diff options
author | Dave Airlie <airlied@redhat.com> | 2014-06-02 19:55:04 +1000 |
---|---|---|
committer | Dave Airlie <airlied@redhat.com> | 2014-06-02 19:55:04 +1000 |
commit | c4e8541269d72fdfd1ec1b988ed2588033fafc6a (patch) | |
tree | 763f5b18c722a97a8b4251daaa3fb363d1c56faa | |
parent | 182407a6ed5333fc37dd980a8de91a8f826a94f6 (diff) | |
parent | f83d6518a13020e3cf7abbcc6b4e6d34459d9a9f (diff) |
Merge tag 'drm-intel-next-2014-05-23' of git://anongit.freedesktop.org/drm-intel into drm-next
- prep refactoring for execlists (Oscar Mateo)
- corner-case fixes for runtime pm (Imre)
- tons of vblank improvements from Ville
- prep work for atomic plane/sprite updates (Ville)
- more chv code, now almost complete (tons of different people)
- refactoring and improvements for drm_irq.c merged through drm-intel-next
- g4x/ilk reset improvements (Ville)
- removal of encoder->mode_set
- moved audio state tracking into pipe_config
- shuffled fb pinning out of the platform crtc modeset callbacks into core code
- userptr support (Chris)
- OOM handling improvements from Chris, with now have a neat oom notifier which
jumps additional debug information.
- topdown allocation of ppgtt PDEs (Ben)
- fixes and small improvements all over
* tag 'drm-intel-next-2014-05-23' of git://anongit.freedesktop.org/drm-intel: (187 commits)
drm/i915: Kill private_default_ctx off
drm/i915: s/i915_hw_context/intel_context
drm/i915: Split the ringbuffers from the rings (3/3)
drm/i915: Split the ringbuffers from the rings (2/3)
drm/i915: Split the ringbuffers from the rings (1/3)
drm/i915: s/intel_ring_buffer/intel_engine_cs
drm/i915: disable GT power saving early during system suspend
drm/i915: fix possible RPM ref leaking during RPS disabling
drm/i915: remove user GTT mappings early during runtime suspend
drm/i915: Implement WaVcpClkGateDisableForMediaReset:ctg, elk
drm/i915: Fix gen2 and hsw+ scanline counter
drm/i915: Draw a picture about video timings
drm/i915: Improve gen3/4 frame counter
drm/i915: Add a small adjustment to the pixel counter on interlaced modes
drm/i915: Hold CRTC lock whilst freezing the planes
drm/i915: Only discard backing storage on releasing the last ref
drm/i915: Wait for pending page flips before enabling/disabling the primary plane
drm/i915: grab the audio power domain when enabling audio on HSW+
drm/i915: don't read HSW_AUD_PIN_ELD_CP_VLD when the power well is off
drm/i915: move bsd dispatch index somewhere better
...
49 files changed, 6778 insertions, 1771 deletions
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl index c1c9cf2a7b48..00f1c25e53df 100644 --- a/Documentation/DocBook/drm.tmpl +++ b/Documentation/DocBook/drm.tmpl @@ -3368,6 +3368,10 @@ void (*disable_vblank) (struct drm_device *dev, int crtc);</synopsis> with a call to <function>drm_vblank_cleanup</function> in the driver <methodname>unload</methodname> operation handler. </para> + <sect2> + <title>Vertical Blanking and Interrupt Handling Functions Reference</title> +!Edrivers/gpu/drm/drm_irq.c + </sect2> </sect1> <!-- Internals: open/close, file operations and ioctls --> @@ -3710,17 +3714,16 @@ int num_ioctls;</synopsis> <term>DRM_IOCTL_MODESET_CTL</term> <listitem> <para> - This should be called by application level drivers before and - after mode setting, since on many devices the vertical blank - counter is reset at that time. Internally, the DRM snapshots - the last vblank count when the ioctl is called with the - _DRM_PRE_MODESET command, so that the counter won't go backwards - (which is dealt with when _DRM_POST_MODESET is used). + This was only used for user-mode-settind drivers around + modesetting changes to allow the kernel to update the vblank + interrupt after mode setting, since on many devices the vertical + blank counter is reset to 0 at some point during modeset. Modern + drivers should not call this any more since with kernel mode + setting it is a no-op. </para> </listitem> </varlistentry> </variablelist> -<!--!Edrivers/char/drm/drm_irq.c--> </para> </sect1> @@ -3783,6 +3786,96 @@ int num_ioctls;</synopsis> probing, so those sections fully apply. </para> </sect2> + <sect2> + <title>DPIO</title> +!Pdrivers/gpu/drm/i915/i915_reg.h DPIO + <table id="dpiox2"> + <title>Dual channel PHY (VLV/CHV)</title> + <tgroup cols="8"> + <colspec colname="c0" /> + <colspec colname="c1" /> + <colspec colname="c2" /> + <colspec colname="c3" /> + <colspec colname="c4" /> + <colspec colname="c5" /> + <colspec colname="c6" /> + <colspec colname="c7" /> + <spanspec spanname="ch0" namest="c0" nameend="c3" /> + <spanspec spanname="ch1" namest="c4" nameend="c7" /> + <spanspec spanname="ch0pcs01" namest="c0" nameend="c1" /> + <spanspec spanname="ch0pcs23" namest="c2" nameend="c3" /> + <spanspec spanname="ch1pcs01" namest="c4" nameend="c5" /> + <spanspec spanname="ch1pcs23" namest="c6" nameend="c7" /> + <thead> + <row> + <entry spanname="ch0">CH0</entry> + <entry spanname="ch1">CH1</entry> + </row> + </thead> + <tbody valign="top" align="center"> + <row> + <entry spanname="ch0">CMN/PLL/REF</entry> + <entry spanname="ch1">CMN/PLL/REF</entry> + </row> + <row> + <entry spanname="ch0pcs01">PCS01</entry> + <entry spanname="ch0pcs23">PCS23</entry> + <entry spanname="ch1pcs01">PCS01</entry> + <entry spanname="ch1pcs23">PCS23</entry> + </row> + <row> + <entry>TX0</entry> + <entry>TX1</entry> + <entry>TX2</entry> + <entry>TX3</entry> + <entry>TX0</entry> + <entry>TX1</entry> + <entry>TX2</entry> + <entry>TX3</entry> + </row> + <row> + <entry spanname="ch0">DDI0</entry> + <entry spanname="ch1">DDI1</entry> + </row> + </tbody> + </tgroup> + </table> + <table id="dpiox1"> + <title>Single channel PHY (CHV)</title> + <tgroup cols="4"> + <colspec colname="c0" /> + <colspec colname="c1" /> + <colspec colname="c2" /> + <colspec colname="c3" /> + <spanspec spanname="ch0" namest="c0" nameend="c3" /> + <spanspec spanname="ch0pcs01" namest="c0" nameend="c1" /> + <spanspec spanname="ch0pcs23" namest="c2" nameend="c3" /> + <thead> + <row> + <entry spanname="ch0">CH0</entry> + </row> + </thead> + <tbody valign="top" align="center"> + <row> + <entry spanname="ch0">CMN/PLL/REF</entry> + </row> + <row> + <entry spanname="ch0pcs01">PCS01</entry> + <entry spanname="ch0pcs23">PCS23</entry> + </row> + <row> + <entry>TX0</entry> + <entry>TX1</entry> + <entry>TX2</entry> + <entry>TX3</entry> + </row> + <row> + <entry spanname="ch0">DDI2</entry> + </row> + </tbody> + </tgroup> + </table> + </sect2> </sect1> <sect1> diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6e2537c32190..f96098fda1a2 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -418,7 +418,7 @@ static size_t __init gen6_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } -static size_t gen8_stolen_size(int num, int slot, int func) +static size_t __init gen8_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; @@ -428,48 +428,73 @@ static size_t gen8_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } +static size_t __init chv_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; + + /* + * 0x0 to 0x10: 32MB increments starting at 0MB + * 0x11 to 0x16: 4MB increments starting at 8MB + * 0x17 to 0x1d: 4MB increments start at 36MB + */ + if (gmch_ctrl < 0x11) + return gmch_ctrl << 25; + else if (gmch_ctrl < 0x17) + return (gmch_ctrl - 0x11 + 2) << 22; + else + return (gmch_ctrl - 0x17 + 9) << 22; +} struct intel_stolen_funcs { size_t (*size)(int num, int slot, int func); u32 (*base)(int num, int slot, int func, size_t size); }; -static const struct intel_stolen_funcs i830_stolen_funcs = { +static const struct intel_stolen_funcs i830_stolen_funcs __initconst = { .base = i830_stolen_base, .size = i830_stolen_size, }; -static const struct intel_stolen_funcs i845_stolen_funcs = { +static const struct intel_stolen_funcs i845_stolen_funcs __initconst = { .base = i845_stolen_base, .size = i830_stolen_size, }; -static const struct intel_stolen_funcs i85x_stolen_funcs = { +static const struct intel_stolen_funcs i85x_stolen_funcs __initconst = { .base = i85x_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs i865_stolen_funcs = { +static const struct intel_stolen_funcs i865_stolen_funcs __initconst = { .base = i865_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen3_stolen_funcs = { +static const struct intel_stolen_funcs gen3_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen6_stolen_funcs = { +static const struct intel_stolen_funcs gen6_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen6_stolen_size, }; -static const struct intel_stolen_funcs gen8_stolen_funcs = { +static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen8_stolen_size, }; -static struct pci_device_id intel_stolen_ids[] __initdata = { +static const struct intel_stolen_funcs chv_stolen_funcs __initconst = { + .base = intel_stolen_base, + .size = chv_stolen_size, +}; + +static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_I830_IDS(&i830_stolen_funcs), INTEL_I845G_IDS(&i845_stolen_funcs), INTEL_I85X_IDS(&i85x_stolen_funcs), @@ -495,7 +520,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = { INTEL_HSW_D_IDS(&gen6_stolen_funcs), INTEL_HSW_M_IDS(&gen6_stolen_funcs), INTEL_BDW_M_IDS(&gen8_stolen_funcs), - INTEL_BDW_D_IDS(&gen8_stolen_funcs) + INTEL_BDW_D_IDS(&gen8_stolen_funcs), + INTEL_CHV_IDS(&chv_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 7583767ec619..b565372a91f3 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -1,6 +1,5 @@ -/** - * \file drm_irq.c - * IRQ support +/* + * drm_irq.c IRQ and vblank support * * \author Rickard E. (Rik) Faith <faith@valinux.com> * \author Gareth Hughes <gareth@valinux.com> @@ -140,33 +139,40 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc) static void vblank_disable_fn(unsigned long arg) { - struct drm_device *dev = (struct drm_device *)arg; + struct drm_vblank_crtc *vblank = (void *)arg; + struct drm_device *dev = vblank->dev; unsigned long irqflags; - int i; + int crtc = vblank->crtc; if (!dev->vblank_disable_allowed) return; - for (i = 0; i < dev->num_crtcs; i++) { - spin_lock_irqsave(&dev->vbl_lock, irqflags); - if (atomic_read(&dev->vblank[i].refcount) == 0 && - dev->vblank[i].enabled) { - DRM_DEBUG("disabling vblank on crtc %d\n", i); - vblank_disable_and_save(dev, i); - } - spin_unlock_irqrestore(&dev->vbl_lock, irqflags); + spin_lock_irqsave(&dev->vbl_lock, irqflags); + if (atomic_read(&vblank->refcount) == 0 && vblank->enabled) { + DRM_DEBUG("disabling vblank on crtc %d\n", crtc); + vblank_disable_and_save(dev, crtc); } + spin_unlock_irqrestore(&dev->vbl_lock, irqflags); } +/** + * drm_vblank_cleanup - cleanup vblank support + * @dev: DRM device + * + * This function cleans up any resources allocated in drm_vblank_init. + */ void drm_vblank_cleanup(struct drm_device *dev) { + int crtc; + /* Bail if the driver didn't call drm_vblank_init() */ if (dev->num_crtcs == 0) return; - del_timer_sync(&dev->vblank_disable_timer); - - vblank_disable_fn((unsigned long)dev); + for (crtc = 0; crtc < dev->num_crtcs; crtc++) { + del_timer_sync(&dev->vblank[crtc].disable_timer); + vblank_disable_fn((unsigned long)&dev->vblank[crtc]); + } kfree(dev->vblank); @@ -174,12 +180,20 @@ void drm_vblank_cleanup(struct drm_device *dev) } EXPORT_SYMBOL(drm_vblank_cleanup); +/** + * drm_vblank_init - initialize vblank support + * @dev: drm_device + * @num_crtcs: number of crtcs supported by @dev + * + * This function initializes vblank support for @num_crtcs display pipelines. + * + * Returns: + * Zero on success or a negative error code on failure. + */ int drm_vblank_init(struct drm_device *dev, int num_crtcs) { int i, ret = -ENOMEM; - setup_timer(&dev->vblank_disable_timer, vblank_disable_fn, - (unsigned long)dev); spin_lock_init(&dev->vbl_lock); spin_lock_init(&dev->vblank_time_lock); @@ -189,8 +203,13 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs) if (!dev->vblank) goto err; - for (i = 0; i < num_crtcs; i++) + for (i = 0; i < num_crtcs; i++) { + dev->vblank[i].dev = dev; + dev->vblank[i].crtc = i; init_waitqueue_head(&dev->vblank[i].queue); + setup_timer(&dev->vblank[i].disable_timer, vblank_disable_fn, + (unsigned long)&dev->vblank[i]); + } DRM_INFO("Supports vblank timestamp caching Rev 2 (21.10.2013).\n"); @@ -234,13 +253,21 @@ static void drm_irq_vgaarb_nokms(void *cookie, bool state) } /** - * Install IRQ handler. - * - * \param dev DRM device. + * drm_irq_install - install IRQ handler + * @dev: DRM device + * @irq: IRQ number to install the handler for * * Initializes the IRQ related data. Installs the handler, calling the driver - * \c irq_preinstall() and \c irq_postinstall() functions - * before and after the installation. + * irq_preinstall() and irq_postinstall() functions before and after the + * installation. + * + * This is the simplified helper interface provided for drivers with no special + * needs. Drivers which need to install interrupt handlers for multiple + * interrupts must instead set drm_device->irq_enabled to signal the DRM core + * that vblank interrupts are available. + * + * Returns: + * Zero on success or a negative error code on failure. */ int drm_irq_install(struct drm_device *dev, int irq) { @@ -300,11 +327,20 @@ int drm_irq_install(struct drm_device *dev, int irq) EXPORT_SYMBOL(drm_irq_install); /** - * Uninstall the IRQ handler. + * drm_irq_uninstall - uninstall the IRQ handler + * @dev: DRM device * - * \param dev DRM device. + * Calls the driver's irq_uninstall() function and unregisters the IRQ handler. + * This should only be called by drivers which used drm_irq_install() to set up + * their interrupt handler. Other drivers must only reset + * drm_device->irq_enabled to false. * - * Calls the driver's \c irq_uninstall() function, and stops the irq. + * Note that for kernel modesetting drivers it is a bug if this function fails. + * The sanity checks are only to catch buggy user modesetting drivers which call + * the same function through an ioctl. + * + * Returns: + * Zero on success or a negative error code on failure. */ int drm_irq_uninstall(struct drm_device *dev) { @@ -349,7 +385,7 @@ int drm_irq_uninstall(struct drm_device *dev) } EXPORT_SYMBOL(drm_irq_uninstall); -/** +/* * IRQ control ioctl. * * \param inode device inode. @@ -402,15 +438,14 @@ int drm_control(struct drm_device *dev, void *data, } /** - * drm_calc_timestamping_constants - Calculate vblank timestamp constants - * - * @crtc drm_crtc whose timestamp constants should be updated. - * @mode display mode containing the scanout timings + * drm_calc_timestamping_constants - calculate vblank timestamp constants + * @crtc: drm_crtc whose timestamp constants should be updated. + * @mode: display mode containing the scanout timings * * Calculate and store various constants which are later * needed by vblank and swap-completion timestamping, e.g, * by drm_calc_vbltimestamp_from_scanoutpos(). They are - * derived from crtc's true scanout timing, so they take + * derived from CRTC's true scanout timing, so they take * things like panel scaling or other adjustments into account. */ void drm_calc_timestamping_constants(struct drm_crtc *crtc, @@ -455,11 +490,22 @@ void drm_calc_timestamping_constants(struct drm_crtc *crtc, EXPORT_SYMBOL(drm_calc_timestamping_constants); /** - * drm_calc_vbltimestamp_from_scanoutpos - helper routine for kms - * drivers. Implements calculation of exact vblank timestamps from - * given drm_display_mode timings and current video scanout position - * of a crtc. This can be called from within get_vblank_timestamp() - * implementation of a kms driver to implement the actual timestamping. + * drm_calc_vbltimestamp_from_scanoutpos - precise vblank timestamp helper + * @dev: DRM device + * @crtc: Which CRTC's vblank timestamp to retrieve + * @max_error: Desired maximum allowable error in timestamps (nanosecs) + * On return contains true maximum error of timestamp + * @vblank_time: Pointer to struct timeval which should receive the timestamp + * @flags: Flags to pass to driver: + * 0 = Default, + * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl IRQ handler + * @refcrtc: CRTC which defines scanout timing + * @mode: mode which defines the scanout timings + * + * Implements calculation of exact vblank timestamps from given drm_display_mode + * timings and current video scanout position of a CRTC. This can be called from + * within get_vblank_timestamp() implementation of a kms driver to implement the + * actual timestamping. * * Should return timestamps conforming to the OML_sync_control OpenML * extension specification. The timestamp corresponds to the end of @@ -474,21 +520,11 @@ EXPORT_SYMBOL(drm_calc_timestamping_constants); * returns as no operation if a doublescan or interlaced video mode is * active. Higher level code is expected to handle this. * - * @dev: DRM device. - * @crtc: Which crtc's vblank timestamp to retrieve. - * @max_error: Desired maximum allowable error in timestamps (nanosecs). - * On return contains true maximum error of timestamp. - * @vblank_time: Pointer to struct timeval which should receive the timestamp. - * @flags: Flags to pass to driver: - * 0 = Default. - * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl irq handler. - * @refcrtc: drm_crtc* of crtc which defines scanout timing. - * @mode: mode which defines the scanout timings - * - * Returns negative value on error, failure or if not supported in current + * Returns: + * Negative value on error, failure or if not supported in current * video mode: * - * -EINVAL - Invalid crtc. + * -EINVAL - Invalid CRTC. * -EAGAIN - Temporary unavailable, e.g., called before initial modeset. * -ENOTSUPP - Function not supported in current display mode. * -EIO - Failed, e.g., due to failed scanout position query. @@ -637,23 +673,23 @@ static struct timeval get_drm_timestamp(void) /** * drm_get_last_vbltimestamp - retrieve raw timestamp for the most recent - * vblank interval. - * + * vblank interval * @dev: DRM device - * @crtc: which crtc's vblank timestamp to retrieve + * @crtc: which CRTC's vblank timestamp to retrieve * @tvblank: Pointer to target struct timeval which should receive the timestamp * @flags: Flags to pass to driver: - * 0 = Default. - * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl irq handler. + * 0 = Default, + * DRM_CALLED_FROM_VBLIRQ = If function is called from vbl IRQ handler * * Fetches the system timestamp corresponding to the time of the most recent - * vblank interval on specified crtc. May call into kms-driver to + * vblank interval on specified CRTC. May call into kms-driver to * compute the timestamp with a high-precision GPU specific method. * * Returns zero if timestamp originates from uncorrected do_gettimeofday() * call, i.e., it isn't very precisely locked to the true vblank. * - * Returns non-zero if timestamp is considered to be very precise. + * Returns: + * Non-zero if timestamp is considered to be very precise, zero otherwise. */ u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc, struct timeval *tvblank, unsigned flags) @@ -688,6 +724,9 @@ EXPORT_SYMBOL(drm_get_last_vbltimestamp); * Fetches the "cooked" vblank count value that represents the number of * vblank events since the system was booted, including lost events due to * modesetting activity. + * + * Returns: + * The software vblank counter. */ u32 drm_vblank_count(struct drm_device *dev, int crtc) { @@ -706,8 +745,7 @@ EXPORT_SYMBOL(drm_vblank_count); * Fetches the "cooked" vblank count value that represents the number of * vblank events since the system was booted, including lost events due to * modesetting activity. Returns corresponding system timestamp of the time - * of the vblank interval that corresponds to the current value vblank counter - * value. + * of the vblank interval that corresponds to the current vblank counter value. */ u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc, struct timeval *vblanktime) @@ -836,6 +874,42 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc) } /** + * drm_vblank_enable - enable the vblank interrupt on a CRTC + * @dev: DRM device + * @crtc: CRTC in question + */ +static int drm_vblank_enable(struct drm_device *dev, int crtc) +{ + int ret = 0; + + assert_spin_locked(&dev->vbl_lock); + + spin_lock(&dev->vblank_time_lock); + + if (!dev->vblank[crtc].enabled) { + /* + * Enable vblank irqs under vblank_time_lock protection. + * All vblank count & timestamp updates are held off + * until we are done reinitializing master counter and + * timestamps. Filtercode in drm_handle_vblank() will + * prevent double-accounting of same vblank interval. + */ + ret = dev->driver->enable_vblank(dev, crtc); + DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", crtc, ret); + if (ret) + atomic_dec(&dev->vblank[crtc].refcount); + else { + dev->vblank[crtc].enabled = true; + drm_update_vblank_count(dev, crtc); + } + } + + spin_unlock(&dev->vblank_time_lock); + + return ret; +} + +/** * drm_vblank_get - get a reference count on vblank events * @dev: DRM device * @crtc: which CRTC to own @@ -843,36 +917,20 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc) * Acquire a reference count on vblank events to avoid having them disabled * while in use. * - * RETURNS + * This is the legacy version of drm_crtc_vblank_get(). + * + * Returns: * Zero on success, nonzero on failure. */ int drm_vblank_get(struct drm_device *dev, int crtc) { - unsigned long irqflags, irqflags2; + unsigned long irqflags; int ret = 0; spin_lock_irqsave(&dev->vbl_lock, irqflags); /* Going from 0->1 means we have to enable interrupts again */ if (atomic_add_return(1, &dev->vblank[crtc].refcount) == 1) { - spin_lock_irqsave(&dev->vblank_time_lock, irqflags2); - if (!dev->vblank[crtc].enabled) { - /* Enable vblank irqs under vblank_time_lock protection. - * All vblank count & timestamp updates are held off - * until we are done reinitializing master counter and - * timestamps. Filtercode in drm_handle_vblank() will - * prevent double-accounting of same vblank interval. - */ - ret = dev->driver->enable_vblank(dev, crtc); - DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", - crtc, ret); - if (ret) - atomic_dec(&dev->vblank[crtc].refcount); - else { - dev->vblank[crtc].enabled = true; - drm_update_vblank_count(dev, crtc); - } - } - spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags2); + ret = drm_vblank_enable(dev, crtc); } else { if (!dev->vblank[crtc].enabled) { atomic_dec(&dev->vblank[crtc].refcount); @@ -886,12 +944,32 @@ int drm_vblank_get(struct drm_device *dev, int crtc) EXPORT_SYMBOL(drm_vblank_get); /** + * drm_crtc_vblank_get - get a reference count on vblank events + * @crtc: which CRTC to own + * + * Acquire a reference count on vblank events to avoid having them disabled + * while in use. + * + * This is the native kms version of drm_vblank_off(). + * + * Returns: + * Zero on success, nonzero on failure. + */ +int drm_crtc_vblank_get(struct drm_crtc *crtc) +{ + return drm_vblank_get(crtc->dev, drm_crtc_index(crtc)); +} +EXPORT_SYMBOL(drm_crtc_vblank_get); + +/** * drm_vblank_put - give up ownership of vblank events * @dev: DRM device * @crtc: which counter to give up * * Release ownership of a given vblank counter, turning off interrupts * if possible. Disable interrupts after drm_vblank_offdelay milliseconds. + * + * This is the legacy version of drm_crtc_vblank_put(). */ void drm_vblank_put(struct drm_device *dev, int crtc) { @@ -900,17 +978,39 @@ void drm_vblank_put(struct drm_device *dev, int crtc) /* Last user schedules interrupt disable */ if (atomic_dec_and_test(&dev->vblank[crtc].refcount) && (drm_vblank_offdelay > 0)) - mod_timer(&dev->vblank_disable_timer, + mod_timer(&dev->vblank[crtc].disable_timer, jiffies + ((drm_vblank_offdelay * HZ)/1000)); } EXPORT_SYMBOL(drm_vblank_put); /** + * drm_crtc_vblank_put - give up ownership of vblank events + * @crtc: which counter to give up + * + * Release ownership of a given vblank counter, turning off interrupts + * if possible. Disable interrupts after drm_vblank_offdelay milliseconds. + * + * This is the native kms version of drm_vblank_put(). + */ +void drm_crtc_vblank_put(struct drm_crtc *crtc) +{ + drm_vblank_put(crtc->dev, drm_crtc_index(crtc)); +} +EXPORT_SYMBOL(drm_crtc_vblank_put); + +/** * drm_vblank_off - disable vblank events on a CRTC * @dev: DRM device * @crtc: CRTC in question * - * Caller must hold event lock. + * Drivers can use this function to shut down the vblank interrupt handling when + * disabling a crtc. This function ensures that the latest vblank frame count is + * stored so that drm_vblank_on() can restore it again. + * + * Drivers must use this function when the hardware vblank counter can get + * reset, e.g. when suspending. + * + * This is the legacy version of drm_crtc_vblank_off(). */ void drm_vblank_off(struct drm_device *dev, int crtc) { @@ -944,12 +1044,87 @@ void drm_vblank_off(struct drm_device *dev, int crtc) EXPORT_SYMBOL(drm_vblank_off); /** + * drm_crtc_vblank_off - disable vblank events on a CRTC + * @crtc: CRTC in question + * + * Drivers can use this function to shut down the vblank interrupt handling when + * disabling a crtc. This function ensures that the latest vblank frame count is + * stored so that drm_vblank_on can restore it again. + * + * Drivers must use this function when the hardware vblank counter can get + * reset, e.g. when suspending. + * + * This is the native kms version of drm_vblank_off(). + */ +void drm_crtc_vblank_off(struct drm_crtc *crtc) +{ + drm_vblank_off(crtc->dev, drm_crtc_index(crtc)); +} +EXPORT_SYMBOL(drm_crtc_vblank_off); + +/** + * drm_vblank_on - enable vblank events on a CRTC + * @dev: DRM device + * @crtc: CRTC in question + * + * This functions restores the vblank interrupt state captured with + * drm_vblank_off() again. Note that calls to drm_vblank_on() and + * drm_vblank_off() can be unbalanced and so can also be unconditionaly called + * in driver load code to reflect the current hardware state of the crtc. + * + * This is the legacy version of drm_crtc_vblank_on(). + */ +void drm_vblank_on(struct drm_device *dev, int crtc) +{ + unsigned long irqflags; + + spin_lock_irqsave(&dev->vbl_lock, irqflags); + /* re-enable interrupts if there's are users left */ + if (atomic_read(&dev->vblank[crtc].refcount) != 0) + WARN_ON(drm_vblank_enable(dev, crtc)); + spin_unlock_irqrestore(&dev->vbl_lock, irqflags); +} +EXPORT_SYMBOL(drm_vblank_on); + +/** + * drm_crtc_vblank_on - enable vblank events on a CRTC + * @crtc: CRTC in question + * + * This functions restores the vblank interrupt state captured with + * drm_vblank_off() again. Note that calls to drm_vblank_on() and + * drm_vblank_off() can be unbalanced and so can also be unconditionaly called + * in driver load code to reflect the current hardware state of the crtc. + * + * This is the native kms version of drm_vblank_on(). + */ +void drm_crtc_vblank_on(struct drm_crtc *crtc) +{ + drm_vblank_on(crtc->dev, drm_crtc_index(crtc)); +} +EXPORT_SYMBOL(drm_crtc_vblank_on); + +/** * drm_vblank_pre_modeset - account for vblanks across mode sets * @dev: DRM device * @crtc: CRTC in question * * Account for vblank events across mode setting events, which will likely * reset the hardware frame counter. + * + * This is done by grabbing a temporary vblank reference to ensure that the + * vblank interrupt keeps running across the modeset sequence. With this the + * software-side vblank frame counting will ensure that there are no jumps or + * discontinuities. + * + * Unfortunately this approach is racy and also doesn't work when the vblank + * interrupt stops running, e.g. across system suspend resume. It is therefore + * highly recommended that drivers use the newer drm_vblank_off() and + * drm_vblank_on() instead. drm_vblank_pre_modeset() only works correctly when + * using "cooked" software vblank frame counters and not relying on any hardware + * counters. + * + * Drivers must call drm_vblank_post_modeset() when re-enabling the same crtc + * again. */ void drm_vblank_pre_modeset(struct drm_device *dev, int crtc) { @@ -971,6 +1146,14 @@ void drm_vblank_pre_modeset(struct drm_device *dev, int crtc) } EXPORT_SYMBOL(drm_vblank_pre_modeset); +/** + * drm_vblank_post_modeset - undo drm_vblank_pre_modeset changes + * @dev: DRM device + * @crtc: CRTC in question + * + * This function again drops the temporary vblank reference acquired in + * drm_vblank_pre_modeset. + */ void drm_vblank_post_modeset(struct drm_device *dev, int crtc) { unsigned long irqflags; @@ -992,7 +1175,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, int crtc) } EXPORT_SYMBOL(drm_vblank_post_modeset); -/** +/* * drm_modeset_ctl - handle vblank event counter changes across mode switch * @DRM_IOCTL_ARGS: standard ioctl arguments * @@ -1105,7 +1288,7 @@ err_put: return ret; } -/** +/* * Wait for VBLANK. * * \param inode device inode. @@ -1116,7 +1299,7 @@ err_put: * * This function enables the vblank interrupt on the pipe requested, then * sleeps waiting for the requested sequence number to occur, and drops - * the vblank interrupt refcount afterwards. (vblank irq disable follows that + * the vblank interrupt refcount afterwards. (vblank IRQ disable follows that * after a timeout with no further vblank waits scheduled). */ int drm_wait_vblank(struct drm_device *dev, void *data, @@ -1187,6 +1370,7 @@ int drm_wait_vblank(struct drm_device *dev, void *data, DRM_WAIT_ON(ret, dev->vblank[crtc].queue, 3 * HZ, (((drm_vblank_count(dev, crtc) - vblwait->request.sequence) <= (1 << 23)) || + !dev->vblank[crtc].enabled || !dev->irq_enabled)); if (ret != -EINTR) { diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index e4e3c01b8cbc..437e1824d0bf 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -5,6 +5,7 @@ config DRM_I915 depends on (AGP || AGP=n) select INTEL_GTT select AGP_INTEL if AGP + select INTERVAL_TREE # we need shmfs for the swappable backing store, and in particular # the shmem_readpage() which depends upon tmpfs select SHMEM diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index b1445b73465b..7b2f3bee3518 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -18,6 +18,7 @@ i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o # GEM code i915-y += i915_cmd_parser.o \ i915_gem_context.o \ + i915_gem_render_state.o \ i915_gem_debug.o \ i915_gem_dmabuf.o \ i915_gem_evict.o \ @@ -26,12 +27,18 @@ i915-y += i915_cmd_parser.o \ i915_gem.o \ i915_gem_stolen.o \ i915_gem_tiling.o \ + i915_gem_userptr.o \ i915_gpu_error.o \ i915_irq.o \ i915_trace_points.o \ intel_ringbuffer.o \ intel_uncore.o +# autogenerated null render state +i915-y += intel_renderstate_gen6.o \ + intel_renderstate_gen7.o \ + intel_renderstate_gen8.o + # modesetting core code i915-y += intel_bios.o \ intel_display.o \ diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 69d34e47d3bc..9d7954366bd2 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -498,16 +498,18 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header) return 0; } -static bool validate_cmds_sorted(struct intel_ring_buffer *ring) +static bool validate_cmds_sorted(struct intel_engine_cs *ring, + const struct drm_i915_cmd_table *cmd_tables, + int cmd_table_count) { int i; bool ret = true; - if (!ring->cmd_tables || ring->cmd_table_count == 0) + if (!cmd_tables || cmd_table_count == 0) return true; - for (i = 0; i < ring->cmd_table_count; i++) { - const struct drm_i915_cmd_table *table = &ring->cmd_tables[i]; + for (i = 0; i < cmd_table_count; i++) { + const struct drm_i915_cmd_table *table = &cmd_tables[i]; u32 previous = 0; int j; @@ -550,35 +552,103 @@ static bool check_sorted(int ring_id, const u32 *reg_table, int reg_count) return ret; } -static bool validate_regs_sorted(struct intel_ring_buffer *ring) +static bool validate_regs_sorted(struct intel_engine_cs *ring) { return check_sorted(ring->id, ring->reg_table, ring->reg_count) && check_sorted(ring->id, ring->master_reg_table, ring->master_reg_count); } +struct cmd_node { + const struct drm_i915_cmd_descriptor *desc; + struct hlist_node node; +}; + +/* + * Different command ranges have different numbers of bits for the opcode. For + * example, MI commands use bits 31:23 while 3D commands use bits 31:16. The + * problem is that, for example, MI commands use bits 22:16 for other fields + * such as GGTT vs PPGTT bits. If we include those bits in the mask then when + * we mask a command from a batch it could hash to the wrong bucket due to + * non-opcode bits being set. But if we don't include those bits, some 3D + * commands may hash to the same bucket due to not including opcode bits that + * make the command unique. For now, we will risk hashing to the same bucket. + * + * If we attempt to generate a perfect hash, we should be able to look at bits + * 31:29 of a command from a batch buffer and use the full mask for that + * client. The existing INSTR_CLIENT_MASK/SHIFT defines can be used for this. + */ +#define CMD_HASH_MASK STD_MI_OPCODE_MASK + +static int init_hash_table(struct intel_engine_cs *ring, + const struct drm_i915_cmd_table *cmd_tables, + int cmd_table_count) +{ + int i, j; + + hash_init(ring->cmd_hash); + + for (i = 0; i < cmd_table_count; i++) { + const struct drm_i915_cmd_table *table = &cmd_tables[i]; + + for (j = 0; j < table->count; j++) { + const struct drm_i915_cmd_descriptor *desc = + &table->table[j]; + struct cmd_node *desc_node = + kmalloc(sizeof(*desc_node), GFP_KERNEL); + + if (!desc_node) + return -ENOMEM; + + desc_node->desc = desc; + hash_add(ring->cmd_hash, &desc_node->node, + desc->cmd.value & CMD_HASH_MASK); + } + } + + return 0; +} + +static void fini_hash_table(struct intel_engine_cs *ring) +{ + struct hlist_node *tmp; + struct cmd_node *desc_node; + int i; + + hash_for_each_safe(ring->cmd_hash, i, tmp, desc_node, node) { + hash_del(&desc_node->node); + kfree(desc_node); + } +} + /** * i915_cmd_parser_init_ring() - set cmd parser related fields for a ringbuffer * @ring: the ringbuffer to initialize * * Optionally initializes fields related to batch buffer command parsing in the - * struct intel_ring_buffer based on whether the platform requires software + * struct intel_engine_cs based on whether the platform requires software * command parsing. + * + * Return: non-zero if initialization fails */ -void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring) +int i915_cmd_parser_init_ring(struct intel_engine_cs *ring) { + const struct drm_i915_cmd_table *cmd_tables; + int cmd_table_count; + int ret; + if (!IS_GEN7(ring->dev)) - return; + return 0; switch (ring->id) { case RCS: if (IS_HASWELL(ring->dev)) { - ring->cmd_tables = hsw_render_ring_cmds; - ring->cmd_table_count = + cmd_tables = hsw_render_ring_cmds; + cmd_table_count = ARRAY_SIZE(hsw_render_ring_cmds); } else { - ring->cmd_tables = gen7_render_cmds; - ring->cmd_table_count = ARRAY_SIZE(gen7_render_cmds); + cmd_tables = gen7_render_cmds; + cmd_table_count = ARRAY_SIZE(gen7_render_cmds); } ring->reg_table = gen7_render_regs; @@ -595,17 +665,17 @@ void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring) ring->get_cmd_length_mask = gen7_render_get_cmd_length_mask; break; case VCS: - ring->cmd_tables = gen7_video_cmds; - ring->cmd_table_count = ARRAY_SIZE(gen7_video_cmds); + cmd_tables = gen7_video_cmds; + cmd_table_count = ARRAY_SIZE(gen7_video_cmds); ring->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; case BCS: if (IS_HASWELL(ring->dev)) { - ring->cmd_tables = hsw_blt_ring_cmds; - ring->cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds); + cmd_tables = hsw_blt_ring_cmds; + cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds); } else { - ring->cmd_tables = gen7_blt_cmds; - ring->cmd_table_count = ARRAY_SIZE(gen7_blt_cmds); + cmd_tables = gen7_blt_cmds; + cmd_table_count = ARRAY_SIZE(gen7_blt_cmds); } ring->reg_table = gen7_blt_regs; @@ -622,8 +692,8 @@ void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring) ring->get_cmd_length_mask = gen7_blt_get_cmd_length_mask; break; case VECS: - ring->cmd_tables = hsw_vebox_cmds; - ring->cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds); + cmd_tables = hsw_vebox_cmds; + cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds); /* VECS can use the same length_mask function as VCS */ ring->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask; break; @@ -633,18 +703,45 @@ void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring) BUG(); } - BUG_ON(!validate_cmds_sorted(ring)); + BUG_ON(!validate_cmds_sorted(ring, cmd_tables, cmd_table_count)); BUG_ON(!validate_regs_sorted(ring)); + + ret = init_hash_table(ring, cmd_tables, cmd_table_count); + if (ret) { + DRM_ERROR("CMD: cmd_parser_init failed!\n"); + fini_hash_table(ring); + return ret; + } + + ring->needs_cmd_parser = true; + + return 0; +} + +/** + * i915_cmd_parser_fini_ring() - clean up cmd parser related fields + * @ring: the ringbuffer to clean up + * + * Releases any resources related to command parsing that may have been + * initialized for the specified ring. + */ +void i915_cmd_parser_fini_ring(struct intel_engine_cs *ring) +{ + if (!ring->needs_cmd_parser) + return; + + fini_hash_table(ring); } static const struct drm_i915_cmd_descriptor* -find_cmd_in_table(const struct drm_i915_cmd_table *table, +find_cmd_in_table(struct intel_engine_cs *ring, u32 cmd_header) { - int i; + struct cmd_node *desc_node; - for (i = 0; i < table->count; i++) { - const struct drm_i915_cmd_descriptor *desc = &table->table[i]; + hash_for_each_possible(ring->cmd_hash, desc_node, node, + cmd_header & CMD_HASH_MASK) { + const struct drm_i915_cmd_descriptor *desc = desc_node->desc; u32 masked_cmd = desc->cmd.mask & cmd_header; u32 masked_value = desc->cmd.value & desc->cmd.mask; @@ -664,20 +761,16 @@ find_cmd_in_table(const struct drm_i915_cmd_table *table, * ring's default length encoding and returns default_desc. */ static const struct drm_i915_cmd_descriptor* -find_cmd(struct intel_ring_buffer *ring, +find_cmd(struct intel_engine_cs *ring, u32 cmd_header, struct drm_i915_cmd_descriptor *default_desc) { + const struct drm_i915_cmd_descriptor *desc; u32 mask; - int i; - - for (i = 0; i < ring->cmd_table_count; i++) { - const struct drm_i915_cmd_descriptor *desc; - desc = find_cmd_in_table(&ring->cmd_tables[i], cmd_header); - if (desc) - return desc; - } + desc = find_cmd_in_table(ring, cmd_header); + if (desc) + return desc; mask = ring->get_cmd_length_mask(cmd_header); if (!mask) @@ -744,12 +837,11 @@ finish: * * Return: true if the ring requires software command parsing */ -bool i915_needs_cmd_parser(struct intel_ring_buffer *ring) +bool i915_needs_cmd_parser(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; - /* No command tables indicates a platform without parsing */ - if (!ring->cmd_tables) + if (!ring->needs_cmd_parser) return false; /* @@ -763,7 +855,7 @@ bool i915_needs_cmd_parser(struct intel_ring_buffer *ring) return (i915.enable_cmd_parser == 1); } -static bool check_cmd(const struct intel_ring_buffer *ring, +static bool check_cmd(const struct intel_engine_cs *ring, const struct drm_i915_cmd_descriptor *desc, const u32 *cmd, const bool is_master, @@ -865,7 +957,7 @@ static bool check_cmd(const struct intel_ring_buffer *ring, * * Return: non-zero if the parser finds violations or otherwise fails */ -int i915_parse_cmds(struct intel_ring_buffer *ring, +int i915_parse_cmds(struct intel_engine_cs *ring, struct drm_i915_gem_object *batch_obj, u32 batch_start_offset, bool is_master) diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 18b3565f431a..333dd12d62f4 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -79,7 +79,7 @@ drm_add_fake_info_node(struct drm_minor *minor, static int i915_capabilities(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; const struct intel_device_info *info = INTEL_INFO(dev); @@ -172,7 +172,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) seq_printf(m, " (%s)", obj->ring->name); } -static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx) +static void describe_ctx(struct seq_file *m, struct intel_context *ctx) { seq_putc(m, ctx->is_initialized ? 'I' : 'i'); seq_putc(m, ctx->remap_slice ? 