj, vm); if (IS_ERR(vma)) { - /* XXX: We don't need an error path fro vma because if - * the vma was created just for this execbuf, object - * unreference should kill it off.*/ DRM_DEBUG("Failed to lookup VMA\n"); ret = PTR_ERR(vma); goto out; diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index 9969d10b80f5..b902f2afc8e2 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -392,7 +392,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, if (gtt_offset == I915_GTT_OFFSET_NONE) return obj; - vma = i915_gem_vma_create(obj, ggtt); + vma = i915_gem_obj_lookup_or_create_vma(obj, ggtt); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto err_out; -- cgit v1.2.3-70-g09d2 From aaa0566792dc7ae68deb1959663581ea8c75d311 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Tue, 20 Aug 2013 12:56:40 +0100 Subject: drm/i915: Don't destroy the vma placeholder during execbuffer reservation The execbuffer handle and exec_link were moved from the object into the vma. As the vma may be unbound and destroyed whilst attempting to reserve the execbuffer objects (either through a forced unbind to fix up a misalignment or through an evict-everything call) we need to prevent the free of the i915_vma itself. Otherwise not only is the list of objects to reserve corrupt, but we continue to reference stale vma entries. Fixes kernel crash with i-g-t/gem_evict_everything This regression has been introduced in commit 04038a515d6eda6dd0857c0ade0b3950d372f4c0 Author: Ben Widawsky AuthorDate: Wed Aug 14 11:38:36 2013 +0200 drm/i915: Convert execbuf code to use vmas Reported-by: Dan Carpenter References: http://www.spinics.net/lists/intel-gfx/msg32038.html Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68298 Signed-off-by: Chris Wilson Cc: Ben Widawsky Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 6820d0a1231f..29b7e1c32b84 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -4159,6 +4159,11 @@ void i915_gem_vma_destroy(struct i915_vma *vma) { WARN_ON(vma->node.allocated); list_del(&vma->vma_link); + + /* Keep the vma as a placeholder in the execbuffer reservation lists */ + if (!list_empty(&vma->exec_list)) + return; + kfree(vma); } -- cgit v1.2.3-70-g09d2 From b93dab6e9d286ec2cd95b28078afdfa6dd515205 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 26 Aug 2013 11:23:47 +0200 Subject: drm/i915: More vma fixups around unbind/destroy The important bugfix here is that we must not unlink the vma when we keep it around as a placeholder for the execbuf code. Since then we won't find it again when execbuf gets interrupt and restarted and create a 2nd vma. And since the code as-is isn't fit yet to deal with more than one vma, hilarity ensues. Specifically the dma map/unmap of the sg table isn't adjusted for multiple vmas yet and will blow up like this: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 IP: [] i915_gem_gtt_finish_object+0x73/0xc8 [i915] PGD 56bb5067 PUD ad3dd067 PMD 0 Oops: 0000 [#1] SMP Modules linked in: tcp_lp ppdev parport_pc lp parport ipv6 dm_mod dcdbas snd_hda_codec_hdmi pcspkr snd_hda_codec_realtek serio_raw i2c_i801 iTCO_wdt iTCO_vendor_support snd_hda_intel snd_hda_codec lpc_ich snd_hwdep mfd_core snd_pcm snd_page_alloc snd_timer snd soundcore acpi_cpufreq i915 video button drm_kms_helper drm mperf freq_table CPU: 1 PID: 16650 Comm: fbo-maxsize Not tainted 3.11.0-rc4_nightlytop_d93f59_debug_20130814_+ #6957 Hardware name: Dell Inc. OptiPlex 9010/03JR84, BIOS A01 05/04/2012 task: ffff8800563b3f00 ti: ffff88004bdf4000 task.ti: ffff88004bdf4000 RIP: 0010:[] [] i915_gem_gtt_finish_object+0x73/0xc8 [i915] RSP: 0018:ffff88004bdf5958 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8801135e0000 RCX: ffff8800ad3bf8e0 RDX: ffff8800ad3bf8e0 RSI: 0000000000000000 RDI: ffff8801007ee780 RBP: ffff88004bdf5978 R08: ffff8800ad3bf8e0 R09: 0000000000000000 R10: ffffffff86ca1810 R11: ffff880036a17101 R12: ffff8801007ee780 R13: 0000000000018001 R14: ffff880118c4e000 R15: ffff8801007ee780 FS: 00007f401a0ce740(0000) GS:ffff88011e280000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000005635c000 CR4: 00000000001407e0 Stack: ffff8801007ee780 ffff88005c253180 0000000000018000 ffff8801135e0000 ffff88004bdf59a8 ffffffffa0088e55 0000000000000011 ffff8801007eec00 0000000000018000 ffff880036a17101 ffff88004bdf5a08 ffffffffa0089026 Call Trace: [] i915_vma_unbind+0xdf/0x1ab [i915] [] __i915_gem_shrink+0x105/0x177 [i915] [] i915_gem_object_get_pages_gtt+0x108/0x309 [i915] [] i915_gem_object_get_pages+0x61/0x90 [i915] [] ? gen6_ppgtt_insert_entries+0x103/0x125 [i915] [] i915_gem_object_pin+0x1fa/0x5df [i915] [] i915_gem_execbuffer_reserve_object.isra.6+0x8d/0x1bc [i915] [] i915_gem_execbuffer_reserve+0x229/0x367 [i915] [] i915_gem_do_execbuffer.isra.12+0x4dc/0xf3a [i915] [] ? might_fault+0x40/0x90 [] i915_gem_execbuffer2+0x187/0x222 [i915] [] drm_ioctl+0x308/0x442 [drm] [] ? i915_gem_execbuffer+0x3ae/0x3ae [i915] [] ? __do_page_fault+0x3dd/0x481 [] vfs_ioctl+0x26/0x39 [] do_vfs_ioctl+0x40e/0x451 [] ? sysret_check+0x1b/0x56 [] SyS_ioctl+0x57/0x87 [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] system_call_fastpath+0x16/0x1b Code: 48 c7 c6 84 30 0e a0 31 