'R' : 'r'); @@ -181,7 +181,7 @@ static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx) static int i915_gem_object_list_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; uintptr_t list = (uintptr_t) node->info_ent->data; struct list_head *head; struct drm_device *dev = node->minor->dev; @@ -239,7 +239,7 @@ static int obj_rank_by_stolen(void *priv, static int i915_gem_stolen_list_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; @@ -371,7 +371,7 @@ static int per_file_stats(int id, void *ptr, void *data) static int i915_gem_object_info(struct seq_file *m, void* data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 count, mappable_count, purgeable_count; @@ -474,7 +474,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data) static int i915_gem_gtt_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; uintptr_t list = (uintptr_t) node->info_ent->data; struct drm_i915_private *dev_priv = dev->dev_private; @@ -509,12 +509,12 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data) static int i915_gem_pageflip_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; unsigned long flags; struct intel_crtc *crtc; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { const char pipe = pipe_name(crtc->pipe); const char plane = plane_name(crtc->plane); struct intel_unpin_work *work; @@ -559,10 +559,10 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data) static int i915_gem_request_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; struct drm_i915_gem_request *gem_request; int ret, count, i; @@ -594,7 +594,7 @@ static int i915_gem_request_info(struct seq_file *m, void *data) } static void i915_ring_seqno_info(struct seq_file *m, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { if (ring->get_seqno) { seq_printf(m, "Current sequence (%s): %u\n", @@ -604,10 +604,10 @@ static void i915_ring_seqno_info(struct seq_file *m, static int i915_gem_seqno_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i; ret = mutex_lock_interruptible(&dev->struct_mutex); @@ -627,10 +627,10 @@ static int i915_gem_seqno_info(struct seq_file *m, void *data) static int i915_interrupt_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i, pipe; ret = mutex_lock_interruptible(&dev->struct_mutex); @@ -638,7 +638,47 @@ static int i915_interrupt_info(struct seq_file *m, void *data) return ret; intel_runtime_pm_get(dev_priv); - if (INTEL_INFO(dev)->gen >= 8) { + if (IS_CHERRYVIEW(dev)) { + int i; + seq_printf(m, "Master Interrupt Control:\t%08x\n", + I915_READ(GEN8_MASTER_IRQ)); + + seq_printf(m, "Display IER:\t%08x\n", + I915_READ(VLV_IER)); + seq_printf(m, "Display IIR:\t%08x\n", + I915_READ(VLV_IIR)); + seq_printf(m, "Display IIR_RW:\t%08x\n", + I915_READ(VLV_IIR_RW)); + seq_printf(m, "Display IMR:\t%08x\n", + I915_READ(VLV_IMR)); + for_each_pipe(pipe) + seq_printf(m, "Pipe %c stat:\t%08x\n", + pipe_name(pipe), + I915_READ(PIPESTAT(pipe))); + + seq_printf(m, "Port hotplug:\t%08x\n", + I915_READ(PORT_HOTPLUG_EN)); + seq_printf(m, "DPFLIPSTAT:\t%08x\n", + I915_READ(VLV_DPFLIPSTAT)); + seq_printf(m, "DPINVGTT:\t%08x\n", + I915_READ(DPINVGTT)); + + for (i = 0; i < 4; i++) { + seq_printf(m, "GT Interrupt IMR %d:\t%08x\n", + i, I915_READ(GEN8_GT_IMR(i))); + seq_printf(m, "GT Interrupt IIR %d:\t%08x\n", + i, I915_READ(GEN8_GT_IIR(i))); + seq_printf(m, "GT Interrupt IER %d:\t%08x\n", + i, I915_READ(GEN8_GT_IER(i))); + } + + seq_printf(m, "PCU interrupt mask:\t%08x\n", + I915_READ(GEN8_PCU_IMR)); + seq_printf(m, "PCU interrupt identity:\t%08x\n", + I915_READ(GEN8_PCU_IIR)); + seq_printf(m, "PCU interrupt enable:\t%08x\n", + I915_READ(GEN8_PCU_IER)); + } else if (INTEL_INFO(dev)->gen >= 8) { seq_printf(m, "Master Interrupt Control:\t%08x\n", I915_READ(GEN8_MASTER_IRQ)); @@ -768,7 +808,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data) static int i915_gem_fence_regs_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int i, ret; @@ -797,10 +837,10 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data) static int i915_hws_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; const u32 *hws; int i; @@ -945,7 +985,7 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_next_seqno_fops, static int i915_rstdby_delays(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u16 crstanddelay; @@ -968,7 +1008,7 @@ static int i915_rstdby_delays(struct seq_file *m, void *unused) static int i915_frequency_info(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int ret = 0; @@ -1108,7 +1148,7 @@ out: static int i915_delayfreq_table(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 delayfreq; @@ -1139,7 +1179,7 @@ static inline int MAP_TO_MV(int map) static int i915_inttoext_table(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 inttoext; @@ -1163,7 +1203,7 @@ static int i915_inttoext_table(struct seq_file *m, void *unused) static int ironlake_drpc_info(struct seq_file *m) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 rgvmodectl, rstdbyctl; @@ -1233,7 +1273,7 @@ static int ironlake_drpc_info(struct seq_file *m) static int vlv_drpc_info(struct seq_file *m) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 rpmodectl1, rcctl1; @@ -1286,7 +1326,7 @@ static int vlv_drpc_info(struct seq_file *m) static int gen6_drpc_info(struct seq_file *m) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; u32 rpmodectl1, gt_core_status, rcctl1, rc6vids = 0; @@ -1385,7 +1425,7 @@ static int gen6_drpc_info(struct seq_file *m) static int i915_drpc_info(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; if (IS_VALLEYVIEW(dev)) @@ -1398,7 +1438,7 @@ static int i915_drpc_info(struct seq_file *m, void *unused) static int i915_fbc_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1460,7 +1500,7 @@ static int i915_fbc_status(struct seq_file *m, void *unused) static int i915_ips_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1483,7 +1523,7 @@ static int i915_ips_status(struct seq_file *m, void *unused) static int i915_sr_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; bool sr_enabled = false; @@ -1509,7 +1549,7 @@ static int i915_sr_status(struct seq_file *m, void *unused) static int i915_emon_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; unsigned long temp, chipset, gfx; @@ -1537,7 +1577,7 @@ static int i915_emon_status(struct seq_file *m, void *unused) static int i915_ring_freq_table(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int ret = 0; @@ -1580,7 +1620,7 @@ out: static int i915_gfxec(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int ret; @@ -1600,7 +1640,7 @@ static int i915_gfxec(struct seq_file *m, void *unused) static int i915_opregion(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_opregion *opregion = &dev_priv->opregion; @@ -1628,7 +1668,7 @@ out: static int i915_gem_framebuffer_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct intel_fbdev *ifbdev = NULL; struct intel_framebuffer *fb; @@ -1674,11 +1714,11 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) static int i915_context_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; - struct i915_hw_context *ctx; + struct intel_engine_cs *ring; + struct intel_context *ctx; int ret, i; ret = mutex_lock_interruptible(&dev->mode_config.mutex); @@ -1718,7 +1758,7 @@ static int i915_context_status(struct seq_file *m, void *unused) static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; unsigned forcewake_count = 0, fw_rendercount = 0, fw_mediacount = 0; @@ -1766,7 +1806,7 @@ static const char *swizzle_string(unsigned swizzle) static int i915_swizzle_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; int ret; @@ -1814,10 +1854,14 @@ static int i915_swizzle_info(struct seq_file *m, void *data) static int per_file_ctx(int id, void *ptr, void *data) { - struct i915_hw_context *ctx = ptr; + struct intel_context *ctx = ptr; struct seq_file *m = data; struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(ctx); + if (i915_gem_context_is_default(ctx)) + seq_puts(m, " default context:\n"); + else + seq_printf(m, " context %d:\n", ctx->id); ppgtt->debug_dump(ppgtt, m); return 0; @@ -1826,7 +1870,7 @@ static int per_file_ctx(int id, void *ptr, void *data) static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; int unused, i; @@ -1850,7 +1894,7 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev) static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; struct drm_file *file; int i; @@ -1877,12 +1921,9 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) list_for_each_entry_reverse(file, &dev->filelist, lhead) { struct drm_i915_file_private *file_priv = file->driver_priv; - struct i915_hw_ppgtt *pvt_ppgtt; - pvt_ppgtt = ctx_to_ppgtt(file_priv->private_default_ctx); seq_printf(m, "proc: %s\n", get_pid_task(file->pid, PIDTYPE_PID)->comm); - seq_puts(m, " default context:\n"); idr_for_each(&file_priv->context_idr, per_file_ctx, m); } seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK)); @@ -1890,7 +1931,7 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev) static int i915_ppgtt_info(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1912,7 +1953,7 @@ static int i915_ppgtt_info(struct seq_file *m, void *data) static int i915_llc(struct seq_file *m, void *data) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2018,7 +2059,7 @@ static int i915_energy_uJ(struct seq_file *m, void *data) static int i915_pc8_status(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2093,7 +2134,7 @@ static const char *power_domain_str(enum intel_display_power_domain domain) static int i915_power_domain_info(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct i915_power_domains *power_domains = &dev_priv->power_domains; @@ -2148,7 +2189,7 @@ static void intel_encoder_info(struct seq_file *m, struct intel_crtc *intel_crtc, struct intel_encoder *intel_encoder) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_crtc *crtc = &intel_crtc->base; struct intel_connector *intel_connector; @@ -2175,7 +2216,7 @@ static void intel_encoder_info(struct seq_file *m, static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_crtc *crtc = &intel_crtc->base; struct intel_encoder *intel_encoder; @@ -2264,10 +2305,8 @@ static bool cursor_active(struct drm_device *dev, int pipe) if (IS_845G(dev) || IS_I865G(dev)) state = I915_READ(_CURACNTR) & CURSOR_ENABLE; - else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) - state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; else - state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE; + state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; return state; } @@ -2277,10 +2316,7 @@ static bool cursor_position(struct drm_device *dev, int pipe, int *x, int *y) struct drm_i915_private *dev_priv = dev->dev_private; u32 pos; - if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev)) - pos = I915_READ(CURPOS_IVB(pipe)); - else - pos = I915_READ(CURPOS(pipe)); + pos = I915_READ(CURPOS(pipe)); *x = (pos >> CURSOR_X_SHIFT) & CURSOR_POS_MASK; if (pos & (CURSOR_POS_SIGN << CURSOR_X_SHIFT)) @@ -2295,7 +2331,7 @@ static bool cursor_position(struct drm_device *dev, int pipe, int *x, int *y) static int i915_display_info(struct seq_file *m, void *unused) { - struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *crtc; @@ -2305,7 +2341,7 @@ static int i915_display_info(struct seq_file *m, void *unused) drm_modeset_lock_all(dev); seq_printf(m, "CRTC info\n"); seq_printf(m, "---------\n"); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { bool active; int x, y; @@ -3084,7 +3120,7 @@ static const struct file_operations i915_display_crc_ctl_fops = { static void wm_latency_show(struct seq_file *m, const uint16_t wm[5]) { struct drm_device *dev = m->private; - int num_levels = IS_HASWELL(dev) || IS_BROADWELL(dev) ? 5 : 4; + int num_levels = ilk_wm_max_level(dev) + 1; int level; drm_modeset_lock_all(dev); @@ -3167,7 +3203,7 @@ static ssize_t wm_latency_write(struct file *file, const char __user *ubuf, struct seq_file *m = file->private_data; struct drm_device *dev = m->private; uint16_t new[5] = { 0 }; - int num_levels = IS_HASWELL(dev) || IS_BROADWELL(dev) ? 5 : 4; + int num_levels = ilk_wm_max_level(dev) + 1; int level; int ret; char tmp[32]; diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index d02c8de4bd6c..4e70de6ed468 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -44,6 +44,7 @@ #include <acpi/video.h> #include <linux/pm.h> #include <linux/pm_runtime.h> +#include <linux/oom.h> #define LP_RING(d) (&((struct drm_i915_private *)(d))->ring[RCS]) @@ -63,7 +64,7 @@ * has access to the ring. */ #define RING_LOCK_TEST_WITH_RETURN(dev, file) do { \ - if (LP_RING(dev->dev_private)->obj == NULL) \ + if (LP_RING(dev->dev_private)->buffer->obj == NULL) \ LOCK_TEST_WITH_RETURN(dev, file); \ } while (0) @@ -119,7 +120,7 @@ static void i915_write_hws_pga(struct drm_device *dev) static void i915_free_hws(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = LP_RING(dev_priv); + struct intel_engine_cs *ring = LP_RING(dev_priv); if (dev_priv->status_page_dmah) { drm_pci_free(dev, dev_priv->status_page_dmah); @@ -139,7 +140,8 @@ void i915_kernel_lost_context(struct drm_device * dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_master_private *master_priv; - struct intel_ring_buffer *ring = LP_RING(dev_priv); + struct intel_engine_cs *ring = LP_RING(dev_priv); + struct intel_ringbuffer *ringbuf = ring->buffer; /* * We should never lose context on the ring with modesetting @@ -148,17 +150,17 @@ void i915_kernel_lost_context(struct drm_device * dev) if (drm_core_check_feature(dev, DRIVER_MODESET)) return; - ring->head = I915_READ_HEAD(ring) & HEAD_ADDR; - ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR; - ring->space = ring->head - (ring->tail + I915_RING_FREE_SPACE); - if (ring->space < 0) - ring->space += ring->size; + ringbuf->head = I915_READ_HEAD(ring) & HEAD_ADDR; + ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR; + ringbuf->space = ringbuf->head - (ringbuf->tail + I915_RING_FREE_SPACE); + if (ringbuf->space < 0) + ringbuf->space += ringbuf->size; if (!dev->primary->master) return; master_priv = dev->primary->master->driver_priv; - if (ring->head == ring->tail && master_priv->sarea_priv) + if (ringbuf->head == ringbuf->tail && master_priv->sarea_priv) master_priv->sarea_priv->perf_boxes |= I915_BOX_RING_EMPTY; } @@ -201,7 +203,7 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init) } if (init->ring_size != 0) { - if (LP_RING(dev_priv)->obj != NULL) { + if (LP_RING(dev_priv)->buffer->obj != NULL) { i915_dma_cleanup(dev); DRM_ERROR("Client tried to initialize ringbuffer in " "GEM mode\n"); @@ -234,11 +236,11 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init) static int i915_dma_resume(struct drm_device * dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = LP_RING(dev_priv); + struct intel_engine_cs *ring = LP_RING(dev_priv); DRM_DEBUG_DRIVER("%s\n", __func__); - if (ring->virtual_start == NULL) { + if (ring->buffer->virtual_start == NULL) { DRM_ERROR("can not ioremap virtual address for" " ring buffer\n"); return -ENOMEM; @@ -360,7 +362,7 @@ static int i915_emit_cmds(struct drm_device * dev, int *buffer, int dwords) struct drm_i915_private *dev_priv = dev->dev_private; int i, ret; - if ((dwords+1) * sizeof(int) >= LP_RING(dev_priv)->size - 8) + if ((dwords+1) * sizeof(int) >= LP_RING(dev_priv)->buffer->size - 8) return -EINVAL; for (i = 0; i < dwords;) { @@ -782,7 +784,7 @@ static int i915_wait_irq(struct drm_device * dev, int irq_nr) struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv; int ret = 0; - struct intel_ring_buffer *ring = LP_RING(dev_priv); + struct intel_engine_cs *ring = LP_RING(dev_priv); DRM_DEBUG_DRIVER("irq_nr=%d breadcrumb=%d\n", irq_nr, READ_BREADCRUMB(dev_priv)); @@ -823,7 +825,7 @@ static int i915_irq_emit(struct drm_device *dev, void *data, if (drm_core_check_feature(dev, DRIVER_MODESET)) return -ENODEV; - if (!dev_priv || !LP_RING(dev_priv)->virtual_start) { + if (!dev_priv || !LP_RING(dev_priv)->buffer->virtual_start) { DRM_ERROR("called with no initialization\n"); return -EINVAL; } @@ -1073,7 +1075,7 @@ static int i915_set_status_page(struct drm_device *dev, void *data, { struct drm_i915_private *dev_priv = dev->dev_private; drm_i915_hws_addr_t *hws = data; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; if (drm_core_check_feature(dev, DRIVER_MODESET)) return -ENODEV; @@ -1570,7 +1572,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) spin_lock_init(&dev_priv->backlight_lock); spin_lock_init(&dev_priv->uncore.lock); spin_lock_init(&dev_priv->mm.object_stat_lock); - dev_priv->ring_index = 0; mutex_init(&dev_priv->dpio_lock); mutex_init(&dev_priv->modeset_restore_lock); @@ -1741,8 +1742,8 @@ out_power_well: intel_power_domains_remove(dev_priv); drm_vblank_cleanup(dev); out_gem_unload: - if (dev_priv->mm.inactive_shrinker.scan_objects) - unregister_shrinker(&dev_priv->mm.inactive_shrinker); + WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier)); + unregister_shrinker(&dev_priv->mm.shrinker); if (dev->pdev->msi_enabled) pci_disable_msi(dev->pdev); @@ -1793,8 +1794,8 @@ int i915_driver_unload(struct drm_device *dev) i915_teardown_sysfs(dev); - if (dev_priv->mm.inactive_shrinker.scan_objects) - unregister_shrinker(&dev_priv->mm.inactive_shrinker); + WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier)); + unregister_shrinker(&dev_priv->mm.shrinker); io_mapping_free(dev_priv->gtt.mappable); arch_phys_wc_del(dev_priv->gtt.mtrr); @@ -1867,7 +1868,7 @@ int i915_driver_unload(struct drm_device *dev) kmem_cache_destroy(dev_priv->slab); pci_dev_put(dev_priv->bridge_dev); - kfree(dev->dev_private); + kfree(dev_priv); return 0; } @@ -1983,6 +1984,7 @@ const struct drm_ioctl_desc i915_ioctls[] = { DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_get_reset_stats_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(I915_GEM_USERPTR, i915_gem_userptr_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), }; int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 208e185c16a9..4619c9e51907 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -36,6 +36,7 @@ #include <linux/console.h> #include <linux/module.h> +#include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> static struct drm_driver driver; @@ -49,12 +50,30 @@ static struct drm_driver driver; .dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET }, \ .palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET } +#define GEN_CHV_PIPEOFFSETS \ + .pipe_offsets = { PIPE_A_OFFSET, PIPE_B_OFFSET, \ + CHV_PIPE_C_OFFSET }, \ + .trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \ + CHV_TRANSCODER_C_OFFSET, }, \ + .dpll_offsets = { DPLL_A_OFFSET, DPLL_B_OFFSET, \ + CHV_DPLL_C_OFFSET }, \ + .dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET, \ + CHV_DPLL_C_MD_OFFSET }, \ + .palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET, \ + CHV_PALETTE_C_OFFSET } + +#define CURSOR_OFFSETS \ + .cursor_offsets = { CURSOR_A_OFFSET, CURSOR_B_OFFSET, CHV_CURSOR_C_OFFSET } + +#define IVB_CURSOR_OFFSETS \ + .cursor_offsets = { CURSOR_A_OFFSET, IVB_CURSOR_B_OFFSET, IVB_CURSOR_C_OFFSET } 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, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_845g_info = { @@ -62,6 +81,7 @@ static const struct intel_device_info intel_845g_info = { .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i85x_info = { @@ -71,6 +91,7 @@ static const struct intel_device_info intel_i85x_info = { .has_fbc = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i865g_info = { @@ -78,6 +99,7 @@ static const struct intel_device_info intel_i865g_info = { .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i915g_info = { @@ -85,6 +107,7 @@ static const struct intel_device_info intel_i915g_info = { .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i915gm_info = { .gen = 3, .is_mobile = 1, .num_pipes = 2, @@ -94,12 +117,14 @@ static const struct intel_device_info intel_i915gm_info = { .has_fbc = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i945g_info = { .gen = 3, .has_hotplug = 1, .cursor_needs_physical = 1, .num_pipes = 2, .has_overlay = 1, .overlay_needs_physical = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i945gm_info = { .gen = 3, .is_i945gm = 1, .is_mobile = 1, .num_pipes = 2, @@ -109,6 +134,7 @@ static const struct intel_device_info intel_i945gm_info = { .has_fbc = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i965g_info = { @@ -117,6 +143,7 @@ static const struct intel_device_info intel_i965g_info = { .has_overlay = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_i965gm_info = { @@ -126,6 +153,7 @@ static const struct intel_device_info intel_i965gm_info = { .supports_tv = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_g33_info = { @@ -134,6 +162,7 @@ static const struct intel_device_info intel_g33_info = { .has_overlay = 1, .ring_mask = RENDER_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_g45_info = { @@ -141,6 +170,7 @@ static const struct intel_device_info intel_g45_info = { .has_pipe_cxsr = 1, .has_hotplug = 1, .ring_mask = RENDER_RING | BSD_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_gm45_info = { @@ -150,6 +180,7 @@ static const struct intel_device_info intel_gm45_info = { .supports_tv = 1, .ring_mask = RENDER_RING | BSD_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_pineview_info = { @@ -157,6 +188,7 @@ static const struct intel_device_info intel_pineview_info = { .need_gfx_hws = 1, .has_hotplug = 1, .has_overlay = 1, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_ironlake_d_info = { @@ -164,6 +196,7 @@ static const struct intel_device_info intel_ironlake_d_info = { .need_gfx_hws = 1, .has_hotplug = 1, .ring_mask = RENDER_RING | BSD_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_ironlake_m_info = { @@ -172,6 +205,7 @@ static const struct intel_device_info intel_ironlake_m_info = { .has_fbc = 1, .ring_mask = RENDER_RING | BSD_RING, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_sandybridge_d_info = { @@ -181,6 +215,7 @@ static const struct intel_device_info intel_sandybridge_d_info = { .ring_mask = RENDER_RING | BSD_RING | BLT_RING, .has_llc = 1, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_sandybridge_m_info = { @@ -190,6 +225,7 @@ static const struct intel_device_info intel_sandybridge_m_info = { .ring_mask = RENDER_RING | BSD_RING | BLT_RING, .has_llc = 1, GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; #define GEN7_FEATURES \ @@ -203,6 +239,7 @@ static const struct intel_device_info intel_ivybridge_d_info = { GEN7_FEATURES, .is_ivybridge = 1, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_ivybridge_m_info = { @@ -210,6 +247,7 @@ static const struct intel_device_info intel_ivybridge_m_info = { .is_ivybridge = 1, .is_mobile = 1, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_ivybridge_q_info = { @@ -217,6 +255,7 @@ static const struct intel_device_info intel_ivybridge_q_info = { .is_ivybridge = 1, .num_pipes = 0, /* legal, last one wins */ GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_valleyview_m_info = { @@ -228,6 +267,7 @@ static const struct intel_device_info intel_valleyview_m_info = { .has_fbc = 0, /* legal, last one wins */ .has_llc = 0, /* legal, last one wins */ GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_valleyview_d_info = { @@ -238,6 +278,7 @@ static const struct intel_device_info intel_valleyview_d_info = { .has_fbc = 0, /* legal, last one wins */ .has_llc = 0, /* legal, last one wins */ GEN_DEFAULT_PIPEOFFSETS, + CURSOR_OFFSETS, }; static const struct intel_device_info intel_haswell_d_info = { @@ -247,6 +288,7 @@ static const struct intel_device_info intel_haswell_d_info = { .has_fpga_dbg = 1, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_haswell_m_info = { @@ -257,6 +299,7 @@ static const struct intel_device_info intel_haswell_m_info = { .has_fpga_dbg = 1, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_broadwell_d_info = { @@ -267,6 +310,7 @@ static const struct intel_device_info intel_broadwell_d_info = { .has_ddi = 1, .has_fbc = 1, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, }; static const struct intel_device_info intel_broadwell_m_info = { @@ -297,6 +341,18 @@ static const struct intel_device_info intel_broadwell_gt3m_info = { .has_ddi = 1, .has_fbc = 1, GEN_DEFAULT_PIPEOFFSETS, + IVB_CURSOR_OFFSETS, +}; + +static const struct intel_device_info intel_cherryview_info = { + .is_preliminary = 1, + .gen = 8, .num_pipes = 3, + .need_gfx_hws = 1, .has_hotplug = 1, + .