c0 e8 d0 e9 f7 ff bf c6 a7 00 00 e8 07 af 2c e1 41 f6 84 24 03 01 00 00 10 75 44 49 8b 84 24 08 01 00 00 <8b> 50 08 48 8b 30 49 8b 86 b0 04 00 00 48 89 c7 48 81 c7 98 00 RIP [] i915_gem_gtt_finish_object+0x73/0xc8 [i915] RSP CR2: 0000000000000008 As a consequence we need to change the "only one vma for now" check in vma_unbind - since vma_destroy isn't always called the obj->vma_list might not be empty. Instead check that the vma list is singular at the beginning of vma_unbind. This is also more symmetric with bind_to_vm. This fixes the igt/gem_evict_everything|alignment testcases. v2: - Add a paranoid WARN to mark_free in the eviction code to make sure we never try to evict a vma used by the execbuf code right now. - Move the check for a temporary execbuf vma into vma_destroy - otherwise the failure path cleanup in bind_to_vm will blow up. Our first attempting at fixing this was commit 1be81a2f2cfd8789a627401d470423358fba2d76 Author: Chris Wilson Date: Tue Aug 20 12:56:40 2013 +0100 drm/i915: Don't destroy the vma placeholder during execbuffer reservation Squash with this when merging! v3: Improvements suggested in Chris' review: - Move the WARN_ON in vma_destroy that checks for vmas with an drm_mm allocation before the early return. - Bail out if we hit the WARN in mark_free to hopefully make the kernel survive for long enough to capture it. Cc: Chris Wilson Cc: Ben Widawsky Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68298 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68171 Tested-by: lu hua (v2) Reviewed-by: Chris Wilson Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem.c | 10 ++++++---- drivers/gpu/drm/i915/i915_gem_evict.c | 3 +++ 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 29b7e1c32b84..d57368d5fc1d 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2604,6 +2604,9 @@ int i915_vma_unbind(struct i915_vma *vma) drm_i915_private_t *dev_priv = obj->base.dev->dev_private; int ret; + /* For now we only ever use 1 vma per object */ + WARN_ON(!list_is_singular(&obj->vma_list)); + if (list_empty(&vma->vma_link)) return 0; @@ -2652,9 +2655,7 @@ destroy: i915_gem_vma_destroy(vma); /* Since the unbound list is global, only move to that list if - * no more VMAs exist. - * NB: Until we have real VMAs there will only ever be one */ - WARN_ON(!list_empty(&obj->vma_list)); + * no more VMAs exist. */ if (list_empty(&obj->vma_list)) list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list); @@ -4158,12 +4159,13 @@ i915_gem_obj_lookup_or_create_vma(struct drm_i915_gem_object *obj, void i915_gem_vma_destroy(struct i915_vma *vma) { WARN_ON(vma->node.allocated); - list_del(&vma->vma_link); /* Keep the vma as a placeholder in the execbuffer reservation lists */ if (!list_empty(&vma->exec_list)) return; + list_del(&vma->vma_link); + kfree(vma); } diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 91b700155850..cc8974fbcf31 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -37,6 +37,9 @@ mark_free(struct i915_vma *vma, struct list_head *unwind) if (vma->obj->pin_count) return false; + if (WARN_ON(!list_empty(&vma->exec_list))) + return false; + list_add(&vma->exec_list, unwind); return drm_mm_scan_add_block(&vma->node); } -- cgit v1.2.3-70-g09d2 From 2cc86b826070cf312d7b0571e383c56d31a1fe5c Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 26 Aug 2013 19:51:00 -0300 Subject: drm/i915: Always prefer CPU relocations with LLC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A follow-on to the update of the LLC coherency logic is that we can rely on the LLC being coherent with the CS for rewriting batchbuffers irrespective of their cache domain. (This should have no effect currently as all the batch buffers are expected to be I915_CACHE_LLC and so using the cpu relocation path anyway.) Signed-off-by: Chris Wilson Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_execbuffer.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 93c8b28ff2e1..e519f9f6e5cd 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -202,7 +202,8 @@ static void eb_destroy(struct eb_vmas *eb) { static inline int use_cpu_reloc(struct drm_i915_gem_object *obj) { - return (obj->base.write_domain == I915_GEM_DOMAIN_CPU || + return (HAS_LLC(obj->base.dev) || + obj->base.write_domain == I915_GEM_DOMAIN_CPU || !obj->map_and_fenceable || obj->cache_level != I915_CACHE_NONE); } @@ -215,7 +216,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj, char *vaddr; int ret = -EINVAL; - ret = i915_gem_object_set_to_cpu_domain(obj, 1); + ret = i915_gem_object_set_to_cpu_domain(obj, true); if (ret) return ret; -- cgit v1.2.3-70-g09d2 From b89232732f642bfa24f9e252dd241ddfb40d3817 Mon Sep 17 00:00:00 2001 From: Shobhit Kumar Date: Tue, 27 Aug 2013 15:12:13 +0300 Subject: drm: add MIPI DSI encoder and connector types MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Shobhit Kumar Signed-off-by: Jani Nikula Acked-by: Dave Airlie Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/drm_crtc.c | 2 ++ include/uapi/drm/drm_mode.