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, + .is_valleyview = 1, + .display_mmio_offset = VLV_DISPLAY_BASE, + GEN_CHV_PIPEOFFSETS, + CURSOR_OFFSETS, }; /* @@ -334,7 +390,8 @@ static const struct intel_device_info intel_broadwell_gt3m_info = { INTEL_BDW_GT12M_IDS(&intel_broadwell_m_info), \ INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info), \ INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info), \ - INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info) + INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info), \ + INTEL_CHV_IDS(&intel_cherryview_info) static const struct pci_device_id pciidlist[] = { /* aka */ INTEL_PCI_IDS, @@ -467,17 +524,21 @@ static int i915_drm_freeze(struct drm_device *dev) return error; } - cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work); - drm_irq_uninstall(dev); dev_priv->enable_hotplug_processing = false; + + intel_disable_gt_powersave(dev); + /* * Disable CRTCs directly since we want to preserve sw state * for _thaw. */ mutex_lock(&dev->mode_config.mutex); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + for_each_crtc(dev, crtc) { + mutex_lock(&crtc->mutex); dev_priv->display.crtc_disable(crtc); + mutex_unlock(&crtc->mutex); + } mutex_unlock(&dev->mode_config.mutex); intel_modeset_suspend_hw(dev); @@ -541,24 +602,6 @@ void intel_console_resume(struct work_struct *work) console_unlock(); } -static void intel_resume_hotplug(struct drm_device *dev) -{ - struct drm_mode_config *mode_config = &dev->mode_config; - struct intel_encoder *encoder; - - mutex_lock(&mode_config->mutex); - DRM_DEBUG_KMS("running encoder hotplug functions\n"); - - list_for_each_entry(encoder, &mode_config->encoder_list, base.head) - if (encoder->hot_plug) - encoder->hot_plug(encoder); - - mutex_unlock(&mode_config->mutex); - - /* Just fire off a uevent and let userspace tell us what to do */ - drm_helper_hpd_irq_event(dev); -} - static int i915_drm_thaw_early(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -614,7 +657,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings) intel_hpd_init(dev); dev_priv->enable_hotplug_processing = true; /* Config may have changed between suspend and resume */ - intel_resume_hotplug(dev); + drm_helper_hpd_irq_event(dev); } intel_opregion_init(dev); @@ -916,21 +959,219 @@ static int i915_pm_poweroff(struct device *dev) return i915_drm_freeze(drm_dev); } -static void hsw_runtime_suspend(struct drm_i915_private *dev_priv) +static int hsw_runtime_suspend(struct drm_i915_private *dev_priv) { hsw_enable_pc8(dev_priv); + + return 0; } -static void snb_runtime_resume(struct drm_i915_private *dev_priv) +static int snb_runtime_resume(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; intel_init_pch_refclk(dev); + + return 0; } -static void hsw_runtime_resume(struct drm_i915_private *dev_priv) +static int hsw_runtime_resume(struct drm_i915_private *dev_priv) { hsw_disable_pc8(dev_priv); + + return 0; +} + +/* + * Save all Gunit registers that may be lost after a D3 and a subsequent + * S0i[R123] transition. The list of registers needing a save/restore is + * defined in the VLV2_S0IXRegs document. This documents marks all Gunit + * registers in the following way: + * - Driver: saved/restored by the driver + * - Punit : saved/restored by the Punit firmware + * - No, w/o marking: no need to save/restore, since the register is R/O or + * used internally by the HW in a way that doesn't depend + * keeping the content across a suspend/resume. + * - Debug : used for debugging + * + * We save/restore all registers marked with 'Driver', with the following + * exceptions: + * - Registers out of use, including also registers marked with 'Debug'. + * These have no effect on the driver's operation, so we don't save/restore + * them to reduce the overhead. + * - Registers that are fully setup by an initialization function called from + * the resume path. For example many clock gating and RPS/RC6 registers. + * - Registers that provide the right functionality with their reset defaults. + * + * TODO: Except for registers that based on the above 3 criteria can be safely + * ignored, we save/restore all others, practically treating the HW context as + * a black-box for the driver. Further investigation is needed to reduce the + * saved/restored registers even further, by following the same 3 criteria. + */ +static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv) +{ + struct vlv_s0ix_state *s = &dev_priv->vlv_s0ix_state; + int i; + + /* GAM 0x4000-0x4770 */ + s->wr_watermark = I915_READ(GEN7_WR_WATERMARK); + s->gfx_prio_ctrl = I915_READ(GEN7_GFX_PRIO_CTRL); + s->arb_mode = I915_READ(ARB_MODE); + s->gfx_pend_tlb0 = I915_READ(GEN7_GFX_PEND_TLB0); + s->gfx_pend_tlb1 = I915_READ(GEN7_GFX_PEND_TLB1); + + for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++) + s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS_BASE + i * 4); + + s->media_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); + s->gfx_max_req_count = I915_READ(GEN7_MEDIA_MAX_REQ_COUNT); + + s->render_hwsp = I915_READ(RENDER_HWS_PGA_GEN7); + s->ecochk = I915_READ(GAM_ECOCHK); + s->bsd_hwsp = I915_READ(BSD_HWS_PGA_GEN7); + s->blt_hwsp = I915_READ(BLT_HWS_PGA_GEN7); + + s->tlb_rd_addr = I915_READ(GEN7_TLB_RD_ADDR); + + /* MBC 0x9024-0x91D0, 0x8500 */ + s->g3dctl = I915_READ(VLV_G3DCTL); + s->gsckgctl = I915_READ(VLV_GSCKGCTL); + s->mbctl = I915_READ(GEN6_MBCTL); + + /* GCP 0x9400-0x9424, 0x8100-0x810C */ + s->ucgctl1 = I915_READ(GEN6_UCGCTL1); + s->ucgctl3 = I915_READ(GEN6_UCGCTL3); + s->rcgctl1 = I915_READ(GEN6_RCGCTL1); + s->rcgctl2 = I915_READ(GEN6_RCGCTL2); + s->rstctl = I915_READ(GEN6_RSTCTL); + s->misccpctl = I915_READ(GEN7_MISCCPCTL); + + /* GPM 0xA000-0xAA84, 0x8000-0x80FC */ + s->gfxpause = I915_READ(GEN6_GFXPAUSE); + s->rpdeuhwtc = I915_READ(GEN6_RPDEUHWTC); + s->rpdeuc = I915_READ(GEN6_RPDEUC); + s->ecobus = I915_READ(ECOBUS); + s->pwrdwnupctl = I915_READ(VLV_PWRDWNUPCTL); + s->rp_down_timeout = I915_READ(GEN6_RP_DOWN_TIMEOUT); + s->rp_deucsw = I915_READ(GEN6_RPDEUCSW); + s->rcubmabdtmr = I915_READ(GEN6_RCUBMABDTMR); + s->rcedata = I915_READ(VLV_RCEDATA); + s->spare2gh = I915_READ(VLV_SPAREG2H); + + /* Display CZ domain, 0x4400C-0x4402C, 0x4F000-0x4F11F */ + s->gt_imr = I915_READ(GTIMR); + s->gt_ier = I915_READ(GTIER); + s->pm_imr = I915_READ(GEN6_PMIMR); + s->pm_ier = I915_READ(GEN6_PMIER); + + for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++) + s->gt_scratch[i] = I915_READ(GEN7_GT_SCRATCH_BASE + i * 4); + + /* GT SA CZ domain, 0x100000-0x138124 */ + s->tilectl = I915_READ(TILECTL); + s->gt_fifoctl = I915_READ(GTFIFOCTL); + s->gtlc_wake_ctrl = I915_READ(VLV_GTLC_WAKE_CTRL); + s->gtlc_survive = I915_READ(VLV_GTLC_SURVIVABILITY_REG); + s->pmwgicz = I915_READ(VLV_PMWGICZ); + + /* Gunit-Display CZ domain, 0x182028-0x1821CF */ + s->gu_ctl0 = I915_READ(VLV_GU_CTL0); + s->gu_ctl1 = I915_READ(VLV_GU_CTL1); + s->clock_gate_dis2 = I915_READ(VLV_GUNIT_CLOCK_GATE2); + + /* + * Not saving any of: + * DFT, 0x9800-0x9EC0 + * SARB, 0xB000-0xB1FC + * GAC, 0x5208-0x524C, 0x14000-0x14C000 + * PCI CFG + */ +} + +static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv) +{ + struct vlv_s0ix_state *s = &dev_priv->vlv_s0ix_state; + u32 val; + int i; + + /* GAM 0x4000-0x4770 */ + I915_WRITE(GEN7_WR_WATERMARK, s->wr_watermark); + I915_WRITE(GEN7_GFX_PRIO_CTRL, s->gfx_prio_ctrl); + I915_WRITE(ARB_MODE, s->arb_mode | (0xffff << 16)); + I915_WRITE(GEN7_GFX_PEND_TLB0, s->gfx_pend_tlb0); + I915_WRITE(GEN7_GFX_PEND_TLB1, s->gfx_pend_tlb1); + + for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++) + I915_WRITE(GEN7_LRA_LIMITS_BASE + i * 4, s->lra_limits[i]); + + I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->media_max_req_count); + I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->gfx_max_req_count); + + I915_WRITE(RENDER_HWS_PGA_GEN7, s->render_hwsp); + I915_WRITE(GAM_ECOCHK, s->ecochk); + I915_WRITE(BSD_HWS_PGA_GEN7, s->bsd_hwsp); + I915_WRITE(BLT_HWS_PGA_GEN7, s->blt_hwsp); + + I915_WRITE(GEN7_TLB_RD_ADDR, s->tlb_rd_addr); + + /* MBC 0x9024-0x91D0, 0x8500 */ + I915_WRITE(VLV_G3DCTL, s->g3dctl); + I915_WRITE(VLV_GSCKGCTL, s->gsckgctl); + I915_WRITE(GEN6_MBCTL, s->mbctl); + + /* GCP 0x9400-0x9424, 0x8100-0x810C */ + I915_WRITE(GEN6_UCGCTL1, s->ucgctl1); + I915_WRITE(GEN6_UCGCTL3, s->ucgctl3); + I915_WRITE(GEN6_RCGCTL1, s->rcgctl1); + I915_WRITE(GEN6_RCGCTL2, s->rcgctl2); + I915_WRITE(GEN6_RSTCTL, s->rstctl); + I915_WRITE(GEN7_MISCCPCTL, s->misccpctl); + + /* GPM 0xA000-0xAA84, 0x8000-0x80FC */ + I915_WRITE(GEN6_GFXPAUSE, s->gfxpause); + I915_WRITE(GEN6_RPDEUHWTC, s->rpdeuhwtc); + I915_WRITE(GEN6_RPDEUC, s->rpdeuc); + I915_WRITE(ECOBUS, s->ecobus); + I915_WRITE(VLV_PWRDWNUPCTL, s->pwrdwnupctl); + I915_WRITE(GEN6_RP_DOWN_TIMEOUT,s->rp_down_timeout); + I915_WRITE(GEN6_RPDEUCSW, s->rp_deucsw); + I915_WRITE(GEN6_RCUBMABDTMR, s->rcubmabdtmr); + I915_WRITE(VLV_RCEDATA, s->rcedata); + I915_WRITE(VLV_SPAREG2H, s->spare2gh); + + /* Display CZ domain, 0x4400C-0x4402C, 0x4F000-0x4F11F */ + I915_WRITE(GTIMR, s->gt_imr); + I915_WRITE(GTIER, s->gt_ier); + I915_WRITE(GEN6_PMIMR, s->pm_imr); + I915_WRITE(GEN6_PMIER, s->pm_ier); + + for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++) + I915_WRITE(GEN7_GT_SCRATCH_BASE + i * 4, s->gt_scratch[i]); + + /* GT SA CZ domain, 0x100000-0x138124 */ + I915_WRITE(TILECTL, s->tilectl); + I915_WRITE(GTFIFOCTL, s->gt_fifoctl); + /* + * Preserve the GT allow wake and GFX force clock bit, they are not + * be restored, as they are used to control the s0ix suspend/resume + * sequence by the caller. + */ + val = I915_READ(VLV_GTLC_WAKE_CTRL); + val &= VLV_GTLC_ALLOWWAKEREQ; + val |= s->gtlc_wake_ctrl & ~VLV_GTLC_ALLOWWAKEREQ; + I915_WRITE(VLV_GTLC_WAKE_CTRL, val); + + val = I915_READ(VLV_GTLC_SURVIVABILITY_REG); + val &= VLV_GFX_CLK_FORCE_ON_BIT; + val |= s->gtlc_survive & ~VLV_GFX_CLK_FORCE_ON_BIT; + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, val); + + I915_WRITE(VLV_PMWGICZ, s->pmwgicz); + + /* Gunit-Display CZ domain, 0x182028-0x1821CF */ + I915_WRITE(VLV_GU_CTL0, s->gu_ctl0); + I915_WRITE(VLV_GU_CTL1, s->gu_ctl1); + I915_WRITE(VLV_GUNIT_CLOCK_GATE2, s->clock_gate_dis2); } int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on) @@ -970,11 +1211,143 @@ int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on) #undef COND } +static int vlv_allow_gt_wake(struct drm_i915_private *dev_priv, bool allow) +{ + u32 val; + int err = 0; + + val = I915_READ(VLV_GTLC_WAKE_CTRL); + val &= ~VLV_GTLC_ALLOWWAKEREQ; + if (allow) + val |= VLV_GTLC_ALLOWWAKEREQ; + I915_WRITE(VLV_GTLC_WAKE_CTRL, val); + POSTING_READ(VLV_GTLC_WAKE_CTRL); + +#define COND (!!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEACK) == \ + allow) + err = wait_for(COND, 1); + if (err) + DRM_ERROR("timeout disabling GT waking\n"); + return err; +#undef COND +} + +static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv, + bool wait_for_on) +{ + u32 mask; + u32 val; + int err; + + mask = VLV_GTLC_PW_MEDIA_STATUS_MASK | VLV_GTLC_PW_RENDER_STATUS_MASK; + val = wait_for_on ? mask : 0; +#define COND ((I915_READ(VLV_GTLC_PW_STATUS) & mask) == val) + if (COND) + return 0; + + DRM_DEBUG_KMS("waiting for GT wells to go %s (%08x)\n", + wait_for_on ? "on" : "off", + I915_READ(VLV_GTLC_PW_STATUS)); + + /* + * RC6 transitioning can be delayed up to 2 msec (see + * valleyview_enable_rps), use 3 msec for safety. + */ + err = wait_for(COND, 3); + if (err) + DRM_ERROR("timeout waiting for GT wells to go %s\n", + wait_for_on ? "on" : "off"); + + return err; +#undef COND +} + +static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv) +{ + if (!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEERR)) + return; + + DRM_ERROR("GT register access while GT waking disabled\n"); + I915_WRITE(VLV_GTLC_PW_STATUS, VLV_GTLC_ALLOWWAKEERR); +} + +static int vlv_runtime_suspend(struct drm_i915_private *dev_priv) +{ + u32 mask; + int err; + + /* + * Bspec defines the following GT well on flags as debug only, so + * don't treat them as hard failures. + */ + (void)vlv_wait_for_gt_wells(dev_priv, false); + + mask = VLV_GTLC_RENDER_CTX_EXISTS | VLV_GTLC_MEDIA_CTX_EXISTS; + WARN_ON((I915_READ(VLV_GTLC_WAKE_CTRL) & mask) != mask); + + vlv_check_no_gt_access(dev_priv); + + err = vlv_force_gfx_clock(dev_priv, true); + if (err) + goto err1; + + err = vlv_allow_gt_wake(dev_priv, false); + if (err) + goto err2; + vlv_save_gunit_s0ix_state(dev_priv); + + err = vlv_force_gfx_clock(dev_priv, false); + if (err) + goto err2; + + return 0; + +err2: + /* For safety always re-enable waking and disable gfx clock forcing */ + vlv_allow_gt_wake(dev_priv, true); +err1: + vlv_force_gfx_clock(dev_priv, false); + + return err; +} + +static int vlv_runtime_resume(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + int err; + int ret; + + /* + * If any of the steps fail just try to continue, that's the best we + * can do at this point. Return the first error code (which will also + * leave RPM permanently disabled). + */ + ret = vlv_force_gfx_clock(dev_priv, true); + + vlv_restore_gunit_s0ix_state(dev_priv); + + err = vlv_allow_gt_wake(dev_priv, true); + if (!ret) + ret = err; + + err = vlv_force_gfx_clock(dev_priv, false); + if (!ret) + ret = err; + + vlv_check_no_gt_access(dev_priv); + + intel_init_clock_gating(dev); + i915_gem_restore_fences(dev); + + return ret; +} + static int intel_runtime_suspend(struct device *device) { struct pci_dev *pdev = to_pci_dev(device); struct drm_device *dev = pci_get_drvdata(pdev); struct drm_i915_private *dev_priv = dev->dev_private; + int ret; if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6(dev)))) return -ENODEV; @@ -985,6 +1358,30 @@ static int intel_runtime_suspend(struct device *device) DRM_DEBUG_KMS("Suspending device\n"); /* + * We could deadlock here in case another thread holding struct_mutex + * calls RPM suspend concurrently, since the RPM suspend will wait + * first for this RPM suspend to finish. In this case the concurrent + * RPM resume will be followed by its RPM suspend counterpart. Still + * for consistency return -EAGAIN, which will reschedule this suspend. + */ + if (!mutex_trylock(&dev->struct_mutex)) { + DRM_DEBUG_KMS("device lock contention, deffering suspend\n"); + /* + * Bump the expiration timestamp, otherwise the suspend won't + * be rescheduled. + */ + pm_runtime_mark_last_busy(device); + + return -EAGAIN; + } + /* + * We are safe here against re-faults, since the fault handler takes + * an RPM reference. + */ + i915_gem_release_all_mmaps(dev_priv); + mutex_unlock(&dev->struct_mutex); + + /* * rps.work can't be rearmed here, since we get here only after making * sure the GPU is idle and the RPS freq is set to the minimum. See * intel_mark_idle(). @@ -992,14 +1389,23 @@ static int intel_runtime_suspend(struct device *device) cancel_work_sync(&dev_priv->rps.work); intel_runtime_pm_disable_interrupts(dev); - if (IS_GEN6(dev)) - ; - else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) - hsw_runtime_suspend(dev_priv); - else + if (IS_GEN6(dev)) { + ret = 0; + } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { + ret = hsw_runtime_suspend(dev_priv); + } else if (IS_VALLEYVIEW(dev)) { + ret = vlv_runtime_suspend(dev_priv); + } else { + ret = -ENODEV; WARN_ON(1); + } - i915_gem_release_all_mmaps(dev_priv); + if (ret) { + DRM_ERROR("Runtime suspend failed, disabling it (%d)\n", ret); + intel_runtime_pm_restore_interrupts(dev); + + return ret; + } del_timer_sync(&dev_priv->gpu_error.hangcheck_timer); dev_priv->pm.suspended = true; @@ -1022,6 +1428,7 @@ static int intel_runtime_resume(struct device *device) struct pci_dev *pdev = to_pci_dev(device); struct drm_device *dev = pci_get_drvdata(pdev); struct drm_i915_private *dev_priv = dev->dev_private; + int ret; WARN_ON(!HAS_RUNTIME_PM(dev)); @@ -1030,21 +1437,33 @@ static int intel_runtime_resume(struct device *device) intel_opregion_notify_adapter(dev, PCI_D0); dev_priv->pm.suspended = false; - if (IS_GEN6(dev)) - snb_runtime_resume(dev_priv); - else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) - hsw_runtime_resume(dev_priv); - else + if (IS_GEN6(dev)) { + ret = snb_runtime_resume(dev_priv); + } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { + ret = hsw_runtime_resume(dev_priv); + } else if (IS_VALLEYVIEW(dev)) { + ret = vlv_runtime_resume(dev_priv); + } else { WARN_ON(1); + ret = -ENODEV; + } + /* + * No point of rolling back things in case of an error, as the best + * we can do is to hope that things will still work (and disable RPM). + */ i915_gem_init_swizzling(dev); gen6_update_ring_freq(dev); intel_runtime_pm_restore_interrupts(dev); intel_reset_gt_powersave(dev); - DRM_DEBUG_KMS("Device resumed\n"); - return 0; + if (ret) + DRM_ERROR("Runtime resume failed, disabling it (%d)\n", ret); + else + DRM_DEBUG_KMS("Device resumed\n"); + + return ret; } static const struct dev_pm_ops i915_pm_ops = { diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 3fc2e3d71136..8f68678f361f 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -41,6 +41,7 @@ #include <linux/i2c-algo-bit.h> #include <drm/intel-gtt.h> #include <linux/backlight.h> +#include <linux/hashtable.h> #include <linux/intel-iommu.h> #include <linux/kref.h> #include <linux/pm_qos.h> @@ -92,7 +93,7 @@ enum port { }; #define port_name(p) ((p) + 'A') -#define I915_NUM_PHYS_VLV 1 +#define I915_NUM_PHYS_VLV 2 enum dpio_channel { DPIO_CH0, @@ -163,6 +164,12 @@ enum hpd_pin { #define for_each_pipe(p) for ((p) = 0; (p) < INTEL_INFO(dev)->num_pipes; (p)++) #define for_each_sprite(p, s) for ((s) = 0; (s) < INTEL_INFO(dev)->num_sprites[(p)]; (s)++) +#define for_each_crtc(dev, crtc) \ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + +#define for_each_intel_crtc(dev, intel_crtc) \ + list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) + #define for_each_encoder_on_crtc(dev, __crtc, intel_encoder) \ list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \ if ((intel_encoder)->base.crtc == (__crtc)) @@ -172,6 +179,7 @@ enum hpd_pin { if ((intel_connector)->base.encoder == (__encoder)) struct drm_i915_private; +struct i915_mmu_object; enum intel_dpll_id { DPLL_ID_PRIVATE = -1, /* non-shared dpll in use */ @@ -397,6 +405,7 @@ struct drm_i915_error_state { u32 tiling:2; u32 dirty:1; u32 purgeable:1; + u32 userptr:1; s32 ring:4; u32 cache_level:3; } **active_bo, **pinned_bo; @@ -461,10 +470,11 @@ struct drm_i915_display_funcs { int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags); - int (*update_primary_plane)(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y); + void (*update_primary_plane)(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + int x, int y); void (*hpd_irq_setup)(struct drm_device *dev); /* clock updates for mode set */ /* cursor updates */ @@ -557,6 +567,7 @@ struct intel_device_info { int dpll_offsets[I915_MAX_PIPES]; int dpll_md_offsets[I915_MAX_PIPES]; int palette_offsets[I915_MAX_PIPES]; + int cursor_offsets[I915_MAX_PIPES]; }; #undef DEFINE_FLAG @@ -588,13 +599,13 @@ struct i915_ctx_hang_stats { /* This must match up with the value previously