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index bff2fa941f60..e79577cb4665 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -202,6 +202,7 @@ static struct drm_conn_prop_enum_list drm_connector_enum_list[] = { DRM_MODE_CONNECTOR_TV, "TV" }, { DRM_MODE_CONNECTOR_eDP, "eDP" }, { DRM_MODE_CONNECTOR_VIRTUAL, "Virtual" }, + { DRM_MODE_CONNECTOR_DSI, "DSI" }, }; static const struct drm_prop_enum_list drm_encoder_enum_list[] = @@ -211,6 +212,7 @@ static const struct drm_prop_enum_list drm_encoder_enum_list[] = { DRM_MODE_ENCODER_LVDS, "LVDS" }, { DRM_MODE_ENCODER_TVDAC, "TV" }, { DRM_MODE_ENCODER_VIRTUAL, "Virtual" }, + { DRM_MODE_ENCODER_DSI, "DSI" }, }; void drm_connector_ida_init(void) diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 550811712f78..113d32457fa4 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -165,6 +165,7 @@ struct drm_mode_get_plane_res { #define DRM_MODE_ENCODER_LVDS 3 #define DRM_MODE_ENCODER_TVDAC 4 #define DRM_MODE_ENCODER_VIRTUAL 5 +#define DRM_MODE_ENCODER_DSI 6 struct drm_mode_get_encoder { __u32 encoder_id; @@ -203,6 +204,7 @@ struct drm_mode_get_encoder { #define DRM_MODE_CONNECTOR_TV 13 #define DRM_MODE_CONNECTOR_eDP 14 #define DRM_MODE_CONNECTOR_VIRTUAL 15 +#define DRM_MODE_CONNECTOR_DSI 16 struct drm_mode_get_connector { -- cgit v1.2.3-70-g09d2 From e9f882a3f1e4ffabe0730af16d5f6d51737515a5 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 27 Aug 2013 15:12:14 +0300 Subject: drm/i915: add more VLV IOSF sideband ports accessors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For GPIO NC, CCK, CCU, and GPS CORE. Signed-off-by: Jani Nikula Signed-off-by: Shobhit Kumar Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_drv.h | 8 +++++ drivers/gpu/drm/i915/i915_reg.h | 4 +++ drivers/gpu/drm/i915/intel_sideband.c | 56 +++++++++++++++++++++++++++++++++++ 3 files changed, 68 insertions(+) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index d5cff9718103..e2628579dcbe 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2248,6 +2248,14 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val) u32 vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr); void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val); u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr); +u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg); +void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val); +u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg); +void vlv_cck_write(struct drm_i915_private *dev_priv, u32 reg, u32 val); +u32 vlv_ccu_read(struct drm_i915_private *dev_priv, u32 reg); +void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val); +u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg); +void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val); u32 vlv_dpio_read(struct drm_i915_private *dev_priv, int reg); void vlv_dpio_write(struct drm_i915_private *dev_priv, int reg, u32 val); u32 intel_sbi_read(struct drm_i915_private *dev_priv, u16 reg, diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index c159e1a6810f..8f4c8b69ebc1 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -346,6 +346,10 @@ #define IOSF_PORT_PUNIT 0x4 #define IOSF_PORT_NC 0x11 #define IOSF_PORT_DPIO 0x12 +#define IOSF_PORT_GPIO_NC 0x13 +#define IOSF_PORT_CCK 0x14 +#define IOSF_PORT_CCU 0xA9 +#define IOSF_PORT_GPS_CORE 0x48 #define VLV_IOSF_DATA (VLV_DISPLAY_BASE + 0x2104) #define VLV_IOSF_ADDR (VLV_DISPLAY_BASE + 0x2108) diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index 9a0e6c5ea540..0a4167019769 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -101,6 +101,62 @@ u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr) return val; } +u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg) +{ + u32 val = 0; + vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC, + PUNIT_OPCODE_REG_READ, reg, &val); + return val; +} + +void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) +{ + vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC, + PUNIT_OPCODE_REG_WRITE, reg, &val); +} + +u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg) +{ + u32 val = 0; + vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK, + PUNIT_OPCODE_REG_READ, reg, &val); + return val; +} + +void vlv_cck_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) +{ + vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK, + PUNIT_OPCODE_REG_WRITE, reg, &val); +} + +u32 vlv_ccu_read(struct drm_i915_private *dev_priv, u32 reg) +{ + u32 val = 0; + vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU, + PUNIT_OPCODE_REG_READ, reg, &val); + return val; +} + +void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) +{ + vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU, + PUNIT_OPCODE_REG_WRITE, reg, &val); +} + +u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg) +{ + u32 val = 0; + vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE, + PUNIT_OPCODE_REG_READ, reg, &val); + return val; +} + +void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) +{ + vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE, + PUNIT_OPCODE_REG_WRITE, reg, &val); +} + u32 vlv_dpio_read(struct drm_i915_private *dev_priv, int reg) { u32 val = 0; -- cgit v1.2.3-70-g09d2 From b6ec10b36566c3eb330f4c03c1b00a02c974fd21 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 