used for execbuf2.rsvd1. */ #define DEFAULT_CONTEXT_ID 0 -struct i915_hw_context { +struct intel_context { struct kref ref; int id; bool is_initialized; uint8_t remap_slice; struct drm_i915_file_private *file_priv; - struct intel_ring_buffer *last_ring; + struct intel_engine_cs *last_ring; struct drm_i915_gem_object *obj; struct i915_ctx_hang_stats hang_stats; struct i915_address_space *vm; @@ -819,6 +830,67 @@ struct i915_suspend_saved_registers { u32 savePCH_PORT_HOTPLUG; }; +struct vlv_s0ix_state { + /* GAM */ + u32 wr_watermark; + u32 gfx_prio_ctrl; + u32 arb_mode; + u32 gfx_pend_tlb0; + u32 gfx_pend_tlb1; + u32 lra_limits[GEN7_LRA_LIMITS_REG_NUM]; + u32 media_max_req_count; + u32 gfx_max_req_count; + u32 render_hwsp; + u32 ecochk; + u32 bsd_hwsp; + u32 blt_hwsp; + u32 tlb_rd_addr; + + /* MBC */ + u32 g3dctl; + u32 gsckgctl; + u32 mbctl; + + /* GCP */ + u32 ucgctl1; + u32 ucgctl3; + u32 rcgctl1; + u32 rcgctl2; + u32 rstctl; + u32 misccpctl; + + /* GPM */ + u32 gfxpause; + u32 rpdeuhwtc; + u32 rpdeuc; + u32 ecobus; + u32 pwrdwnupctl; + u32 rp_down_timeout; + u32 rp_deucsw; + u32 rcubmabdtmr; + u32 rcedata; + u32 spare2gh; + + /* Display 1 CZ domain */ + u32 gt_imr; + u32 gt_ier; + u32 pm_imr; + u32 pm_ier; + u32 gt_scratch[GEN7_GT_SCRATCH_REG_NUM]; + + /* GT SA CZ domain */ + u32 tilectl; + u32 gt_fifoctl; + u32 gtlc_wake_ctrl; + u32 gtlc_survive; + u32 pmwgicz; + + /* Display 2 CZ domain */ + u32 gu_ctl0; + u32 gu_ctl1; + u32 clock_gate_dis2; +}; + struct intel_gen6_power_mgmt { /* work and pm_iir are protected by dev_priv->irq_lock */ struct work_struct work; @@ -987,7 +1059,8 @@ struct i915_gem_mm { /** PPGTT used for aliasing the PPGTT with the GTT */ struct i915_hw_ppgtt *aliasing_ppgtt; - struct shrinker inactive_shrinker; + struct notifier_block oom_notifier; + struct shrinker shrinker; bool shrinker_no_lock_stealing; /** LRU list of objects with fence regs on them. */ @@ -1025,6 +1098,9 @@ struct i915_gem_mm { */ bool busy; + /* the indicator for dispatch video commands on two BSD rings */ + int bsd_ring_dispatch_index; + /** Bit 6 swizzling required for X tiling */ uint32_t bit_6_swizzle_x; /** Bit 6 swizzling required for Y tiling */ @@ -1290,10 +1366,13 @@ struct drm_i915_private { */ uint32_t gpio_mmio_base; + /* MMIO base address for MIPI regs */ + uint32_t mipi_mmio_base; + wait_queue_head_t gmbus_wait_queue; struct pci_dev *bridge_dev; - struct intel_ring_buffer ring[I915_NUM_RINGS]; + struct intel_engine_cs ring[I915_NUM_RINGS]; uint32_t last_seqno, next_seqno; drm_dma_handle_t *status_page_dmah; @@ -1380,6 +1459,9 @@ struct drm_i915_private { struct i915_gtt gtt; /* VM representing the global address space */ struct i915_gem_mm mm; +#if defined(CONFIG_MMU_NOTIFIER) + DECLARE_HASHTABLE(mmu_notifiers, 7); +#endif /* Kernel Modesetting */ @@ -1448,6 +1530,7 @@ struct drm_i915_private { u32 suspend_count; struct i915_suspend_saved_registers regfile; + struct vlv_s0ix_state vlv_s0ix_state; struct { /* @@ -1473,8 +1556,11 @@ struct drm_i915_private { struct i915_dri1_state dri1; /* Old ums support infrastructure, same warning applies. */ struct i915_ums_state ums; - /* the indicator for dispatch video commands on two BSD rings */ - int ring_index; + + /* + * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch + * will be rejected. Instead look for a better place. + */ }; static inline struct drm_i915_private *to_i915(const struct drm_device *dev) @@ -1512,6 +1598,8 @@ struct drm_i915_gem_object_ops { */ int (*get_pages)(struct drm_i915_gem_object *); void (*put_pages)(struct drm_i915_gem_object *); + int (*dmabuf_export)(struct drm_i915_gem_object *); + void (*release)(struct drm_i915_gem_object *); }; struct drm_i915_gem_object { @@ -1602,7 +1690,7 @@ struct drm_i915_gem_object { void *dma_buf_vmapping; int vmapping_count; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; /** Breadcrumb of last rendering to the buffer. */ uint32_t last_read_seqno; @@ -1625,8 +1713,20 @@ struct drm_i915_gem_object { /** for phy allocated objects */ struct drm_i915_gem_phys_object *phys_obj; -}; + union { + struct i915_gem_userptr { + uintptr_t ptr; + unsigned read_only :1; + unsigned workers :4; +#define I915_GEM_USERPTR_MAX_WORKERS 15 + + struct mm_struct *mm; + struct i915_mmu_object *mn; + struct work_struct *work; + } userptr; + }; +}; #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base) /** @@ -1641,7 +1741,7 @@ struct drm_i915_gem_object { */ struct drm_i915_gem_request { /** On Which ring this request was generated */ - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; /** GEM sequence number associated with this request. */ uint32_t seqno; @@ -1653,7 +1753,7 @@ struct drm_i915_gem_request { u32 tail; /** Context related to this request */ - struct i915_hw_context *ctx; + struct intel_context *ctx; /** Batch buffer related to this request if any */ struct drm_i915_gem_object *batch_obj; @@ -1680,9 +1780,8 @@ struct drm_i915_file_private { } mm; struct idr context_idr; - struct i915_hw_context *private_default_ctx; atomic_t rps_wait_boost; - struct intel_ring_buffer *bsd_ring; + struct intel_engine_cs *bsd_ring; }; /* @@ -1848,9 +1947,10 @@ struct drm_i915_cmd_table { #define I915_NEED_GFX_HWS(dev) (INTEL_INFO(dev)->need_gfx_hws) #define HAS_HW_CONTEXTS(dev) (INTEL_INFO(dev)->gen >= 6) -#define HAS_ALIASING_PPGTT(dev) (INTEL_INFO(dev)->gen >= 6 && !IS_VALLEYVIEW(dev)) -#define HAS_PPGTT(dev) (INTEL_INFO(dev)->gen >= 7 && !IS_VALLEYVIEW(dev) \ - && !IS_BROADWELL(dev)) +#define HAS_ALIASING_PPGTT(dev) (INTEL_INFO(dev)->gen >= 6 && \ + (!IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev))) +#define HAS_PPGTT(dev) (INTEL_INFO(dev)->gen >= 7 \ + && !IS_GEN8(dev)) #define USES_PPGTT(dev) intel_enable_ppgtt(dev, false) #define USES_FULL_PPGTT(dev) intel_enable_ppgtt(dev, true) @@ -1889,7 +1989,7 @@ struct drm_i915_cmd_table { #define HAS_FPGA_DBG_UNCLAIMED(dev) (INTEL_INFO(dev)->has_fpga_dbg) #define HAS_PSR(dev) (IS_HASWELL(dev) || IS_BROADWELL(dev)) #define HAS_RUNTIME_PM(dev) (IS_GEN6(dev) || IS_HASWELL(dev) || \ - IS_BROADWELL(dev)) + IS_BROADWELL(dev) || IS_VALLEYVIEW(dev)) #define INTEL_PCH_DEVICE_ID_MASK 0xff00 #define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00 @@ -2050,6 +2150,9 @@ int i915_gem_set_tiling(struct drm_device *dev, void *data, struct drm_file *file_priv); int i915_gem_get_tiling(struct drm_device *dev, void *data, struct drm_file *file_priv); +int i915_gem_init_userptr(struct drm_device *dev); +int i915_gem_userptr_ioctl(struct drm_device *dev, void *data, + struct drm_file *file); int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int i915_gem_wait_ioctl(struct drm_device *dev, void *data, @@ -2105,9 +2208,9 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj) int __must_check i915_mutex_lock_interruptible(struct drm_device *dev); int i915_gem_object_sync(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *to); + struct intel_engine_cs *to); void i915_vma_move_to_active(struct i915_vma *vma, - struct intel_ring_buffer *ring); + struct intel_engine_cs *ring); int i915_gem_dumb_create(struct drm_file *file_priv, struct drm_device *dev, struct drm_mode_create_dumb *args); @@ -2127,31 +2230,14 @@ int __must_check i915_gem_set_seqno(struct drm_device *dev, u32 seqno); int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj); int __must_check i915_gem_object_put_fence(struct drm_i915_gem_object *obj); -static inline bool -i915_gem_object_pin_fence(struct drm_i915_gem_object *obj) -{ - if (obj->fence_reg != I915_FENCE_REG_NONE) { - struct drm_i915_private *dev_priv = obj->base.dev->dev_private; - dev_priv->fence_regs[obj->fence_reg].pin_count++; - return true; - } else - return false; -} - -static inline void -i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj) -{ - if (obj->fence_reg != I915_FENCE_REG_NONE) { - struct drm_i915_private *dev_priv = obj->base.dev->dev_private; - WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0); - dev_priv->fence_regs[obj->fence_reg].pin_count--; - } -} +bool i915_gem_object_pin_fence(struct drm_i915_gem_object *obj); +void i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj); struct drm_i915_gem_request * -i915_gem_find_active_request(struct intel_ring_buffer *ring); +i915_gem_find_active_request(struct intel_engine_cs *ring); bool i915_gem_retire_requests(struct drm_device *dev); +void i915_gem_retire_requests_ring(struct intel_engine_cs *ring); int __must_check i915_gem_check_wedge(struct i915_gpu_error *error, bool interruptible); static inline bool i915_reset_in_progress(struct i915_gpu_error *error) @@ -2187,18 +2273,18 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force); int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj); int __must_check i915_gem_init(struct drm_device *dev); int __must_check i915_gem_init_hw(struct drm_device *dev); -int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice); +int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice); void i915_gem_init_swizzling(struct drm_device *dev); void i915_gem_cleanup_ringbuffer(struct drm_device *dev); int __must_check i915_gpu_idle(struct drm_device *dev); int __must_check i915_gem_suspend(struct drm_device *dev); -int __i915_add_request(struct intel_ring_buffer *ring, +int __i915_add_request(struct intel_engine_cs *ring, struct drm_file *file, struct drm_i915_gem_object *batch_obj, u32 *seqno); #define i915_add_request(ring, seqno) \ __i915_add_request(ring, NULL, NULL, seqno) -int __must_check i915_wait_seqno(struct intel_ring_buffer *ring, +int __must_check i915_wait_seqno(struct intel_engine_cs *ring, uint32_t seqno); int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf); int __must_check @@ -2209,7 +2295,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write); int __must_check i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, u32 alignment, - struct intel_ring_buffer *pipelined); + struct intel_engine_cs *pipelined); void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj); int i915_gem_attach_phys_object(struct drm_device *dev, struct drm_i915_gem_object *obj, @@ -2311,22 +2397,22 @@ void i915_gem_context_reset(struct drm_device *dev); int i915_gem_context_open(struct drm_device *dev, struct drm_file *file); int i915_gem_context_enable(struct drm_i915_private *dev_priv); void i915_gem_context_close(struct drm_device *dev, struct drm_file *file); -int i915_switch_context(struct intel_ring_buffer *ring, - struct i915_hw_context *to); -struct i915_hw_context * +int i915_switch_context(struct intel_engine_cs *ring, + struct intel_context *to); +struct intel_context * i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id); void i915_gem_context_free(struct kref *ctx_ref); -static inline void i915_gem_context_reference(struct i915_hw_context *ctx) +static inline void i915_gem_context_reference(struct intel_context *ctx) { kref_get(&ctx->ref); } -static inline void i915_gem_context_unreference(struct i915_hw_context *ctx) +static inline void i915_gem_context_unreference(struct intel_context *ctx) { kref_put(&ctx->ref, i915_gem_context_free); } -static inline bool i915_gem_context_is_default(const struct i915_hw_context *c) +static inline bool i915_gem_context_is_default(const struct intel_context *c) { return c->id == DEFAULT_CONTEXT_ID; } @@ -2336,6 +2422,8 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file); +/* i915_gem_render_state.c */ +int i915_gem_render_state_init(struct intel_engine_cs *ring); /* i915_gem_evict.c */ int __must_check i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm, @@ -2420,9 +2508,10 @@ const char *i915_cache_level_str(int type); /* i915_cmd_parser.c */ int i915_cmd_parser_get_version(void); -void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring); -bool i915_needs_cmd_parser(struct intel_ring_buffer *ring); -int i915_parse_cmds(struct intel_ring_buffer *ring, +int i915_cmd_parser_init_ring(struct intel_engine_cs *ring); +void i915_cmd_parser_fini_ring(struct intel_engine_cs *ring); +bool i915_needs_cmd_parser(struct intel_engine_cs *ring); +int i915_parse_cmds(struct intel_engine_cs *ring, struct drm_i915_gem_object *batch_obj, u32 batch_start_offset, bool is_master); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index e1fa919017e2..87e9b349ebef 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -31,6 +31,7 @@ #include "i915_drv.h" #include "i915_trace.h" #include "intel_drv.h" +#include <linux/oom.h> #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/swap.h> @@ -57,14 +58,15 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj, struct drm_i915_fence_reg *fence, bool enable); -static unsigned long i915_gem_inactive_count(struct shrinker *shrinker, +static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc); -static unsigned long i915_gem_inactive_scan(struct shrinker *shrinker, +static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc); +static int i915_gem_shrinker_oom(struct notifier_block *nb, + unsigned long event, + void *ptr); static unsigned long i915_gem_purge(struct drm_i915_private *dev_priv, long target); static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv); -static void i915_gem_object_truncate(struct drm_i915_gem_object *obj); -static void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring); static bool cpu_cache_is_coherent(struct drm_device *dev, enum i915_cache_level level) @@ -977,7 +979,7 @@ i915_gem_check_wedge(struct i915_gpu_error *error, * equal. */ static int -i915_gem_check_olr(struct intel_ring_buffer *ring, u32 seqno) +i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno) { int ret; @@ -996,7 +998,7 @@ static void fake_irq(unsigned long data) } static bool missed_irq(struct drm_i915_private *dev_priv, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings); } @@ -1027,7 +1029,7 @@ static bool can_wait_boost(struct drm_i915_file_private *file_priv) * Returns 0 if the seqno was found within the alloted time. Else returns the * errno with remaining time filled in timeout argument. */ -static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, +static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno, unsigned reset_counter, bool interruptible, struct timespec *timeout, @@ -1134,7 +1136,7 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno, * request and object lists appropriately for that event. */ int -i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno) +i915_wait_seqno(struct intel_engine_cs *ring, uint32_t seqno) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1159,7 +1161,7 @@ i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno) static int i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { if (!obj->active) return 0; @@ -1184,7 +1186,7 @@ static __must_check int i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj, bool readonly) { - struct intel_ring_buffer *ring = obj->ring; + struct intel_engine_cs *ring = obj->ring; u32 seqno; int ret; @@ -1209,7 +1211,7 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj, { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = obj->ring; + struct intel_engine_cs *ring = obj->ring; unsigned reset_counter; u32 seqno; int ret; @@ -1692,12 +1694,16 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data, return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset); } +static inline int +i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj) +{ + return obj->madv == I915_MADV_DONTNEED; +} + /* Immediately discard the backing storage */ static void i915_gem_object_truncate(struct drm_i915_gem_object *obj) { - struct inode *inode; - i915_gem_object_free_mmap_offset(obj); if (obj->base.filp == NULL) @@ -1708,16 +1714,28 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj) * To do this we must instruct the shmfs to drop all of its * backing pages, *now*. */ - inode = file_inode(obj->base.filp); - shmem_truncate_range(inode, 0, (loff_t)-1); - + shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1); obj->madv = __I915_MADV_PURGED; } -static inline int -i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj) +/* Try to discard unwanted pages */ +static void +i915_gem_object_invalidate(struct drm_i915_gem_object *obj) { - return obj->madv == I915_MADV_DONTNEED; + struct address_space *mapping; + + switch (obj->madv) { + case I915_MADV_DONTNEED: + i915_gem_object_truncate(obj); + case __I915_MADV_PURGED: + return; + } + + if (obj->base.filp == NULL) + return; + + mapping = file_inode(obj->base.filp)->i_mapping, + invalidate_mapping_pages(mapping, 0, (loff_t)-1); } static void @@ -1782,8 +1800,7 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj) ops->put_pages(obj); obj->pages = NULL; - if (i915_gem_object_is_purgeable(obj)) - i915_gem_object_truncate(obj); + i915_gem_object_invalidate(obj); return 0; } @@ -1974,7 +1991,19 @@ err_pages: page_cache_release(sg_page_iter_page(&sg_iter)); sg_free_table(st); kfree(st); - return PTR_ERR(page); + + /* shmemfs first checks if there is enough memory to allocate the page + * and reports ENOSPC should there be insufficient, along with the usual + * ENOMEM for a genuine allocation failure. + * + * We use ENOSPC in our driver to mean that we have run out of aperture + * space and so want to translate the error from shmemfs back to our + * usual understanding of ENOMEM. + */ + if (PTR_ERR(page) == -ENOSPC) + return -ENOMEM; + else + return PTR_ERR(page); } /* Ensure that the associated pages are gathered from the backing storage @@ -2011,7 +2040,7 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj) static void i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct drm_device *dev = obj->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2049,7 +2078,7 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj, } void i915_vma_move_to_active(struct i915_vma *vma, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { list_move_tail(&vma->mm_list, &vma->vm->active_list); return i915_gem_object_move_to_active(vma->obj, ring); @@ -2090,7 +2119,7 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj) static void i915_gem_object_retire(struct drm_i915_gem_object *obj) { - struct intel_ring_buffer *ring = obj->ring; + struct intel_engine_cs *ring = obj->ring; if (ring == NULL) return; @@ -2104,7 +2133,7 @@ static int i915_gem_init_seqno(struct drm_device *dev, u32 seqno) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i, j; /* Carefully retire all requests without writing to the rings */ @@ -2170,7 +2199,7 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno) return 0; } -int __i915_add_request(struct intel_ring_buffer *ring, +int __i915_add_request(struct intel_engine_cs *ring, struct drm_file *file, struct drm_i915_gem_object *obj, u32 *out_seqno) @@ -2275,7 +2304,7 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request) } static bool i915_context_is_banned(struct drm_i915_private *dev_priv, - const struct i915_hw_context *ctx) + const struct intel_context *ctx) { unsigned long elapsed; @@ -2299,7 +2328,7 @@ static bool i915_context_is_banned(struct drm_i915_private *dev_priv, } static void i915_set_reset_status(struct drm_i915_private *dev_priv, - struct i915_hw_context *ctx, + struct intel_context *ctx, const bool guilty) { struct i915_ctx_hang_stats *hs; @@ -2330,7 +2359,7 @@ static void i915_gem_free_request(struct drm_i915_gem_request *request) } struct drm_i915_gem_request * -i915_gem_find_active_request(struct intel_ring_buffer *ring) +i915_gem_find_active_request(struct intel_engine_cs *ring) { struct drm_i915_gem_request *request; u32 completed_seqno; @@ -2348,7 +2377,7 @@ i915_gem_find_active_request(struct intel_ring_buffer *ring) } static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct drm_i915_gem_request *request; bool ring_hung; @@ -2367,7 +2396,7 @@ static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv, } static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { while (!list_empty(&ring->active_list)) { struct drm_i915_gem_object *obj; @@ -2426,7 +2455,7 @@ void i915_gem_restore_fences(struct drm_device *dev) void i915_gem_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; /* @@ -2448,8 +2477,8 @@ void i915_gem_reset(struct drm_device *dev) /** * This function clears the request list as sequence numbers are passed. */ -static void -i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) +void +i915_gem_retire_requests_ring(struct intel_engine_cs *ring) { uint32_t seqno; @@ -2494,7 +2523,7 @@ i915_gem_retire_requests_ring(struct intel_ring_buffer *ring) * of tail of the request to update the last known position * of the GPU head. */ - ring->last_retired_head = request->tail; + ring->buffer->last_retired_head = request->tail; i915_gem_free_request(request); } @@ -2512,7 +2541,7 @@ bool i915_gem_retire_requests(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; bool idle = true; int i; @@ -2606,7 +2635,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file) struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_wait *args = data; struct drm_i915_gem_object *obj; - struct intel_ring_buffer *ring = NULL; + struct intel_engine_cs *ring = NULL; struct timespec timeout_stack, *timeout = NULL; unsigned reset_counter; u32 seqno = 0; @@ -2677,9 +2706,9 @@ out: */ int i915_gem_object_sync(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *to) + struct intel_engine_cs *to) { - struct intel_ring_buffer *from = obj->ring; + struct intel_engine_cs *from = obj->ring; u32 seqno; int ret, idx; @@ -2762,12 +2791,14 @@ int i915_vma_unbind(struct i915_vma *vma) * cause memory corruption through use-after-free. */ - i915_gem_object_finish_gtt(obj); + if (i915_is_ggtt(vma->vm)) { + i915_gem_object_finish_gtt(obj); - /* release the fence reg _after_ flushing */ - ret = i915_gem_object_put_fence(obj); - if (ret) - return ret; + /* release the fence reg _after_ flushing */ + ret = i915_gem_object_put_fence(obj); + if (ret) + return ret; + } trace_i915_vma_unbind(vma); @@ -2800,7 +2831,7 @@ int i915_vma_unbind(struct i915_vma *vma) int i915_gpu_idle(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i; /* Flush everything onto the inactive list. */ @@ -3041,6 +3072,9 @@ i915_gem_object_put_fence(struct drm_i915_gem_object *obj) fence = &dev_priv->fence_regs[obj->fence_reg]; + if (WARN_ON(fence->pin_count)) + return -EBUSY; + i915_gem_object_fence_lost(obj); i915_gem_object_update_fence(obj, fence, false); @@ -3637,6 +3671,15 @@ unlock: static bool is_pin_display(struct drm_i915_gem_object *obj) { + struct i915_vma *vma; + + if (list_empty(&obj->vma_list)) + return false; + + vma = i915_gem_obj_to_ggtt(obj); + if (!vma) + return false; + /* There are 3 sources that pin objects: * 1. The display engine (scanouts, sprites, cursors); * 2. Reservations for execbuffer; @@ -3648,7 +3691,7 @@ static bool is_pin_display(struct drm_i915_gem_object *obj) * subtracting the potential reference by the user, any pin_count * remains, it must be due to another use by the display engine. */ - return i915_gem_obj_to_ggtt(obj)->pin_count - !!obj->user_pin_count; + return vma->pin_count - !!obj->user_pin_count; } /* @@ -3659,9 +3702,10 @@ static bool is_pin_display(struct drm_i915_gem_object *obj) int i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, u32 alignment, - struct intel_ring_buffer *pipelined) + struct intel_engine_cs *pipelined) { u32 old_read_domains, old_write_domain; + bool was_pin_display; int ret; if (pipelined != obj->ring) { @@ -3673,6 +3717,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, /* Mark the pin_display early so that we account for the * display coherency whilst setting up the cache domains. */ + was_pin_display = obj->pin_display; obj->pin_display = true; /* The display engine is not coherent with the LLC cache on gen6. As @@ -3715,7 +3760,8 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, return 0; err_unpin_display: - obj->pin_display = is_pin_display(obj); + WARN_ON(was_pin_display != is_pin_display(obj)); + obj->pin_display = was_pin_display; return ret; } @@ -3812,7 +3858,7 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file) struct drm_i915_file_private *file_priv = file->driver_priv; unsigned long recent_enough = jiffies - msecs_to_jiffies(20); struct drm_i915_gem_request *request; - struct intel_ring_buffer *ring = NULL; + struct intel_engine_cs *ring = NULL; unsigned reset_counter; u32 seqno = 0; int ret; @@ -3852,9 +3898,13 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj, uint32_t alignment, unsigned flags) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; struct i915_vma *vma; int ret; + if (WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base)) + return -ENODEV; + if (WARN_ON(flags & (PIN_GLOBAL | PIN_MAPPABLE) && !i915_is_ggtt(vm))) return -EINVAL; @@ -3910,6 +3960,32 @@ i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj) obj->pin_mappable = false; } +bool +i915_gem_object_pin_fence(struct drm_i915_gem_object *obj) +{ + if (obj->fence_reg != I915_FENCE_REG_NONE) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; + struct i915_vma *ggtt_vma = i915_gem_obj_to_ggtt(obj); + + WARN_ON(!ggtt_vma || + dev_priv->fence_regs[obj->fence_reg].pin_count > + ggtt_vma->pin_count); + dev_priv->fence_regs[obj->fence_reg].pin_count++; + return true; + } else + return false; +} + +void +i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj) +{ + if (obj->fence_reg != I915_FENCE_REG_NONE) { + struct drm_i915_private *dev_priv = obj->base.dev->dev_private; + WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0); + dev_priv->fence_regs[obj->fence_reg].pin_count--; + } +} + int i915_gem_pin_ioctl(struct drm_device *dev, void *data, struct drm_file *file) @@ -4170,6 +4246,30 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, return obj; } +static bool discard_backing_storage(struct drm_i915_gem_object *obj) +{ + /* If we are the last user of the backing storage (be it shmemfs + * pages or stolen etc), we know that the pages are going to be + * immediately released. In this case, we can then skip copying + * back the contents from the GPU. + */ + + if (obj->madv != I915_MADV_WILLNEED) + return false; + + if (obj->base.filp == NULL) + return true; + + /* At first glance, this looks racy, but then again so would be + * userspace racing mmap against close. However, the first external + * reference to the filp can only be obtained through the + * i915_gem_mmap_ioctl() which safeguards us against the user + * acquiring such a reference whilst we are in the middle of + * freeing the object. + */ + return atomic_long_read(&obj->base.filp->f_count) == 1; +} + void i915_gem_free_object(struct drm_gem_object *gem_obj) { struct drm_i915_gem_object *obj = to_intel_bo(gem_obj); @@ -4208,6 +4308,8 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) if (WARN_ON(obj->pages_pin_count)) obj->pages_pin_count = 0; + if (discard_backing_storage(obj)) + obj->madv = I915_MADV_DONTNEED; i915_gem_object_put_pages(obj); i915_gem_object_free_mmap_offset(obj); i915_gem_object_release_stolen(obj); @@ -4217,6 +4319,9 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj) if (obj->base.import_attach) drm_prime_gem_destroy(&obj->base, NULL); + if (obj->ops->release) + obj->ops->release(obj); + drm_gem_object_release(&obj->base); i915_gem_info_remove_obj(dev_priv, obj->base.size); @@ -4254,7 +4359,7 @@ static void i915_gem_stop_ringbuffers(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; for_each_ring(ring, dev_priv, i) @@ -4303,7 +4408,7 @@ err: return ret; } -int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice) +int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -4496,6 +4601,7 @@ int i915_gem_init(struct drm_device *dev) DRM_DEBUG_DRIVER("allow wake ack timed out\n"); } + i915_gem_init_userptr(dev); i915_gem_init_global_gtt(dev); ret = i915_gem_context_init(dev); @@ -4526,7 +4632,7 @@ void i915_gem_cleanup_ringbuffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; for_each_ring(ring, dev_priv, i) @@ -4602,7 +4708,7 @@ i915_gem_lastclose(struct drm_device *dev) } static void -init_ring_lists(struct intel_ring_buffer *ring) +init_ring_lists(struct intel_engine_cs *ring) { INIT_LIST_HEAD(&ring->active_list); INIT_LIST_HEAD(&ring->request_list); @@ -4677,10 +4783,13 @@ i915_gem_load(struct drm_device *dev) dev_priv->mm.interruptible = true; - dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan; - dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count; - dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS; - register_shrinker(&dev_priv->mm.inactive_shrinker); + dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan; + dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count; + dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS; + register_shrinker(&dev_priv->mm.shrinker); + + dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom; + register_oom_notifier(&dev_priv->mm.oom_notifier); } /* @@ -4939,27 +5048,46 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) #endif } +static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock) +{ + if (!mutex_trylock(&dev->struct_mutex)) { + if (!mutex_is_locked_by(&dev->struct_mutex, current)) + return false; + + if (to_i915(dev)->mm.shrinker_no_lock_stealing) + return false; + + *unlock = false; + } else + *unlock = true; + + return true; +} + +static int num_vma_bound(struct drm_i915_gem_object *obj) +{ + struct i915_vma *vma; + int count = 0; + + list_for_each_entry(vma, &obj->vma_list, vma_link) + if (drm_mm_node_allocated(&vma->node)) + count++; + + return count; +} + static unsigned long -i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc) +i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { struct drm_i915_private *dev_priv = - container_of(shrinker, - struct drm_i915_private, - mm.inactive_shrinker); + container_of(shrinker, struct drm_i915_private, mm.shrinker); struct drm_device *dev = dev_priv->dev; struct drm_i915_gem_object *obj; - bool unlock = true; unsigned long count; + bool unlock; - if (!mutex_trylock(&dev->struct_mutex)) { - if (!mutex_is_locked_by(&dev->struct_mutex, current)) - return 0; - - if (dev_priv->mm.shrinker_no_lock_stealing) - return 0; - - unlock = false; - } + if (!i915_gem_shrinker_lock(dev, &unlock)) + return 0; count = 0; list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) @@ -4967,10 +5095,8 @@ i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc) count += obj->base.size >> PAGE_SHIFT; list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { - if (obj->active) - continue; - - if (!i915_gem_obj_is_pinned(obj) && obj->pages_pin_count == 0) + if (!i915_gem_obj_is_pinned(obj) && + obj->pages_pin_count == num_vma_bound(obj)) count += obj->base.size >> PAGE_SHIFT; } @@ -5043,44 +5169,99 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o, } static unsigned long -i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc) +i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { struct drm_i915_private *dev_priv = - container_of(shrinker, - struct drm_i915_private, - mm.inactive_shrinker); + container_of(shrinker, struct drm_i915_private, mm.shrinker); struct drm_device *dev = dev_priv->dev; unsigned long freed; - bool unlock = true; + bool unlock; - if (!mutex_trylock(&dev->struct_mutex)) { - if (!mutex_is_locked_by(&dev->struct_mutex, current)) - return SHRINK_STOP; - - if (dev_priv->mm.shrinker_no_lock_stealing) - return SHRINK_STOP; - - unlock = false; - } + if (!i915_gem_shrinker_lock(dev, &unlock)) + return SHRINK_STOP; freed = i915_gem_purge(dev_priv, sc->nr_to_scan); if (freed < sc->nr_to_scan) freed += __i915_gem_shrink(dev_priv, sc->nr_to_scan - freed, false); - if (freed < sc->nr_to_scan) - freed += i915_gem_shrink_all(dev_priv); - if (unlock) mutex_unlock(&dev->struct_mutex); return freed; } +static int +i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr) +{ + struct drm_i915_private *dev_priv = + container_of(nb, struct drm_i915_private, mm.oom_notifier); + struct drm_device *dev = dev_priv->dev; + struct drm_i915_gem_object *obj; + unsigned long timeout = msecs_to_jiffies(5000) + 1; + unsigned long pinned, bound, unbound, freed; + bool was_interruptible; + bool unlock; + + while (!i915_gem_shrinker_lock(dev, &unlock) && --timeout) + schedule_timeout_killable(1); + if (timeout == 0) { + pr_err("Unable to purge GPU memory due lock contention.\n"); + return NOTIFY_DONE; + } + + was_interruptible = dev_priv->mm.interruptible; + dev_priv->mm.interruptible = false; + + freed = i915_gem_shrink_all(dev_priv); + + dev_priv->mm.interruptible = was_interruptible; + + /* Because we may be allocating inside our own driver, we cannot + * assert that there are no objects with pinned pages that are not + * being pointed to by hardware. + */ + unbound = bound = pinned = 0; + list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) { + if (!obj->base.filp) /* not backed by a freeable object */ + continue; + + if (obj->pages_pin_count) + pinned += obj->base.size; + else + unbound += obj->base.size; + } + list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) { + if (!obj->base.filp) + continue; + + if (obj->pages_pin_count) + pinned += obj->base.size; + else + bound += obj->base.size; + } + + if (unlock) + mutex_unlock(&dev->struct_mutex); + + pr_info("Purging GPU memory, %lu bytes freed, %lu bytes still pinned.\n", + freed, pinned); + if (unbound || bound) + pr_err("%lu and %lu bytes still available in the " + "bound and unbound GPU page lists.\n", + bound, unbound); + + *(unsigned long *)ptr += freed; + return NOTIFY_DONE; +} + struct i915_vma *i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj) { struct i915_vma *vma; + /* This WARN has probably outlived its usefulness (callers already + * WARN if they don't find the GGTT vma they expect). When removing, + * remember to remove the pre-check in is_pin_display() as well */ if (WARN_ON(list_empty(&obj->vma_list))) return NULL; diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index f77b4c126465..3ffe308d5893 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -178,7 +178,7 @@ static int get_context_size(struct drm_device *dev) void i915_gem_context_free(struct kref *ctx_ref) { - struct i915_hw_context *ctx = container_of(ctx_ref, + struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref); struct i915_hw_ppgtt *ppgtt = NULL; @@ -199,7 +199,7 @@ void i915_gem_context_free(struct kref *ctx_ref) } static struct i915_hw_ppgtt * -create_vm_for_ctx(struct drm_device *dev, struct i915_hw_context *ctx) +create_vm_for_ctx(struct drm_device *dev, struct intel_context *ctx) { struct i915_hw_ppgtt *ppgtt; int ret; @@ -218,12 +218,12 @@ create_vm_for_ctx(struct drm_device *dev, struct i915_hw_context *ctx) return ppgtt; } -static struct i915_hw_context * +static struct intel_context * __create_hw_context(struct drm_device *dev, struct drm_i915_file_private *file_priv) { struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -285,14 +285,14 @@ err_out: * context state of the GPU for applications that don't utilize HW contexts, as * well as an idle case. */ -static struct i915_hw_context * +static struct intel_context * i915_gem_create_context(struct drm_device *dev, struct drm_i915_file_private *file_priv, bool create_vm) { const bool is_global_default_ctx = file_priv == NULL; struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret = 0; BUG_ON(!mutex_is_locked(&dev->struct_mutex)); @@ -364,8 +364,8 @@ void i915_gem_context_reset(struct drm_device *dev) /* Prevent the hardware from restoring the last context (which hung) on * the next switch */ for (i = 0; i < I915_NUM_RINGS; i++) { - struct intel_ring_buffer *ring = &dev_priv->ring[i]; - struct i915_hw_context *dctx = ring->default_context; + struct intel_engine_cs *ring = &dev_priv->ring[i]; + struct intel_context *dctx = ring->default_context; /* Do a fake switch to the default context */ if (ring->last_context == dctx) @@ -391,7 +391,7 @@ void i915_gem_context_reset(struct drm_device *dev) int i915_gem_context_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_context *ctx; + struct intel_context *ctx; int i; /* Init should only be called once per module load. Eventually the @@ -426,7 +426,7 @@ int i915_gem_context_init(struct drm_device *dev) void i915_gem_context_fini(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct i915_hw_context *dctx = dev_priv->ring[RCS].default_context; + struct intel_context *dctx = dev_priv->ring[RCS].default_context; int i; if (dctx->obj) { @@ -449,10 +449,12 @@ void i915_gem_context_fini(struct drm_device *dev) i915_gem_context_unreference(dctx); dev_priv->ring[RCS].last_context = NULL; } + + i915_gem_object_ggtt_unpin(dctx->obj); } for (i = 0; i < I915_NUM_RINGS; i++) { - struct intel_ring_buffer *ring = &dev_priv->ring[i]; + struct intel_engine_cs *ring = &dev_priv->ring[i]; if (ring->last_context) i915_gem_context_unreference(ring->last_context); @@ -461,13 +463,12 @@ void i915_gem_context_fini(struct drm_device *dev) ring->last_context = NULL; } - i915_gem_object_ggtt_unpin(dctx->obj); i915_gem_context_unreference(dctx); } int i915_gem_context_enable(struct drm_i915_private *dev_priv) { - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int ret, i; /* This is the only place the aliasing PPGTT gets enabled, which means @@ -494,11 +495,7 @@ int i915_gem_context_enable(struct drm_i915_private *dev_priv) static int context_idr_cleanup(int id, void *p, void *data) { - struct i915_hw_context *ctx = p; - - /* Ignore the default context because close will handle it */ - if (i915_gem_context_is_default(ctx)) - return 0; + struct intel_context *ctx = p; i915_gem_context_unreference(ctx); return 0; @@ -507,17 +504,17 @@ static int context_idr_cleanup(int id, void *p, void *data) int i915_gem_context_open(struct drm_device *dev, struct drm_file *file) { struct drm_i915_file_private *file_priv = file->driver_priv; + struct intel_context *ctx; idr_init(&file_priv->context_idr); mutex_lock(&dev->struct_mutex); - file_priv->private_default_ctx = - i915_gem_create_context(dev, file_priv, USES_FULL_PPGTT(dev)); + ctx = i915_gem_create_context(dev, file_priv, USES_FULL_PPGTT(dev)); mutex_unlock(&dev->struct_mutex); - if (IS_ERR(file_priv->private_default_ctx)) { + if (IS_ERR(ctx)) { idr_destroy(&file_priv->context_idr); - return PTR_ERR(file_priv->private_default_ctx); + return PTR_ERR(ctx); } return 0; @@ -529,16 +526,14 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file) idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL); idr_destroy(&file_priv->context_idr); - - i915_gem_context_unreference(file_priv->private_default_ctx); } -struct i915_hw_context * +struct intel_context * i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id) { - struct i915_hw_context *ctx; + struct intel_context *ctx; - ctx = (struct i915_hw_context *)idr_find(&file_priv->context_idr, id); + ctx = (struct intel_context *)idr_find(&file_priv->context_idr, id); if (!ctx) return ERR_PTR(-ENOENT); @@ -546,8 +541,8 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id) } static inline int -mi_set_context(struct intel_ring_buffer *ring, - struct i915_hw_context *new_context, +mi_set_context(struct intel_engine_cs *ring, + struct intel_context *new_context, u32 hw_flags) { int ret; @@ -567,7 +562,7 @@ mi_set_context(struct intel_ring_buffer *ring, if (ret) return ret; - /* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw */ + /* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw,chv */ if (INTEL_INFO(ring->dev)->gen >= 7) intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_DISABLE); else @@ -596,11 +591,11 @@ mi_set_context(struct intel_ring_buffer *ring, return ret; } -static int do_switch(struct intel_ring_buffer *ring, - struct i915_hw_context *to) +static int do_switch(struct intel_engine_cs *ring, + struct intel_context *to) { struct drm_i915_private *dev_priv = ring->dev->dev_private; - struct i915_hw_context *from = ring->last_context; + struct intel_context *from = ring->last_context; struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(to); u32 hw_flags = 0; int ret, i; @@ -701,13 +696,19 @@ static int do_switch(struct intel_ring_buffer *ring, i915_gem_context_unreference(from); } - to->is_initialized = true; - done: i915_gem_context_reference(to); ring->last_context = to; to->last_ring = ring; + if (ring->id == RCS && !to->is_initialized && from == NULL) { + ret = i915_gem_render_state_init(ring); + if (ret) + DRM_ERROR("init render state: %d\n", ret); + } + + to->is_initialized = true; + return 0; unpin_out: @@ -726,8 +727,8 @@ unpin_out: * it will have a refoucnt > 1. This allows us to destroy the context abstract * object while letting the normal object tracking destroy the backing BO. */ -int i915_switch_context(struct intel_ring_buffer *ring, - struct i915_hw_context *to) +int i915_switch_context(struct intel_engine_cs *ring, + struct intel_context *to) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -756,7 +757,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data, { struct drm_i915_gem_context_create *args = data; struct drm_i915_file_private *file_priv = file->driver_priv; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret; if (!hw_context_enabled(dev)) @@ -782,7 +783,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, { struct drm_i915_gem_context_destroy *args = data; struct drm_i915_file_private *file_priv = file->driver_priv; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret; if (args->ctx_id == DEFAULT_CONTEXT_ID) diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c index 321102a8374b..580aa42443ed 100644 --- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c @@ -229,6 +229,14 @@ static const struct dma_buf_ops i915_dmabuf_ops = { struct dma_buf *i915_gem_prime_export(struct drm_device *dev, struct drm_gem_object *gem_obj, int flags) { + struct drm_i915_gem_object *obj = to_intel_bo(gem_obj); + + if (obj->ops->dmabuf_export) { + int ret = obj->ops->dmabuf_export(obj); + if (ret) + return ERR_PTR(ret); + } + return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags); } diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 47fe8ecef135..008e208e9a3a 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -541,7 +541,7 @@ need_reloc_mappable(struct i915_vma *vma) static int i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool *need_reloc) { struct drm_i915_gem_object *obj = vma->obj; @@ -596,7 +596,7 @@ i915_gem_execbuffer_reserve_vma(struct i915_vma *vma, } static int -i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, +i915_gem_execbuffer_reserve(struct intel_engine_cs *ring, struct list_head *vmas, bool *need_relocs) { @@ -610,6 +610,8 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring, if (list_empty(vmas)) return 0; + i915_gem_retire_requests_ring(ring); + vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm; INIT_LIST_HEAD(&ordered_vmas); @@ -711,7 +713,7 @@ static int i915_gem_execbuffer_relocate_slow(struct drm_device *dev, struct drm_i915_gem_execbuffer2 *args, struct drm_file *file, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, struct eb_vmas *eb, struct drm_i915_gem_exec_object2 *exec) { @@ -827,7 +829,7 @@ err: } static int -i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring, +i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring, struct list_head *vmas) { struct i915_vma *vma; @@ -910,11 +912,11 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec, return 0; } -static struct i915_hw_context * +static struct intel_context * i915_gem_validate_context(struct drm_device *dev, struct drm_file *file, - struct intel_ring_buffer *ring, const u32 ctx_id) + struct intel_engine_cs *ring, const u32 ctx_id) { - struct i915_hw_context *ctx = NULL; + struct intel_context *ctx = NULL; struct i915_ctx_hang_stats *hs; if (ring->id != RCS && ctx_id != DEFAULT_CONTEXT_ID) @@ -935,7 +937,7 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file, static void i915_gem_execbuffer_move_to_active(struct list_head *vmas, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct i915_vma *vma; @@ -970,7 +972,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas, static void i915_gem_execbuffer_retire_commands(struct drm_device *dev, struct drm_file *file, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, struct drm_i915_gem_object *obj) { /* Unconditionally force add_request to emit a full flush. */ @@ -982,7 +984,7 @@ i915_gem_execbuffer_retire_commands(struct drm_device *dev, static int i915_reset_gen7_sol_offsets(struct drm_device *dev, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = dev->dev_private; int ret, i; @@ -1025,12 +1027,12 @@ static int gen8_dispatch_bsd_ring(struct drm_device *dev, int ring_id; mutex_lock(&dev->struct_mutex); - if (dev_priv->ring_index == 0) { + if (dev_priv->mm.bsd_ring_dispatch_index == 0) { ring_id = VCS; - dev_priv->ring_index = 1; + dev_priv->mm.bsd_ring_dispatch_index = 1; } else { ring_id = VCS2; - dev_priv->ring_index = 0; + dev_priv->mm.bsd_ring_dispatch_index = 0; } file_priv->bsd_ring = &dev_priv->ring[ring_id]; mutex_unlock(&dev->struct_mutex); @@ -1048,8 +1050,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, struct eb_vmas *eb; struct drm_i915_gem_object *batch_obj; struct drm_clip_rect *cliprects = NULL; - struct intel_ring_buffer *ring; - struct i915_hw_context *ctx; + struct intel_engine_cs *ring; + struct intel_context *ctx; struct i915_address_space *vm; const u32 ctx_id = i915_execbuffer2_get_context_id(*args); u64 exec_start = args->batch_start_offset, exec_len; @@ -1168,6 +1170,11 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data, goto pre_mutex_err; } } else { + if (args->DR4 == 0xffffffff) { + DRM_DEBUG("UXA submitting garbage DR4, fixing up\n"); + args->DR4 = 0; + } + if (args->DR1 || args->DR4 || args->cliprects_ptr) { DRM_DEBUG("0 cliprects but dirt in cliprects fields\n"); return -EINVAL; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 496916298e8a..94916362b61c 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -30,7 +30,8 @@ #include "i915_trace.h" #include "intel_drv.h" -static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv); +static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv); +static void chv_setup_private_ppat(struct drm_i915_private *dev_priv); bool intel_enable_ppgtt(struct drm_device *dev, bool full) { @@ -196,7 +197,7 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr, } /* Broadwell Page Directory Pointer Descriptors */ -static int gen8_write_pdp(struct intel_ring_buffer *ring, unsigned entry, +static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry, uint64_t val, bool synchronous) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -226,7 +227,7 @@ static int gen8_write_pdp(struct intel_ring_buffer *ring, unsigned entry, } static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous) { int i, ret; @@ -275,6 +276,8 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm, num_entries--; } + if (!HAS_LLC(ppgtt->base.dev)) + drm_clflush_virt_range(pt_vaddr, PAGE_SIZE); kunmap_atomic(pt_vaddr); pte = 0; @@ -311,6 +314,8 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, gen8_pte_encode(sg_page_iter_dma_address(&sg_iter), cache_level, true); if (++pte == GEN8_PTES_PER_PAGE) { + if (!HAS_LLC(ppgtt->base.dev)) + drm_clflush_virt_range(pt_vaddr, PAGE_SIZE); kunmap_atomic(pt_vaddr); pt_vaddr = NULL; if (++pde == GEN8_PDES_PER_PAGE) { @@ -320,8 +325,11 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm, pte = 0; } } - if (pt_vaddr) + if (pt_vaddr) { + if (!HAS_LLC(ppgtt->base.dev)) + drm_clflush_virt_range(pt_vaddr, PAGE_SIZE); kunmap_atomic(pt_vaddr); + } } static void gen8_free_page_tables(struct page **pt_pages) @@ -584,6 +592,8 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size) pd_vaddr[j] = gen8_pde_encode(ppgtt->base.dev, addr, I915_CACHE_LLC); } + if (!HAS_LLC(ppgtt->base.dev)) + drm_clflush_virt_range(pd_vaddr, PAGE_SIZE); kunmap_atomic(pd_vaddr); } @@ -696,7 +706,7 @@ static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt) } static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous) { struct drm_device *dev = ppgtt->base.dev; @@ -740,7 +750,7 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt, } static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous) { struct drm_device *dev = ppgtt->base.dev; @@ -791,7 +801,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt, } static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous) { struct drm_device *dev = ppgtt->base.dev; @@ -812,7 +822,7 @@ static int gen8_ppgtt_enable(struct i915_hw_ppgtt *ppgtt) { struct drm_device *dev = ppgtt->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int j, ret; for_each_ring(ring, dev_priv, j) { @@ -842,7 +852,7 @@ static int gen7_ppgtt_enable(struct i915_hw_ppgtt *ppgtt) { struct drm_device *dev = ppgtt->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; uint32_t ecochk, ecobits; int i; @@ -881,7 +891,7 @@ static int gen6_ppgtt_enable(struct i915_hw_ppgtt *ppgtt) { struct drm_device *dev = ppgtt->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; uint32_t ecochk, gab_ctl, ecobits; int i; @@ -1025,8 +1035,7 @@ alloc: &ppgtt->node, GEN6_PD_SIZE, GEN6_PD_ALIGN, 0, 0, dev_priv->gtt.base.total, - DRM_MM_SEARCH_DEFAULT, - DRM_MM_CREATE_DEFAULT); + DRM_MM_TOPDOWN); if (ret == -ENOSPC && !retried) { ret = i915_gem_evict_something(dev, &dev_priv->gtt.base, GEN6_PD_SIZE, GEN6_PD_ALIGN, @@ -1250,7 +1259,7 @@ static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible) void i915_check_and_clear_faults(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; if (INTEL_INFO(dev)->gen < 6) @@ -1325,7 +1334,11 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev) if (INTEL_INFO(dev)->gen >= 8) { - gen8_setup_private_ppat(dev_priv); + if (IS_CHERRYVIEW(dev)) + chv_setup_private_ppat(dev_priv); + else + bdw_setup_private_ppat(dev_priv); + return; } @@ -1753,6 +1766,17 @@ static inline unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl) return bdw_gmch_ctl << 20; } +static inline unsigned int chv_get_total_gtt_size(u16 gmch_ctrl) +{ + gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GGMS_MASK; + + if (gmch_ctrl) + return 1 << (20 + gmch_ctrl); + + return 0; +} + static inline size_t gen6_get_stolen_size(u16 snb_gmch_ctl) { snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT; @@ -1767,6 +1791,24 @@ static inline size_t gen8_get_stolen_size(u16 bdw_gmch_ctl) return bdw_gmch_ctl << 25; /* 32 MB units */ } +static size_t chv_get_stolen_size(u16 gmch_ctrl) +{ + gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GMS_MASK; + + /* + * 0x0 to 0x10: 32MB increments starting at 0MB + * 0x11 to 0x16: 4MB increments starting at 8MB + * 0x17 to 0x1d: 4MB increments start at 36MB + */ + if (gmch_ctrl < 0x11) + return gmch_ctrl << 25; + else if (gmch_ctrl < 0x17) + return (gmch_ctrl - 0x11 + 2) << 22; + else + return (gmch_ctrl - 0x17 + 9) << 22; +} + static int ggtt_probe_common(struct drm_device *dev, size_t gtt_size) { @@ -1797,7 +1839,7 @@ static int ggtt_probe_common(struct drm_device *dev, /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability * bits. When using advanced contexts each context stores its own PAT, but * writing this data shouldn't be harmful even in those cases. */ -static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv) +static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv) { uint64_t pat; @@ -1816,6 +1858,33 @@ static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv) I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32); } +static void chv_setup_private_ppat(struct drm_i915_private *dev_priv) +{ + uint64_t pat; + + /* + * Map WB on BDW to snooped on CHV. + * + * Only the snoop bit has meaning for CHV, the rest is + * ignored. + * + * Note that the harware enforces snooping for all page + * table accesses. The snoop bit is actually ignored for + * PDEs. + */ + pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) | + GEN8_PPAT(1, 0) | + GEN8_PPAT(2, 0) | + GEN8_PPAT(3, 0) | + GEN8_PPAT(4, CHV_PPAT_SNOOP) | + GEN8_PPAT(5, CHV_PPAT_SNOOP) | + GEN8_PPAT(6, CHV_PPAT_SNOOP) | + GEN8_PPAT(7, CHV_PPAT_SNOOP); + + I915_WRITE(GEN8_PRIVATE_PAT, pat); + I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32); +} + static int gen8_gmch_probe(struct drm_device *dev, size_t *gtt_total, size_t *stolen, @@ -1836,12 +1905,20 @@ static int gen8_gmch_probe(struct drm_device *dev, pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl); - *stolen = gen8_get_stolen_size(snb_gmch_ctl); + if (IS_CHERRYVIEW(dev)) { + *stolen = chv_get_stolen_size(snb_gmch_ctl); + gtt_size = chv_get_total_gtt_size(snb_gmch_ctl); + } else { + *stolen = gen8_get_stolen_size(snb_gmch_ctl); + gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl); + } - gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl); *gtt_total = (gtt_size / sizeof(gen8_gtt_pte_t)) << PAGE_SHIFT; - gen8_setup_private_ppat(dev_priv); + if (IS_CHERRYVIEW(dev)) + chv_setup_private_ppat(dev_priv); + else + bdw_setup_private_ppat(dev_priv); ret = ggtt_probe_common(dev, gtt_size); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index b5e8ac0f5ce4..1b96a06be3cb 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -95,6 +95,7 @@ typedef gen8_gtt_pte_t gen8_ppgtt_pde_t; #define PPAT_CACHED_INDEX _PAGE_PAT /* WB LLCeLLC */ #define PPAT_DISPLAY_ELLC_INDEX _PAGE_PCD /* WT eLLC */ +#define CHV_PPAT_SNOOP (1<<6) #define GEN8_PPAT_AGE(x) (x<<4) #define GEN8_PPAT_LLCeLLC (3<<2) #define GEN8_PPAT_LLCELLC (2<<2) @@ -256,11 +257,11 @@ struct i915_hw_ppgtt { dma_addr_t *gen8_pt_dma_addr[4]; }; - struct i915_hw_context *ctx; + struct intel_context *ctx; int (*enable)(struct i915_hw_ppgtt *ppgtt); int (*switch_mm)(struct i915_hw_ppgtt *ppgtt, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, bool synchronous); void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m); }; diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c new file mode 100644 index 000000000000..3521f998a178 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gem_render_state.c @@ -0,0 +1,198 @@ +/* + * Copyright © 2014 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. + * + * Authors: + * Mika Kuoppala <mika.kuoppala@intel.com> + * + */ + +#include "i915_drv.h" +#include "intel_renderstate.h" + +struct i915_render_state { + struct drm_i915_gem_object *obj; + unsigned long ggtt_offset; + void *batch; + u32 size; + u32 len; +}; + +static struct i915_render_state *render_state_alloc(struct drm_device *dev) +{ + struct i915_render_state *so; + struct page *page; + int ret; + + so = kzalloc(sizeof(*so), GFP_KERNEL); + if (!so) + return ERR_PTR(-ENOMEM); + + so->obj = i915_gem_alloc_object(dev, 4096); + if (so->obj == NULL) { + ret = -ENOMEM; + goto free; + } + so->size = 4096; + + ret = i915_gem_obj_ggtt_pin(so->obj, 4096, 0); + if (ret) + goto free_gem; + + BUG_ON(so->obj->pages->nents != 1); + page = sg_page(so->obj->pages->sgl); + + so->batch = kmap(page); + if (!so->batch) { + ret = -ENOMEM; + goto unpin; + } + + so->ggtt_offset = i915_gem_obj_ggtt_offset(so->obj); + + return so; +unpin: + i915_gem_object_ggtt_unpin(so->obj); +free_gem: + drm_gem_object_unreference(&so->obj->base); +free: + kfree(so); + return ERR_PTR(ret); +} + +static void render_state_free(struct i915_render_state *so) +{ + kunmap(so->batch); + i915_gem_object_ggtt_unpin(so->obj); + drm_gem_object_unreference(&so->obj->base); + kfree(so); +} + +static const struct intel_renderstate_rodata * +render_state_get_rodata(struct drm_device *dev, const int gen) +{ + switch (gen) { + case 6: + return &gen6_null_state; + case 7: + return &gen7_null_state; + case 8: + return &gen8_null_state; + } + + return NULL; +} + +static int render_state_setup(const int gen, + const struct intel_renderstate_rodata *rodata, + struct i915_render_state *so) +{ + const u64 goffset = i915_gem_obj_ggtt_offset(so->obj); + u32 reloc_index = 0; + u32 * const d = so->batch; + unsigned int i = 0; + int ret; + + if (!rodata || rodata->batch_items * 4 > so->size) + return -EINVAL; + + ret = i915_gem_object_set_to_cpu_domain(so->obj, true); + if (ret) + return ret; + + while (i < rodata->batch_items) { + u32 s = rodata->batch[i]; + + if (reloc_index < rodata->reloc_items && + i * 4 == rodata->reloc[reloc_index]) { + + s += goffset & 0xffffffff; + + /* We keep batch offsets max 32bit */ + if (gen >= 8) { + if (i + 1 >= rodata->batch_items || + rodata->batch[i + 1] != 0) + return -EINVAL; + + d[i] = s; + i++; + s = (goffset & 0xffffffff00000000ull) >> 32; + } + + reloc_index++; + } + + d[i] = s; + i++; + } + + ret = i915_gem_object_set_to_gtt_domain(so->obj, false); + if (ret) + return ret; + + if (rodata->reloc_items != reloc_index) { + DRM_ERROR("not all relocs resolved, %d out of %d\n", + reloc_index, rodata->reloc_items); + return -EINVAL; + } + + so->len = rodata->batch_items * 4; + + return 0; +} + +int i915_gem_render_state_init(struct intel_engine_cs *ring) +{ + const int gen = INTEL_INFO(ring->dev)->gen; + struct i915_render_state *so; + const struct intel_renderstate_rodata *rodata; + int ret; + + if (WARN_ON(ring->id != RCS)) + return -ENOENT; + + rodata = render_state_get_rodata(ring->dev, gen); + if (rodata == NULL) + return 0; + + so = render_state_alloc(ring->dev); + if (IS_ERR(so)) + return PTR_ERR(so); + + ret = render_state_setup(gen, rodata, so); + if (ret) + goto out; + + ret = ring->dispatch_execbuffer(ring, + i915_gem_obj_ggtt_offset(so->obj), + so->len, + I915_DISPATCH_SECURE); + if (ret) + goto out; + + i915_vma_move_to_active(i915_gem_obj_to_ggtt(so->obj), ring); + + ret = __i915_add_request(ring, NULL, so->obj, NULL); + /* __i915_add_request moves object to inactive if it fails */ +out: + render_state_free(so); + return ret; +} diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c new file mode 100644 index 000000000000..21ea92886a56 --- /dev/null +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -0,0 +1,711 @@ +/* + * Copyright © 2012-2014 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. + * + */ + +#include "drmP.h" +#include "i915_drm.h" +#include "i915_drv.h" +#include "i915_trace.h" +#include "intel_drv.h" +#include <linux/mmu_context.h> +#include <linux/mmu_notifier.h> +#include <linux/mempolicy.h> +#include <linux/swap.h> + +#if defined(CONFIG_MMU_NOTIFIER) +#include <linux/interval_tree.h> + +struct i915_mmu_notifier { + spinlock_t lock; + struct hlist_node node; + struct mmu_notifier mn; + struct rb_root objects; + struct drm_device *dev; + struct mm_struct *mm; + struct work_struct work; + unsigned long count; + unsigned long serial; +}; + +struct i915_mmu_object { + struct i915_mmu_notifier *mmu; + struct interval_tree_node it; + struct drm_i915_gem_object *obj; +}; + +static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn, + struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + struct i915_mmu_notifier *mn = container_of(_mn, struct i915_mmu_notifier, mn); + struct interval_tree_node *it = NULL; + unsigned long serial = 0; + + end--; /* interval ranges are inclusive, but invalidate range is exclusive */ + while (start < end) { + struct drm_i915_gem_object *obj; + + obj = NULL; + spin_lock(&mn->lock); + if (serial == mn->serial) + it = interval_tree_iter_next(it, start, end); + else + it = interval_tree_iter_first(&mn->objects, start, end); + if (it != NULL) { + obj = container_of(it, struct i915_mmu_object, it)->obj; + drm_gem_object_reference(&obj->base); + serial = mn->serial; + } + spin_unlock(&mn->lock); + if (obj == NULL) + return; + + mutex_lock(&mn->dev->struct_mutex); + /* Cancel any active worker and force us to re-evaluate gup */ + obj->userptr.work = NULL; + + if (obj->pages != NULL) { + struct drm_i915_private *dev_priv = to_i915(mn->dev); + struct i915_vma *vma, *tmp; + bool was_interruptible; + + was_interruptible = dev_priv->mm.interruptible; + dev_priv->mm.interruptible = false; + + list_for_each_entry_safe(vma, tmp, &obj->vma_list, vma_link) { + int ret = i915_vma_unbind(vma); + WARN_ON(ret && ret != -EIO); + } + WARN_ON(i915_gem_object_put_pages(obj)); + + dev_priv->mm.interruptible = was_interruptible; + } + + start = obj->userptr.ptr + obj->base.size; + + drm_gem_object_unreference(&obj->base); + mutex_unlock(&mn->dev->struct_mutex); + } +} + +static const struct mmu_notifier_ops i915_gem_userptr_notifier = { + .invalidate_range_start = i915_gem_userptr_mn_invalidate_range_start, +}; + +static struct i915_mmu_notifier * +__i915_mmu_notifier_lookup(struct drm_device *dev, struct mm_struct *mm) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct i915_mmu_notifier *mmu; + + /* Protected by dev->struct_mutex */ + hash_for_each_possible(dev_priv->mmu_notifiers, mmu, node, (unsigned long)mm) + if (mmu->mm == mm) + return mmu; + + return NULL; +} + +static struct i915_mmu_notifier * +i915_mmu_notifier_get(struct drm_device *dev, struct mm_struct *mm) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + struct i915_mmu_notifier *mmu; + int ret; + + lockdep_assert_held(&dev->struct_mutex); + + mmu = __i915_mmu_notifier_lookup(dev, mm); + if (mmu) + return mmu; + + mmu = kmalloc(sizeof(*mmu), GFP_KERNEL); + if (mmu == NULL) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&mmu->lock); + mmu->dev = dev; + mmu->mn.ops = &i915_gem_userptr_notifier; + mmu->mm = mm; + mmu->objects = RB_ROOT; + mmu->count = 0; + mmu->serial = 0; + + /* Protected by mmap_sem (write-lock) */ + ret = __mmu_notifier_register(&mmu->mn, mm); + if (ret) { + kfree(mmu); + return ERR_PTR(ret); + } + + /* Protected by dev->struct_mutex */ + hash_add(dev_priv->mmu_notifiers, &mmu->node, (unsigned long)mm); + return mmu; +} + +static void +__i915_mmu_notifier_destroy_worker(struct work_struct *work) +{ + struct i915_mmu_notifier *mmu = container_of(work, typeof(*mmu), work); + mmu_notifier_unregister(&mmu->mn, mmu->mm); + kfree(mmu); +} + +static void +__i915_mmu_notifier_destroy(struct i915_mmu_notifier *mmu) +{ + lockdep_assert_held(&mmu->dev->struct_mutex); + + /* Protected by dev->struct_mutex */ + hash_del(&mmu->node); + + /* Our lock ordering is: mmap_sem, mmu_notifier_scru, struct_mutex. + * We enter the function holding struct_mutex, therefore we need + * to drop our mutex prior to calling mmu_notifier_unregister in + * order to prevent lock inversion (and system-wide deadlock) + * between the mmap_sem and struct-mutex. Hence we defer the + * unregistration to a workqueue where we hold no locks. + */ + INIT_WORK(&mmu->work, __i915_mmu_notifier_destroy_worker); + schedule_work(&mmu->work); +} + +static void __i915_mmu_notifier_update_serial(struct i915_mmu_notifier *mmu) +{ + if (++mmu->serial == 0) + mmu->serial = 1; +} + +static void +i915_mmu_notifier_del(struct i915_mmu_notifier *mmu, + struct i915_mmu_object *mn) +{ + lockdep_assert_held(&mmu->dev->struct_mutex); + + spin_lock(&mmu->lock); + interval_tree_remove(&mn->it, &mmu->objects); + __i915_mmu_notifier_update_serial(mmu); + spin_unlock(&mmu->lock); + + /* Protected against _add() by dev->struct_mutex */ + if (--mmu->count == 0) + __i915_mmu_notifier_destroy(mmu); +} + +static int +i915_mmu_notifier_add(struct i915_mmu_notifier *mmu, + struct i915_mmu_object *mn) +{ + struct interval_tree_node *it; + int ret; + + ret = i915_mutex_lock_interruptible(mmu->dev); + if (ret) + return ret; + + /* Make sure we drop the final active reference (and thereby + * remove the objects from the interval tree) before we do + * the check for overlapping objects. + */ + i915_gem_retire_requests(mmu->dev); + + /* Disallow overlapping userptr objects */ + spin_lock(&mmu->lock); + it = interval_tree_iter_first(&mmu->objects, + mn->it.start, mn->it.last); + if (it) { + struct drm_i915_gem_object *obj; + + /* We only need to check the first object in the range as it + * either has cancelled gup work queued and we need to + * return back to the user to give time for the gup-workers + * to flush their object references upon which the object will + * be removed from the interval-tree, or the the range is + * still in use by another client and the overlap is invalid. + */ + + obj = container_of(it, struct i915_mmu_object, it)->obj; + ret = obj->userptr.workers ? -EAGAIN : -EINVAL; + } else { + interval_tree_insert(&mn->it, &mmu->objects); + __i915_mmu_notifier_update_serial(mmu); + ret = 0; + } + spin_unlock(&mmu->lock); + mutex_unlock(&mmu->dev->struct_mutex); + + return ret; +} + +static void +i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj) +{ + struct i915_mmu_object *mn; + + mn = obj->userptr.mn; + if (mn == NULL) + return; + + i915_mmu_notifier_del(mn->mmu, mn); + obj->userptr.mn = NULL; +} + +static int +i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj, + unsigned flags) +{ + struct i915_mmu_notifier *mmu; + struct i915_mmu_object *mn; + int ret; + + if (flags & I915_USERPTR_UNSYNCHRONIZED) + return capable(CAP_SYS_ADMIN) ? 