27 Aug 2013 15:12:15 +0300 Subject: drm/i915: add VLV pipeconf bit definition for DSI PLL lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit v2: Add comment this is pipe A only (Ville) Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_reg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 8f4c8b69ebc1..7a7b9c2f84cb 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2986,6 +2986,7 @@ #define PIPECONF_DISABLE 0 #define PIPECONF_DOUBLE_WIDE (1<<30) #define I965_PIPECONF_ACTIVE (1<<30) +#define PIPECONF_DSI_PLL_LOCKED (1<<29) /* vlv & pipe A only */ #define PIPECONF_FRAME_START_DELAY_MASK (3<<27) #define PIPECONF_SINGLE_WIDE 0 #define PIPECONF_PIPE_UNLOCKED 0 -- cgit v1.2.3-70-g09d2 From 3230bf14c14e04d49525d172db53a55e153447a7 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 27 Aug 2013 15:12:16 +0300 Subject: drm/i915: add MIPI DSI register definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add definitions for VLV MIPI DSI registers. v2: Small fixes per Ville's review comments. Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_reg.h | 410 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 410 insertions(+) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 7a7b9c2f84cb..b26cf9b5b1e4 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -5121,4 +5121,414 @@ #define PIPE_CSC_POSTOFF_ME(pipe) _PIPE(pipe, _PIPE_A_CSC_POSTOFF_ME, _PIPE_B_CSC_POSTOFF_ME) #define PIPE_CSC_POSTOFF_LO(pipe) _PIPE(pipe, _PIPE_A_CSC_POSTOFF_LO, _PIPE_B_CSC_POSTOFF_LO) +/* VLV MIPI registers */ + +#define _MIPIA_PORT_CTRL (VLV_DISPLAY_BASE + 0x61190) +#define _MIPIB_PORT_CTRL (VLV_DISPLAY_BASE + 0x61700) +#define MIPI_PORT_CTRL(pipe) _PIPE(pipe, _MIPIA_PORT_CTRL, _MIPIB_PORT_CTRL) +#define DPI_ENABLE (1 << 31) /* A + B */ +#define MIPIA_MIPI4DPHY_DELAY_COUNT_SHIFT 27 +#define MIPIA_MIPI4DPHY_DELAY_COUNT_MASK (0xf << 27) +#define DUAL_LINK_MODE_MASK (1 << 26) +#define DUAL_LINK_MODE_FRONT_BACK (0 << 26) +#define DUAL_LINK_MODE_PIXEL_ALTERNATIVE (1 << 26) +#define DITHERING_ENABLE (1 << 25) /* A + B */ +#define FLOPPED_HSTX (1 << 23) +#define DE_INVERT (1 << 19) /* XXX */ +#define MIPIA_FLISDSI_DELAY_COUNT_SHIFT 18 +#define MIPIA_FLISDSI_DELAY_COUNT_MASK (0xf << 18) +#define AFE_LATCHOUT (1 << 17) +#define LP_OUTPUT_HOLD (1 << 16) +#define MIPIB_FLISDSI_DELAY_COUNT_HIGH_SHIFT 15 +#define MIPIB_FLISDSI_DELAY_COUNT_HIGH_MASK (1 << 15) +#define MIPIB_MIPI4DPHY_DELAY_COUNT_SHIFT 11 +#define MIPIB_MIPI4DPHY_DELAY_COUNT_MASK (0xf << 11) +#define CSB_SHIFT 9 +#define CSB_MASK (3 << 9) +#define CSB_20MHZ (0 << 9) +#define CSB_10MHZ (1 << 9) +#define CSB_40MHZ (2 << 9) +#define BANDGAP_MASK (1 << 8) +#define BANDGAP_PNW_CIRCUIT (0 << 8) +#define BANDGAP_LNC_CIRCUIT (1 << 8) +#define MIPIB_FLISDSI_DELAY_COUNT_LOW_SHIFT 5 +#define MIPIB_FLISDSI_DELAY_COUNT_LOW_MASK (7 << 5) +#define TEARING_EFFECT_DELAY (1 << 4) /* A + B */ +#define TEARING_EFFECT_SHIFT 2 /* A + B */ +#define TEARING_EFFECT_MASK (3 << 2) +#define TEARING_EFFECT_OFF (0 << 2) +#define TEARING_EFFECT_DSI (1 << 2) +#define TEARING_EFFECT_GPIO (2 << 2) +#define LANE_CONFIGURATION_SHIFT 0 +#define LANE_CONFIGURATION_MASK (3 << 0) +#define LANE_CONFIGURATION_4LANE (0 << 0) +#define LANE_CONFIGURATION_DUAL_LINK_A (1 << 0) +#define LANE_CONFIGURATION_DUAL_LINK_B (2 << 0) + +#define _MIPIA_TEARING_CTRL (VLV_DISPLAY_BASE + 0x61194) +#define _MIPIB_TEARING_CTRL (VLV_DISPLAY_BASE + 0x61704) +#define MIPI_TEARING_CTRL(pipe) _PIPE(pipe, _MIPIA_TEARING_CTRL, _MIPIB_TEARING_CTRL) +#define TEARING_EFFECT_DELAY_SHIFT 0 +#define TEARING_EFFECT_DELAY_MASK (0xffff << 0) + +/* XXX: all bits reserved */ +#define _MIPIA_AUTOPWG (VLV_DISPLAY_BASE + 0x611a0) + +/* MIPI DSI Controller and D-PHY registers */ + +#define _MIPIA_DEVICE_READY (VLV_DISPLAY_BASE + 0xb000) +#define _MIPIB_DEVICE_READY (VLV_DISPLAY_BASE + 0xb800) +#define MIPI_DEVICE_READY(pipe) _PIPE(pipe, _MIPIA_DEVICE_READY, _MIPIB_DEVICE_READY) +#define BUS_POSSESSION (1 << 3) /* set to give bus to receiver */ +#define ULPS_STATE_MASK (3 << 1) +#define ULPS_STATE_ENTER (2 << 1) +#define ULPS_STATE_EXIT (1 << 1) +#define ULPS_STATE_NORMAL_OPERATION (0 << 1) +#define DEVICE_READY (1 << 0) + +#define _MIPIA_INTR_STAT (VLV_DISPLAY_BASE + 0xb004) +#define _MIPIB_INTR_STAT (VLV_DISPLAY_BASE + 0xb804) +#define MIPI_INTR_STAT(pipe) _PIPE(pipe, _MIPIA_INTR_STAT, _MIPIB_INTR_STAT) +#define _MIPIA_INTR_EN (VLV_DISPLAY_BASE + 0xb008) +#define _MIPIB_INTR_EN (VLV_DISPLAY_BASE + 0xb808) +#define MIPI_INTR_EN(pipe) _PIPE(pipe, _MIPIA_INTR_EN, _MIPIB_INTR_EN) +#define TEARING_EFFECT (1 << 31) +#define SPL_PKT_SENT_INTERRUPT (1 << 30) +#define GEN_READ_DATA_AVAIL (1 << 29) +#define LP_GENERIC_WR_FIFO_FULL (1 << 28) +#define HS_GENERIC_WR_FIFO_FULL (1 << 27) +#define RX_PROT_VIOLATION (1 << 26) +#define RX_INVALID_TX_LENGTH (1 << 25) +#define ACK_WITH_NO_ERROR (1 << 24) +#define TURN_AROUND_ACK_TIMEOUT (1 << 23) +#define LP_RX_TIMEOUT (1 << 22) +#define HS_TX_TIMEOUT (1 << 21) +#define DPI_FIFO_UNDERRUN (1 << 20) +#define LOW_CONTENTION (1 << 19) +#define HIGH_CONTENTION (1 << 18) +#define TXDSI_VC_ID_INVALID (1 << 17) +#define TXDSI_DATA_TYPE_NOT_RECOGNISED (1 << 16) +#define TXCHECKSUM_ERROR (1 << 15) +#define TXECC_MULTIBIT_ERROR (1 << 14) +#define TXECC_SINGLE_BIT_ERROR (1 << 13) +#define TXFALSE_CONTROL_ERROR (1 << 12) +#define RXDSI_VC_ID_INVALID (1 << 11) +#define RXDSI_DATA_TYPE_NOT_REGOGNISED (1 << 10) +#define RXCHECKSUM_ERROR (1 << 9) +#define RXECC_MULTIBIT_ERROR (1 << 8) +#define RXECC_SINGLE_BIT_ERROR (1 << 7) +#define RXFALSE_CONTROL_ERROR (1 << 6) +#define RXHS_RECEIVE_TIMEOUT_ERROR (1 << 5) +#define RX_LP_TX_SYNC_ERROR (1 << 4) +#define RXEXCAPE_MODE_ENTRY_ERROR (1 << 3) +#define RXEOT_SYNC_ERROR (1 << 2) +#define RXSOT_SYNC_ERROR (1 << 1) +#define RXSOT_ERROR (1 << 0) + +#define _MIPIA_DSI_FUNC_PRG (VLV_DISPLAY_BASE + 0xb00c) +#define _MIPIB_DSI_FUNC_PRG (VLV_DISPLAY_BASE + 0xb80c) +#define MIPI_DSI_FUNC_PRG(pipe) _PIPE(pipe, _MIPIA_DSI_FUNC_PRG, _MIPIB_DSI_FUNC_PRG) +#define CMD_MODE_DATA_WIDTH_MASK (7 << 13) +#define CMD_MODE_NOT_SUPPORTED (0 << 13) +#define CMD_MODE_DATA_WIDTH_16_BIT (1 << 13) +#define CMD_MODE_DATA_WIDTH_9_BIT (2 << 13) +#define CMD_MODE_DATA_WIDTH_8_BIT (3 << 13) +#define CMD_MODE_DATA_WIDTH_OPTION1 (4 << 13) +#define CMD_MODE_DATA_WIDTH_OPTION2 (5 << 13) +#define VID_MODE_FORMAT_MASK (0xf << 7) +#define VID_MODE_NOT_SUPPORTED (0 << 7) +#define VID_MODE_FORMAT_RGB565 (1 << 7) +#define VID_MODE_FORMAT_RGB666 (2 << 7) +#define VID_MODE_FORMAT_RGB666_LOOSE (3 << 7) +#define VID_MODE_FORMAT_RGB888 (4 << 7) +#define CMD_MODE_CHANNEL_NUMBER_SHIFT 5 +#define CMD_MODE_CHANNEL_NUMBER_MASK (3 << 5) +#define VID_MODE_CHANNEL_NUMBER_SHIFT 3 +#define VID_MODE_CHANNEL_NUMBER_MASK (3 << 3) +#define DATA_LANES_PRG_REG_SHIFT 0 +#define DATA_LANES_PRG_REG_MASK (7 << 0) + +#define _MIPIA_HS_TX_TIMEOUT (VLV_DISPLAY_BASE + 0xb010) +#define _MIPIB_HS_TX_TIMEOUT (VLV_DISPLAY_BASE + 0xb810) +#define MIPI_HS_TX_TIMEOUT(pipe) _PIPE(pipe, _MIPIA_HS_TX_TIMEOUT, _MIPIB_HS_TX_TIMEOUT) +#define HIGH_SPEED_TX_TIMEOUT_COUNTER_MASK 0xffffff + +#define _MIPIA_LP_RX_TIMEOUT (VLV_DISPLAY_BASE + 0xb014) +#define _MIPIB_LP_RX_TIMEOUT (VLV_DISPLAY_BASE + 0xb814) +#define MIPI_LP_RX_TIMEOUT(pipe) _PIPE(pipe, _MIPIA_LP_RX_TIMEOUT, _MIPIB_LP_RX_TIMEOUT) +#define LOW_POWER_RX_TIMEOUT_COUNTER_MASK 0xffffff + +#define _MIPIA_TURN_AROUND_TIMEOUT (VLV_DISPLAY_BASE + 0xb018) +#define _MIPIB_TURN_AROUND_TIMEOUT (VLV_DISPLAY_BASE + 0xb818) +#define MIPI_TURN_AROUND_TIMEOUT(pipe) _PIPE(pipe, _MIPIA_TURN_AROUND_TIMEOUT, _MIPIB_TURN_AROUND_TIMEOUT) +#define TURN_AROUND_TIMEOUT_MASK 0x3f + +#define _MIPIA_DEVICE_RESET_TIMER (VLV_DISPLAY_BASE + 0xb01c) +#define _MIPIB_DEVICE_RESET_TIMER (VLV_DISPLAY_BASE + 0xb81c) +#define MIPI_DEVICE_RESET_TIMER(pipe) _PIPE(pipe, _MIPIA_DEVICE_RESET_TIMER, _MIPIB_DEVICE_RESET_TIMER) +#define DEVICE_RESET_TIMER_MASK 0xffff + +#define _MIPIA_DPI_RESOLUTION (VLV_DISPLAY_BASE + 0xb020) +#define _MIPIB_DPI_RESOLUTION (VLV_DISPLAY_BASE + 0xb820) +#define MIPI_DPI_RESOLUTION(pipe) _PIPE(pipe, _MIPIA_DPI_RESOLUTION, _MIPIB_DPI_RESOLUTION) +#define VERTICAL_ADDRESS_SHIFT 16 +#define VERTICAL_ADDRESS_MASK (0xffff << 16) +#define HORIZONTAL_ADDRESS_SHIFT 0 +#define HORIZONTAL_ADDRESS_MASK 0xffff + +#define _MIPIA_DBI_FIFO_THROTTLE (VLV_DISPLAY_BASE + 0xb024) +#define _MIPIB_DBI_FIFO_THROTTLE (VLV_DISPLAY_BASE + 0xb824) +#define MIPI_DBI_FIFO_THROTTLE(pipe) _PIPE(pipe, _MIPIA_DBI_FIFO_THROTTLE, _MIPIB_DBI_FIFO_THROTTLE) +#define DBI_FIFO_EMPTY_HALF (0 << 0) +#define DBI_FIFO_EMPTY_QUARTER (1 << 0) +#define DBI_FIFO_EMPTY_7_LOCATIONS (2 << 0) + +/* regs below are bits 15:0 */ +#define _MIPIA_HSYNC_PADDING_COUNT (VLV_DISPLAY_BASE + 0xb028) +#define _MIPIB_HSYNC_PADDING_COUNT (VLV_DISPLAY_BASE + 0xb828) +#define MIPI_HSYNC_PADDING_COUNT(pipe) _PIPE(pipe, _MIPIA_HSYNC_PADDING_COUNT, _MIPIB_HSYNC_PADDING_COUNT) + +#define _MIPIA_HBP_COUNT (VLV_DISPLAY_BASE + 0xb02c) +#define _MIPIB_HBP_COUNT (VLV_DISPLAY_BASE + 0xb82c) +#define MIPI_HBP_COUNT(pipe) _PIPE(pipe, _MIPIA_HBP_COUNT, _MIPIB_HBP_COUNT) + +#define _MIPIA_HFP_COUNT (VLV_DISPLAY_BASE + 0xb030) +#define _MIPIB_HFP_COUNT (VLV_DISPLAY_BASE + 0xb830) +#define MIPI_HFP_COUNT(pipe) _PIPE(pipe, _MIPIA_HFP_COUNT, _MIPIB_HFP_COUNT) + +#define _MIPIA_HACTIVE_AREA_COUNT (VLV_DISPLAY_BASE + 0xb034) +#define _MIPIB_HACTIVE_AREA_COUNT (VLV_DISPLAY_BASE + 0xb834) +#define MIPI_HACTIVE_AREA_COUNT(pipe) _PIPE(pipe, _MIPIA_HACTIVE_AREA_COUNT, _MIPIB_HACTIVE_AREA_COUNT) + +#define _MIPIA_VSYNC_PADDING_COUNT (VLV_DISPLAY_BASE + 0xb038) +#define _MIPIB_VSYNC_PADDING_COUNT (VLV_DISPLAY_BASE + 0xb838) +#define MIPI_VSYNC_PADDING_COUNT(pipe) _PIPE(pipe, _MIPIA_VSYNC_PADDING_COUNT, _MIPIB_VSYNC_PADDING_COUNT) + +#define _MIPIA_VBP_COUNT (VLV_DISPLAY_BASE + 0xb03c) +#define _MIPIB_VBP_COUNT (VLV_DISPLAY_BASE + 0xb83c) +#define MIPI_VBP_COUNT(pipe) _PIPE(pipe, _MIPIA_VBP_COUNT, _MIPIB_VBP_COUNT) + +#define _MIPIA_VFP_COUNT (VLV_DISPLAY_BASE + 0xb040) +#define _MIPIB_VFP_COUNT (VLV_DISPLAY_BASE + 0xb840) +#define MIPI_VFP_COUNT(pipe) _PIPE(pipe, _MIPIA_VFP_COUNT, _MIPIB_VFP_COUNT) + +#define _MIPIA_HIGH_LOW_SWITCH_COUNT (VLV_DISPLAY_BASE + 0xb044) +#define _MIPIB_HIGH_LOW_SWITCH_COUNT (VLV_DISPLAY_BASE + 0xb844) +#define MIPI_HIGH_LOW_SWITCH_COUNT(pipe) _PIPE(pipe, _MIPIA_HIGH_LOW_SWITCH_COUNT, _MIPIB_HIGH_LOW_SWITCH_COUNT) +/* regs above are bits 15:0 */ + +#define _MIPIA_DPI_CONTROL (VLV_DISPLAY_BASE + 0xb048) +#define _MIPIB_DPI_CONTROL (VLV_DISPLAY_BASE + 0xb848) +#define MIPI_DPI_CONTROL(pipe) _PIPE(pipe, _MIPIA_DPI_CONTROL, _MIPIB_DPI_CONTROL) +#define DPI_LP_MODE (1 << 6) +#define BACKLIGHT_OFF (1 << 5) +#define BACKLIGHT_ON (1 << 4) +#define COLOR_MODE_OFF (1 << 3) +#define COLOR_MODE_ON (1 << 2) +#define TURN_ON (1 << 1) +#define SHUTDOWN (1 << 0) + +#define _MIPIA_DPI_DATA (VLV_DISPLAY_BASE + 0xb04c) +#define _MIPIB_DPI_DATA (VLV_DISPLAY_BASE + 0xb84c) +#define MIPI_DPI_DATA(pipe) _PIPE(pipe, _MIPIA_DPI_DATA, _MIPIB_DPI_DATA) +#define COMMAND_BYTE_SHIFT 0 +#define COMMAND_BYTE_MASK (0x3f << 0) + +#define _MIPIA_INIT_COUNT (VLV_DISPLAY_BASE + 0xb050) +#define _MIPIB_INIT_COUNT (VLV_DISPLAY_BASE + 0xb850) +#define MIPI_INIT_COUNT(pipe) _PIPE(pipe, _MIPIA_INIT_COUNT, _MIPIB_INIT_COUNT) +#define MASTER_INIT_TIMER_SHIFT 0 +#define MASTER_INIT_TIMER_MASK (0xffff << 0) + +#define _MIPIA_MAX_RETURN_PKT_SIZE (VLV_DISPLAY_BASE + 0xb054) +#define _MIPIB_MAX_RETURN_PKT_SIZE (VLV_DISPLAY_BASE + 0xb854) +#define MIPI_MAX_RETURN_PKT_SIZE(pipe) _PIPE(pipe, _MIPIA_MAX_RETURN_PKT_SIZE, _MIPIB_MAX_RETURN_PKT_SIZE) +#define MAX_RETURN_PKT_SIZE_SHIFT 0 +#define MAX_RETURN_PKT_SIZE_MASK (0x3ff << 0) + +#define _MIPIA_VIDEO_MODE_FORMAT (VLV_DISPLAY_BASE + 0xb058) +#define _MIPIB_VIDEO_MODE_FORMAT (VLV_DISPLAY_BASE + 0xb858) +#define MIPI_VIDEO_MODE_FORMAT(pipe) _PIPE(pipe, _MIPIA_VIDEO_MODE_FORMAT, _MIPIB_VIDEO_MODE_FORMAT) +#define RANDOM_DPI_DISPLAY_RESOLUTION (1 << 4) +#define DISABLE_VIDEO_BTA (1 << 3) +#define IP_TG_CONFIG (1 << 2) +#define VIDEO_MODE_NON_BURST_WITH_SYNC_PULSE (1 << 0) +#define VIDEO_MODE_NON_BURST_WITH_SYNC_EVENTS (2 << 0) +#define VIDEO_MODE_BURST (3 << 0) + +#define _MIPIA_EOT_DISABLE (VLV_DISPLAY_BASE + 0xb05c) +#define _MIPIB_EOT_DISABLE (VLV_DISPLAY_BASE + 0xb85c) +#define MIPI_EOT_DISABLE(pipe) _PIPE(pipe, _MIPIA_EOT_DISABLE, _MIPIB_EOT_DISABLE) +#define LP_RX_TIMEOUT_ERROR_RECOVERY_DISABLE (1 << 7) +#define HS_RX_TIMEOUT_ERROR_RECOVERY_DISABLE (1 << 6) +#define LOW_CONTENTION_RECOVERY_DISABLE (1 << 5) +#define HIGH_CONTENTION_RECOVERY_DISABLE (1 << 4) +#define TXDSI_TYPE_NOT_RECOGNISED_ERROR_RECOVERY_DISABLE (1 << 3) +#define TXECC_MULTIBIT_ERROR_RECOVERY_DISABLE (1 << 2) +#define CLOCKSTOP (1 << 1) +#define EOT_DISABLE (1 << 0) + +#define _MIPIA_LP_BYTECLK (VLV_DISPLAY_BASE + 0xb060) +#define _MIPIB_LP_BYTECLK (VLV_DISPLAY_BASE + 0xb860) +#define MIPI_LP_BYTECLK(pipe) _PIPE(pipe, _MIPIA_LP_BYTECLK, _MIPIB_LP_BYTECLK) +#define LP_BYTECLK_SHIFT 0 +#define LP_BYTECLK_MASK (0xffff << 0) + +/* bits 31:0 */ +#define _MIPIA_LP_GEN_DATA (VLV_DISPLAY_BASE + 0xb064) +#define _MIPIB_LP_GEN_DATA (VLV_DISPLAY_BASE + 0xb864) +#define MIPI_LP_GEN_DATA(pipe) _PIPE(pipe, _MIPIA_LP_GEN_DATA, _MIPIB_LP_GEN_DATA) + +/* bits 31:0 */ +#define _MIPIA_HS_GEN_DATA (VLV_DISPLAY_BASE + 0xb068) +#define _MIPIB_HS_GEN_DATA (VLV_DISPLAY_BASE + 0xb868) +#define MIPI_HS_GEN_DATA(pipe) _PIPE(pipe, _MIPIA_HS_GEN_DATA, _MIPIB_HS_GEN_DATA) + +#define _MIPIA_LP_GEN_CTRL (VLV_DISPLAY_BASE + 0xb06c) +#define _MIPIB_LP_GEN_CTRL (VLV_DISPLAY_BASE + 0xb86c) +#define MIPI_LP_GEN_CTRL(pipe) _PIPE(pipe, _MIPIA_LP_GEN_CTRL, _MIPIB_LP_GEN_CTRL) +#define _MIPIA_HS_GEN_CTRL (VLV_DISPLAY_BASE + 0xb070) +#define _MIPIB_HS_GEN_CTRL (VLV_DISPLAY_BASE + 0xb870) +#define MIPI_HS_GEN_CTRL(pipe) _PIPE(pipe, _MIPIA_HS_GEN_CTRL, _MIPIB_HS_GEN_CTRL) +#define LONG_PACKET_WORD_COUNT_SHIFT 8 +#define LONG_PACKET_WORD_COUNT_MASK (0xffff << 8) +#define SHORT_PACKET_PARAM_SHIFT 8 +#define SHORT_PACKET_PARAM_MASK (0xffff << 8) +#define VIRTUAL_CHANNEL_SHIFT 6 +#define VIRTUAL_CHANNEL_MASK (3 << 6) +#define DATA_TYPE_SHIFT 0 +#define DATA_TYPE_MASK (3f << 0) +/* data type values, see include/video/mipi_display.h */ + +#define _MIPIA_GEN_FIFO_STAT (VLV_DISPLAY_BASE + 0xb074) +#define _MIPIB_GEN_FIFO_STAT (VLV_DISPLAY_BASE + 0xb874) +#define MIPI_GEN_FIFO_STAT(pipe) _PIPE(pipe, _MIPIA_GEN_FIFO_STAT, _MIPIB_GEN_FIFO_STAT) +#define DPI_FIFO_EMPTY (1 << 28) +#define DBI_FIFO_EMPTY (1 << 27) +#define LP_CTRL_FIFO_EMPTY (1 << 26) +#define LP_CTRL_FIFO_HALF_EMPTY (1 << 25) +#define LP_CTRL_FIFO_FULL (1 << 24) +#define HS_CTRL_FIFO_EMPTY (1 << 18) +#define HS_CTRL_FIFO_HALF_EMPTY (1 << 17) +#define HS_CTRL_FIFO_FULL (1 << 16) +#define LP_DATA_FIFO_EMPTY (1 << 10) +#define LP_DATA_FIFO_HALF_EMPTY (1 << 9) +#define LP_DATA_FIFO_FULL (1 << 8) +#define HS_DATA_FIFO_EMPTY (1 << 2) +#define HS_DATA_FIFO_HALF_EMPTY (1 << 1) +#define HS_DATA_FIFO_FULL (1 << 0) + +#define _MIPIA_HS_LS_DBI_ENABLE (VLV_DISPLAY_BASE + 0xb078) +#define _MIPIB_HS_LS_DBI_ENABLE (VLV_DISPLAY_BASE + 0xb878) +#define MIPI_HS_LP_DBI_ENABLE(pipe) _PIPE(pipe, _MIPIA_HS_LS_DBI_ENABLE, _MIPIB_HS_LS_DBI_ENABLE) +#define DBI_HS_LP_MODE_MASK (1 << 0) +#define DBI_LP_MODE (1 << 0) +#define DBI_HS_MODE (0 << 0) + +#define _MIPIA_DPHY_PARAM (VLV_DISPLAY_BASE + 0xb080) +#define _MIPIB_DPHY_PARAM (VLV_DISPLAY_BASE + 0xb880) +#define MIPI_DPHY_PARAM(pipe) _PIPE(pipe, _MIPIA_DPHY_PARAM, _MIPIB_DPHY_PARAM) +#define EXIT_ZERO_COUNT_SHIFT 24 +#define EXIT_ZERO_COUNT_MASK (0x3f << 24) +#define TRAIL_COUNT_SHIFT 16 +#define TRAIL_COUNT_MASK (0x1f << 16) +#define CLK_ZERO_COUNT_SHIFT 8 +#define CLK_ZERO_COUNT_MASK (0xff << 8) +#define PREPARE_COUNT_SHIFT 0 +#define PREPARE_COUNT_MASK (0x3f << 0) + +/* bits 31:0 */ +#define _MIPIA_DBI_BW_CTRL (VLV_DISPLAY_BASE + 0xb084) +#define _MIPIB_DBI_BW_CTRL (VLV_DISPLAY_BASE + 0xb884) +#define MIPI_DBI_BW_CTRL(pipe) _PIPE(pipe, _MIPIA_DBI_BW_CTRL, _MIPIB_DBI_BW_CTRL) + +#define _MIPIA_CLK_LANE_SWITCH_TIME_CNT (VLV_DISPLAY_BASE + 0xb088) +#define _MIPIB_CLK_LANE_SWITCH_TIME_CNT (VLV_DISPLAY_BASE + 0xb888) +#define MIPI_CLK_LANE_SWITCH_TIME_CNT(pipe) _PIPE(pipe, _MIPIA_CLK_LANE_SWITCH_TIME_CNT, _MIPIB_CLK_LANE_SWITCH_TIME_CNT) +#define LP_HS_SSW_CNT_SHIFT 16 +#define LP_HS_SSW_CNT_MASK (0xffff << 16) +#define HS_LP_PWR_SW_CNT_SHIFT 0 +#define HS_LP_PWR_SW_CNT_MASK (0xffff << 0) + +#define _MIPIA_STOP_STATE_STALL (VLV_DISPLAY_BASE + 0xb08c) +#define _MIPIB_STOP_STATE_STALL (VLV_DISPLAY_BASE + 0xb88c) +#define MIPI_STOP_STATE_STALL(pipe) _PIPE(pipe, _MIPIA_STOP_STATE_STALL, _MIPIB_STOP_STATE_STALL) +#define STOP_STATE_STALL_COUNTER_SHIFT 0 +#define STOP_STATE_STALL_COUNTER_MASK (0xff << 0) + +#define _MIPIA_INTR_STAT_REG_1 (VLV_DISPLAY_BASE + 0xb090) +#define _MIPIB_INTR_STAT_REG_1 (VLV_DISPLAY_BASE + 0xb890) +#define MIPI_INTR_STAT_REG_1(pipe) _PIPE(pipe, _MIPIA_INTR_STAT_REG_1, _MIPIB_INTR_STAT_REG_1) +#define _MIPIA_INTR_EN_REG_1 (VLV_DISPLAY_BASE + 0xb094) +#define _MIPIB_INTR_EN_REG_1 (VLV_DISPLAY_BASE + 0xb894) +#define MIPI_INTR_EN_REG_1(pipe) _PIPE(pipe, _MIPIA_INTR_EN_REG_1, _MIPIB_INTR_EN_REG_1) +#define RX_CONTENTION_DETECTED (1 << 0) + +/* XXX: only pipe A ?!? */ +#define MIPIA_DBI_TYPEC_CTRL (VLV_DISPLAY_BASE + 0xb100) +#define DBI_TYPEC_ENABLE (1 << 31) +#define DBI_TYPEC_WIP (1 << 30) +#define DBI_TYPEC_OPTION_SHIFT 28 +#define DBI_TYPEC_OPTION_MASK (3 << 28) +#define DBI_TYPEC_FREQ_SHIFT 24 +#define DBI_TYPEC_FREQ_MASK (0xf << 24) +#define DBI_TYPEC_OVERRIDE (1 << 8) +#define DBI_TYPEC_OVERRIDE_COUNTER_SHIFT 0 +#define DBI_TYPEC_OVERRIDE_COUNTER_MASK (0xff << 0) + + +/* MIPI adapter registers */ + +#define _MIPIA_CTRL (VLV_DISPLAY_BASE + 0xb104) +#define _MIPIB_CTRL (VLV_DISPLAY_BASE + 0xb904) +#define MIPI_CTRL(pipe) _PIPE(pipe, _MIPIA_CTRL, _MIPIB_CTRL) +#define ESCAPE_CLOCK_DIVIDER_SHIFT 5 /* A only */ +#define ESCAPE_CLOCK_DIVIDER_MASK (3 << 5) +#define ESCAPE_CLOCK_DIVIDER_1 (0 << 5) +#define ESCAPE_CLOCK_DIVIDER_2 (1 << 5) +#define ESCAPE_CLOCK_DIVIDER_4 (2 << 5) +#define READ_REQUEST_PRIORITY_SHIFT 3 +#define READ_REQUEST_PRIORITY_MASK (3 << 3) +#define READ_REQUEST_PRIORITY_LOW (0 << 3) +#define READ_REQUEST_PRIORITY_HIGH (3 << 3) +#define RGB_FLIP_TO_BGR (1 << 2) + +#define _MIPIA_DATA_ADDRESS (VLV_DISPLAY_BASE + 0xb108) +#define _MIPIB_DATA_ADDRESS (VLV_DISPLAY_BASE + 0xb908) +#define MIPI_DATA_ADDRESS(pipe) _PIPE(pipe, _MIPIA_DATA_ADDRESS, _MIPIB_DATA_ADDRESS) +#define DATA_MEM_ADDRESS_SHIFT 5 +#define DATA_MEM_ADDRESS_MASK (0x7ffffff << 5) +#define DATA_VALID (1 << 0) + +#define _MIPIA_DATA_LENGTH (VLV_DISPLAY_BASE + 0xb10c) +#define _MIPIB_DATA_LENGTH (VLV_DISPLAY_BASE + 0xb90c) +#define MIPI_DATA_LENGTH(pipe) _PIPE(pipe, _MIPIA_DATA_LENGTH, _MIPIB_DATA_LENGTH) +#define DATA_LENGTH_SHIFT 0 +#define DATA_LENGTH_MASK (0xfffff << 0) + +#define _MIPIA_COMMAND_ADDRESS (VLV_DISPLAY_BASE + 0xb110) +#define _MIPIB_COMMAND_ADDRESS (VLV_DISPLAY_BASE + 0xb910) +#define MIPI_COMMAND_ADDRESS(pipe) _PIPE(pipe, _MIPIA_COMMAND_ADDRESS, _MIPIB_COMMAND_ADDRESS) +#define COMMAND_MEM_ADDRESS_SHIFT 5 +#define COMMAND_MEM_ADDRESS_MASK (0x7ffffff << 5) +#define AUTO_PWG_ENABLE (1 << 2) +#define MEMORY_WRITE_DATA_FROM_PIPE_RENDERING (1 << 1) +#define COMMAND_VALID (1 << 0) + +#define _MIPIA_COMMAND_LENGTH (VLV_DISPLAY_BASE + 0xb114) +#define _MIPIB_COMMAND_LENGTH (VLV_DISPLAY_BASE + 0xb914) +#define MIPI_COMMAND_LENGTH(pipe) _PIPE(pipe, _MIPIA_COMMAND_LENGTH, _MIPIB_COMMAND_LENGTH) +#define COMMAND_LENGTH_SHIFT(n) (8 * (n)) /* n: 0...3 */ +#define COMMAND_LENGTH_MASK(n) (0xff << (8 * (n))) + +#define _MIPIA_READ_DATA_RETURN0 (VLV_DISPLAY_BASE + 0xb118) +#define _MIPIB_READ_DATA_RETURN0 (VLV_DISPLAY_BASE + 0xb918) +#define MIPI_READ_DATA_RETURN(pipe, n) \ + (_PIPE(pipe, _MIPIA_READ_DATA_RETURN0, _MIPIB_READ_DATA_RETURN0) + 4 * (n)) /* n: 0...7 */ + +#define _MIPIA_READ_DATA_VALID (VLV_DISPLAY_BASE + 0xb138) +#define _MIPIB_READ_DATA_VALID (VLV_DISPLAY_BASE + 0xb938) +#define MIPI_READ_DATA_VALID(pipe) _PIPE(pipe, _MIPIA_READ_DATA_VALID, _MIPIB_READ_DATA_VALID) +#define READ_DATA_VALID(n) (1 << (n)) + #endif /* _I915_REG_H_ */ -- cgit v1.2.3-70-g09d2 From 72ffa333418426b46648ac84ad4f015963b025e1 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 27 Aug 2013 15:12:17 +0300 Subject: drm/i915: add MIPI DSI output type and subtypes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Jani Nikula Signed-off-by: Shobhit Kumar Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_drv.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index dbfe5f7bb3de..8e0d54d895be 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -93,13 +93,17 @@ #define INTEL_OUTPUT_HDMI 6 #define INTEL_OUTPUT_DISPLAYPORT 7 #define INTEL_OUTPUT_EDP 8 -#define INTEL_OUTPUT_UNKNOWN 9 +#define INTEL_OUTPUT_DSI 9 +#define INTEL_OUTPUT_UNKNOWN 10 #define INTEL_DVO_CHIP_NONE 0 #define INTEL_DVO_CHIP_LVDS 1 #define INTEL_DVO_CHIP_TMDS 2 #define INTEL_DVO_CHIP_TVOUT 4 +#define INTEL_DSI_COMMAND_MODE 0 +#define INTEL_DSI_VIDEO_MODE 1 + struct intel_framebuffer { struct drm_framebuffer base; struct drm_i915_gem_object *obj; -- cgit v1.2.3-70-g09d2 From f5e11b06eb8a5aa6d4918aca85f88268e131a88e Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 27 Aug 2013 15:12:18 +0300 Subject: drm/i915: add structs for MIPI DSI output MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The sub-encoder model is copied from DVO. v2: Add attached_connector to struct intel_dsi. Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_dsi.h | 99 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) create mode 100644 drivers/gpu/drm/i915/intel_dsi.h (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h new file mode 100644 index 000000000000..f308269cd87c --- /dev/null +++ b/drivers/gpu/drm/i915/intel_dsi.h @@ -0,0 +1,99 @@ +/* + * Copyright © 2013 Intel Corporation + * + * 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, sublicense, + * 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 NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS 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. + */ + +#ifndef _INTEL_DSI_H +#define _INTEL_DSI_H + +#include +#include +#include "intel_drv.h" + +struct intel_dsi_device { + unsigned int panel_id; + const char *name; + int type; + const struct intel_dsi_dev_ops *dev_ops; + void *dev_priv; +}; + +struct intel_dsi_dev_ops { + bool (*init)(struct intel_dsi_device *dsi); + + /* This callback must be able to assume DSI commands can be sent */ + void (*enable)(struct intel_dsi_device *dsi); + + /* This callback must be able to assume DSI commands can be sent */ + void (*disable)(struct intel_dsi_device *dsi); + + int (*mode_valid)(struct intel_dsi_device *dsi, + struct drm_display_mode *mode); + + bool (*mode_fixup)(struct intel_dsi_device *dsi, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); + + void (*mode_set)(struct intel_dsi_device *dsi, + struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode); + + enum drm_connector_status (*detect)(struct intel_dsi_device *dsi); + + bool (*get_hw_state)(struct intel_dsi_device *dev); + + struct drm_display_mode *(*get_modes)(struct intel_dsi_device *dsi); + + void (*destroy) (struct intel_dsi_device *dsi); +}; + +struct intel_dsi { + struct intel_encoder base; + + struct intel_dsi_device dev; + + struct intel_connector *attached_connector; + + /* if true, use HS mode, otherwise LP */ + bool hs; + + /* virtual channel */ + int channel; + + /* number of DSI lanes */ + unsigned int lane_count; + + /* video mode pixel format for MIPI_DSI_FUNC_PRG register */ + u32 pixel_format; + + /* video mode format for MIPI_VIDEO_MODE_FORMAT register */ + u32 video_mode_format; + + /* eot for MIPI_EOT_DISABLE register */ + u32 eot_disable; +}; + +static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder) +{ + return container_of(encoder, struct intel_dsi, base.base); +} + +#endif /* _INTEL_DSI_H */ -- cgit v1.2.3-70-g09d2 From 69c05eb2d8421cbe96c2c66ea6e3223d25928d92 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 27 Aug 2013 15:12:19 +0300 Subject: drm/i915: add MIPI DSI command sending routines MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit v2: Rebase due to register bit definition change. v3: Mostly based on Ville's review comments. - Use size_t for length all around. - Reuse dsi_vc_send_short in dsi_vc_send_long. - Remove stale/incorrect comments. - Reverse special packet sent interrupt check. - Use DSI controller regs for reading, not adapter. Signed-off-by: Jani Nikula Reviewed-by: Ville Syrjälä Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/Makefile | 1 + drivers/gpu/drm/i915/intel_dsi_cmd.c | 427 +++++++++++++++++++++++++++++++++++ drivers/gpu/drm/i915/intel_dsi_cmd.h | 109 +++++++++ 3 files changed, 537 insertions(+) create mode 100644 drivers/gpu/drm/i915/intel_dsi_cmd.c create mode 100644 drivers/gpu/drm/i915/intel_dsi_cmd.h (limited to 'drivers/gpu') diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index b8449a84a0dc..8bffd292d1dc 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -21,6 +21,7 @@ i915-y := i915_drv.o i915_dma.o i915_irq.o \ intel_display.o \ intel_crt.o \ intel_lvds.o \ + intel_dsi_cmd.o \ intel_bios.o \ intel_ddi.o \ intel_dp.o \ diff --git a/drivers/gpu/drm/i915/intel_dsi_cmd.c b/drivers/gpu/drm/i915/intel_dsi_cmd.c new file mode 100644 index 000000000000..86577a0fc620 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_dsi_cmd.c @@ -0,0 +1,427 @@ +/* + * Copyright © 2013 Intel Corporation + * + * 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, sublicense, + * 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 NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS 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. + * + * Author: Jani Nikula + */ + +#include +#include +#include +#include