0 : -EPERM; + + down_write(&obj->userptr.mm->mmap_sem); + ret = i915_mutex_lock_interruptible(obj->base.dev); + if (ret == 0) { + mmu = i915_mmu_notifier_get(obj->base.dev, obj->userptr.mm); + if (!IS_ERR(mmu)) + mmu->count++; /* preemptive add to act as a refcount */ + else + ret = PTR_ERR(mmu); + mutex_unlock(&obj->base.dev->struct_mutex); + } + up_write(&obj->userptr.mm->mmap_sem); + if (ret) + return ret; + + mn = kzalloc(sizeof(*mn), GFP_KERNEL); + if (mn == NULL) { + ret = -ENOMEM; + goto destroy_mmu; + } + + mn->mmu = mmu; + mn->it.start = obj->userptr.ptr; + mn->it.last = mn->it.start + obj->base.size - 1; + mn->obj = obj; + + ret = i915_mmu_notifier_add(mmu, mn); + if (ret) + goto free_mn; + + obj->userptr.mn = mn; + return 0; + +free_mn: + kfree(mn); +destroy_mmu: + mutex_lock(&obj->base.dev->struct_mutex); + if (--mmu->count == 0) + __i915_mmu_notifier_destroy(mmu); + mutex_unlock(&obj->base.dev->struct_mutex); + return ret; +} + +#else + +static void +i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj) +{ +} + +static int +i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj, + unsigned flags) +{ + if ((flags & I915_USERPTR_UNSYNCHRONIZED) == 0) + return -ENODEV; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return 0; +} +#endif + +struct get_pages_work { + struct work_struct work; + struct drm_i915_gem_object *obj; + struct task_struct *task; +}; + + +#if IS_ENABLED(CONFIG_SWIOTLB) +#define swiotlb_active() swiotlb_nr_tbl() +#else +#define swiotlb_active() 0 +#endif + +static int +st_set_pages(struct sg_table **st, struct page **pvec, int num_pages) +{ + struct scatterlist *sg; + int ret, n; + + *st = kmalloc(sizeof(**st), GFP_KERNEL); + if (*st == NULL) + return -ENOMEM; + + if (swiotlb_active()) { + ret = sg_alloc_table(*st, num_pages, GFP_KERNEL); + if (ret) + goto err; + + for_each_sg((*st)->sgl, sg, num_pages, n) + sg_set_page(sg, pvec[n], PAGE_SIZE, 0); + } else { + ret = sg_alloc_table_from_pages(*st, pvec, num_pages, + 0, num_pages << PAGE_SHIFT, + GFP_KERNEL); + if (ret) + goto err; + } + + return 0; + +err: + kfree(*st); + *st = NULL; + return ret; +} + +static void +__i915_gem_userptr_get_pages_worker(struct work_struct *_work) +{ + struct get_pages_work *work = container_of(_work, typeof(*work), work); + struct drm_i915_gem_object *obj = work->obj; + struct drm_device *dev = obj->base.dev; + const int num_pages = obj->base.size >> PAGE_SHIFT; + struct page **pvec; + int pinned, ret; + + ret = -ENOMEM; + pinned = 0; + + pvec = kmalloc(num_pages*sizeof(struct page *), + GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); + if (pvec == NULL) + pvec = drm_malloc_ab(num_pages, sizeof(struct page *)); + if (pvec != NULL) { + struct mm_struct *mm = obj->userptr.mm; + + down_read(&mm->mmap_sem); + while (pinned < num_pages) { + ret = get_user_pages(work->task, mm, + obj->userptr.ptr + pinned * PAGE_SIZE, + num_pages - pinned, + !obj->userptr.read_only, 0, + pvec + pinned, NULL); + if (ret < 0) + break; + + pinned += ret; + } + up_read(&mm->mmap_sem); + } + + mutex_lock(&dev->struct_mutex); + if (obj->userptr.work != &work->work) { + ret = 0; + } else if (pinned == num_pages) { + ret = st_set_pages(&obj->pages, pvec, num_pages); + if (ret == 0) { + list_add_tail(&obj->global_list, &to_i915(dev)->mm.unbound_list); + pinned = 0; + } + } + + obj->userptr.work = ERR_PTR(ret); + obj->userptr.workers--; + drm_gem_object_unreference(&obj->base); + mutex_unlock(&dev->struct_mutex); + + release_pages(pvec, pinned, 0); + drm_free_large(pvec); + + put_task_struct(work->task); + kfree(work); +} + +static int +i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) +{ + const int num_pages = obj->base.size >> PAGE_SHIFT; + struct page **pvec; + int pinned, ret; + + /* If userspace should engineer that these pages are replaced in + * the vma between us binding this page into the GTT and completion + * of rendering... Their loss. If they change the mapping of their + * pages they need to create a new bo to point to the new vma. + * + * However, that still leaves open the possibility of the vma + * being copied upon fork. Which falls under the same userspace + * synchronisation issue as a regular bo, except that this time + * the process may not be expecting that a particular piece of + * memory is tied to the GPU. + * + * Fortunately, we can hook into the mmu_notifier in order to + * discard the page references prior to anything nasty happening + * to the vma (discard or cloning) which should prevent the more + * egregious cases from causing harm. + */ + + pvec = NULL; + pinned = 0; + if (obj->userptr.mm == current->mm) { + pvec = kmalloc(num_pages*sizeof(struct page *), + GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY); + if (pvec == NULL) { + pvec = drm_malloc_ab(num_pages, sizeof(struct page *)); + if (pvec == NULL) + return -ENOMEM; + } + + pinned = __get_user_pages_fast(obj->userptr.ptr, num_pages, + !obj->userptr.read_only, pvec); + } + if (pinned < num_pages) { + if (pinned < 0) { + ret = pinned; + pinned = 0; + } else { + /* Spawn a worker so that we can acquire the + * user pages without holding our mutex. Access + * to the user pages requires mmap_sem, and we have + * a strict lock ordering of mmap_sem, struct_mutex - + * we already hold struct_mutex here and so cannot + * call gup without encountering a lock inversion. + * + * Userspace will keep on repeating the operation + * (thanks to EAGAIN) until either we hit the fast + * path or the worker completes. If the worker is + * cancelled or superseded, the task is still run + * but the results ignored. (This leads to + * complications that we may have a stray object + * refcount that we need to be wary of when + * checking for existing objects during creation.) + * If the worker encounters an error, it reports + * that error back to this function through + * obj->userptr.work = ERR_PTR. + */ + ret = -EAGAIN; + if (obj->userptr.work == NULL && + obj->userptr.workers < I915_GEM_USERPTR_MAX_WORKERS) { + struct get_pages_work *work; + + work = kmalloc(sizeof(*work), GFP_KERNEL); + if (work != NULL) { + obj->userptr.work = &work->work; + obj->userptr.workers++; + + work->obj = obj; + drm_gem_object_reference(&obj->base); + + work->task = current; + get_task_struct(work->task); + + INIT_WORK(&work->work, __i915_gem_userptr_get_pages_worker); + schedule_work(&work->work); + } else + ret = -ENOMEM; + } else { + if (IS_ERR(obj->userptr.work)) { + ret = PTR_ERR(obj->userptr.work); + obj->userptr.work = NULL; + } + } + } + } else { + ret = st_set_pages(&obj->pages, pvec, num_pages); + if (ret == 0) { + obj->userptr.work = NULL; + pinned = 0; + } + } + + release_pages(pvec, pinned, 0); + drm_free_large(pvec); + return ret; +} + +static void +i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj) +{ + struct scatterlist *sg; + int i; + + BUG_ON(obj->userptr.work != NULL); + + if (obj->madv != I915_MADV_WILLNEED) + obj->dirty = 0; + + for_each_sg(obj->pages->sgl, sg, obj->pages->nents, i) { + struct page *page = sg_page(sg); + + if (obj->dirty) + set_page_dirty(page); + + mark_page_accessed(page); + page_cache_release(page); + } + obj->dirty = 0; + + sg_free_table(obj->pages); + kfree(obj->pages); +} + +static void +i915_gem_userptr_release(struct drm_i915_gem_object *obj) +{ + i915_gem_userptr_release__mmu_notifier(obj); + + if (obj->userptr.mm) { + mmput(obj->userptr.mm); + obj->userptr.mm = NULL; + } +} + +static int +i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj) +{ + if (obj->userptr.mn) + return 0; + + return i915_gem_userptr_init__mmu_notifier(obj, 0); +} + +static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = { + .dmabuf_export = i915_gem_userptr_dmabuf_export, + .get_pages = i915_gem_userptr_get_pages, + .put_pages = i915_gem_userptr_put_pages, + .release = i915_gem_userptr_release, +}; + +/** + * Creates a new mm object that wraps some normal memory from the process + * context - user memory. + * + * We impose several restrictions upon the memory being mapped + * into the GPU. + * 1. It must be page aligned (both start/end addresses, i.e ptr and size). + * 2. It cannot overlap any other userptr object in the same address space. + * 3. It must be normal system memory, not a pointer into another map of IO + * space (e.g. it must not be a GTT mmapping of another object). + * 4. We only allow a bo as large as we could in theory map into the GTT, + * that is we limit the size to the total size of the GTT. + * 5. The bo is marked as being snoopable. The backing pages are left + * accessible directly by the CPU, but reads and writes by the GPU may + * incur the cost of a snoop (unless you have an LLC architecture). + * + * Synchronisation between multiple users and the GPU is left to userspace + * through the normal set-domain-ioctl. The kernel will enforce that the + * GPU relinquishes the VMA before it is returned back to the system + * i.e. upon free(), munmap() or process termination. However, the userspace + * malloc() library may not immediately relinquish the VMA after free() and + * instead reuse it whilst the GPU is still reading and writing to the VMA. + * Caveat emptor. + * + * Also note, that the object created here is not currently a "first class" + * object, in that several ioctls are banned. These are the CPU access + * ioctls: mmap(), pwrite and pread. In practice, you are expected to use + * direct access via your pointer rather than use those ioctls. + * + * If you think this is a good interface to use to pass GPU memory between + * drivers, please use dma-buf instead. In fact, wherever possible use + * dma-buf instead. + */ +int +i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct drm_i915_gem_userptr *args = data; + struct drm_i915_gem_object *obj; + int ret; + u32 handle; + + if (args->flags & ~(I915_USERPTR_READ_ONLY | + I915_USERPTR_UNSYNCHRONIZED)) + return -EINVAL; + + if (offset_in_page(args->user_ptr | args->user_size)) + return -EINVAL; + + if (args->user_size > dev_priv->gtt.base.total) + return -E2BIG; + + if (!access_ok(args->flags & I915_USERPTR_READ_ONLY ? VERIFY_READ : VERIFY_WRITE, + (char __user *)(unsigned long)args->user_ptr, args->user_size)) + return -EFAULT; + + if (args->flags & I915_USERPTR_READ_ONLY) { + /* On almost all of the current hw, we cannot tell the GPU that a + * page is readonly, so this is just a placeholder in the uAPI. + */ + return -ENODEV; + } + + /* Allocate the new object */ + obj = i915_gem_object_alloc(dev); + if (obj == NULL) + return -ENOMEM; + + drm_gem_private_object_init(dev, &obj->base, args->user_size); + i915_gem_object_init(obj, &i915_gem_userptr_ops); + obj->cache_level = I915_CACHE_LLC; + obj->base.write_domain = I915_GEM_DOMAIN_CPU; + obj->base.read_domains = I915_GEM_DOMAIN_CPU; + + obj->userptr.ptr = args->user_ptr; + obj->userptr.read_only = !!(args->flags & I915_USERPTR_READ_ONLY); + + /* And keep a pointer to the current->mm for resolving the user pages + * at binding. This means that we need to hook into the mmu_notifier + * in order to detect if the mmu is destroyed. + */ + ret = -ENOMEM; + if ((obj->userptr.mm = get_task_mm(current))) + ret = i915_gem_userptr_init__mmu_notifier(obj, args->flags); + if (ret == 0) + ret = drm_gem_handle_create(file, &obj->base, &handle); + + /* drop reference from allocate - handle holds it now */ + drm_gem_object_unreference_unlocked(&obj->base); + if (ret) + return ret; + + args->handle = handle; + return 0; +} + +int +i915_gem_init_userptr(struct drm_device *dev) +{ +#if defined(CONFIG_MMU_NOTIFIER) + struct drm_i915_private *dev_priv = to_i915(dev); + hash_init(dev_priv->mmu_notifiers); +#endif + return 0; +} diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 2d819858c19b..87ec60e181a7 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -205,6 +205,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m, err_puts(m, tiling_flag(err->tiling)); err_puts(m, dirty_flag(err->dirty)); err_puts(m, purgeable_flag(err->purgeable)); + err_puts(m, err->userptr ? " userptr" : ""); err_puts(m, err->ring != -1 ? " " : ""); err_puts(m, ring_str(err->ring)); err_puts(m, i915_cache_level_str(err->cache_level)); @@ -641,6 +642,7 @@ static void capture_bo(struct drm_i915_error_buffer *err, err->tiling = obj->tiling_mode; err->dirty = obj->dirty; err->purgeable = obj->madv != I915_MADV_WILLNEED; + err->userptr = obj->userptr.mm != NULL; err->ring = obj->ring ? obj->ring->id : -1; err->cache_level = obj->cache_level; } @@ -745,7 +747,7 @@ static void i915_gem_record_fences(struct drm_device *dev, } static void i915_record_ring_state(struct drm_device *dev, - struct intel_ring_buffer *ring, + struct intel_engine_cs *ring, struct drm_i915_error_ring *ering) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -823,8 +825,8 @@ static void i915_record_ring_state(struct drm_device *dev, ering->hws = I915_READ(mmio); } - ering->cpu_ring_head = ring->head; - ering->cpu_ring_tail = ring->tail; + ering->cpu_ring_head = ring->buffer->head; + ering->cpu_ring_tail = ring->buffer->tail; ering->hangcheck_score = ring->hangcheck.score; ering->hangcheck_action = ring->hangcheck.action; @@ -857,7 +859,7 @@ static void i915_record_ring_state(struct drm_device *dev, } -static void i915_gem_record_active_context(struct intel_ring_buffer *ring, +static void i915_gem_record_active_context(struct intel_engine_cs *ring, struct drm_i915_error_state *error, struct drm_i915_error_ring *ering) { @@ -884,7 +886,7 @@ static void i915_gem_record_rings(struct drm_device *dev, int i, count; for (i = 0; i < I915_NUM_RINGS; i++) { - struct intel_ring_buffer *ring = &dev_priv->ring[i]; + struct intel_engine_cs *ring = &dev_priv->ring[i]; if (ring->dev == NULL) continue; @@ -928,7 +930,7 @@ static void i915_gem_record_rings(struct drm_device *dev, } error->ring[i].ringbuffer = - i915_error_ggtt_object_create(dev_priv, ring->obj); + i915_error_ggtt_object_create(dev_priv, ring->buffer->obj); if (ring->status_page.obj) error->ring[i].hws_page = diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 2d7618366b75..28bae6e4a424 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -248,6 +248,46 @@ static bool ivb_can_enable_err_int(struct drm_device *dev) return true; } +/** + * bdw_update_pm_irq - update GT interrupt 2 + * @dev_priv: driver private + * @interrupt_mask: mask of interrupt bits to update + * @enabled_irq_mask: mask of interrupt bits to enable + * + * Copied from the snb function, updated with relevant register offsets + */ +static void bdw_update_pm_irq(struct drm_i915_private *dev_priv, + uint32_t interrupt_mask, + uint32_t enabled_irq_mask) +{ + uint32_t new_val; + + assert_spin_locked(&dev_priv->irq_lock); + + if (WARN_ON(dev_priv->pm.irqs_disabled)) + return; + + new_val = dev_priv->pm_irq_mask; + new_val &= ~interrupt_mask; + new_val |= (~enabled_irq_mask & interrupt_mask); + + if (new_val != dev_priv->pm_irq_mask) { + dev_priv->pm_irq_mask = new_val; + I915_WRITE(GEN8_GT_IMR(2), dev_priv->pm_irq_mask); + POSTING_READ(GEN8_GT_IMR(2)); + } +} + +void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask) +{ + bdw_update_pm_irq(dev_priv, mask, mask); +} + +void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask) +{ + bdw_update_pm_irq(dev_priv, mask, 0); +} + static bool cpt_can_enable_serr_int(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -266,16 +306,50 @@ static bool cpt_can_enable_serr_int(struct drm_device *dev) return true; } -static void i9xx_clear_fifo_underrun(struct drm_device *dev, enum pipe pipe) +void i9xx_check_fifo_underruns(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *crtc; + unsigned long flags; + + spin_lock_irqsave(&dev_priv->irq_lock, flags); + + for_each_intel_crtc(dev, crtc) { + u32 reg = PIPESTAT(crtc->pipe); + u32 pipestat; + + if (crtc->cpu_fifo_underrun_disabled) + continue; + + pipestat = I915_READ(reg) & 0xffff0000; + if ((pipestat & PIPE_FIFO_UNDERRUN_STATUS) == 0) + continue; + + I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS); + POSTING_READ(reg); + + DRM_ERROR("pipe %c underrun\n", pipe_name(crtc->pipe)); + } + + spin_unlock_irqrestore(&dev_priv->irq_lock, flags); +} + +static void i9xx_set_fifo_underrun_reporting(struct drm_device *dev, + enum pipe pipe, bool enable) { struct drm_i915_private *dev_priv = dev->dev_private; u32 reg = PIPESTAT(pipe); - u32 pipestat = I915_READ(reg) & 0x7fff0000; + u32 pipestat = I915_READ(reg) & 0xffff0000; assert_spin_locked(&dev_priv->irq_lock); - I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS); - POSTING_READ(reg); + if (enable) { + I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS); + POSTING_READ(reg); + } else { + if (pipestat & PIPE_FIFO_UNDERRUN_STATUS) + DRM_ERROR("pipe %c underrun\n", pipe_name(pipe)); + } } static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev, @@ -303,15 +377,11 @@ static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev, ironlake_enable_display_irq(dev_priv, DE_ERR_INT_IVB); } else { - bool was_enabled = !(I915_READ(DEIMR) & DE_ERR_INT_IVB); - - /* Change the state _after_ we've read out the current one. */ ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB); - if (!was_enabled && - (I915_READ(GEN7_ERR_INT) & ERR_INT_FIFO_UNDERRUN(pipe))) { - DRM_DEBUG_KMS("uncleared fifo underrun on pipe %c\n", - pipe_name(pipe)); + if (I915_READ(GEN7_ERR_INT) & ERR_INT_FIFO_UNDERRUN(pipe)) { + DRM_ERROR("uncleared fifo underrun on pipe %c\n", + pipe_name(pipe)); } } } @@ -387,16 +457,11 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, ibx_enable_display_interrupt(dev_priv, SDE_ERROR_CPT); } else { - uint32_t tmp = I915_READ(SERR_INT); - bool was_enabled = !(I915_READ(SDEIMR) & SDE_ERROR_CPT); - - /* Change the state _after_ we've read out the current one. */ ibx_disable_display_interrupt(dev_priv, SDE_ERROR_CPT); - if (!was_enabled && - (tmp & SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder))) { - DRM_DEBUG_KMS("uncleared pch fifo underrun on pch transcoder %c\n", - transcoder_name(pch_transcoder)); + if (I915_READ(SERR_INT) & SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder)) { + DRM_ERROR("uncleared pch fifo underrun on pch transcoder %c\n", + transcoder_name(pch_transcoder)); } } } @@ -415,8 +480,8 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev, * * Returns the previous state of underrun reporting. */ -bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, - enum pipe pipe, bool enable) +static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, + enum pipe pipe, bool enable) { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; @@ -432,8 +497,8 @@ bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, intel_crtc->cpu_fifo_underrun_disabled = !enable; - if (enable && (INTEL_INFO(dev)->gen < 5 || IS_VALLEYVIEW(dev))) - i9xx_clear_fifo_underrun(dev, pipe); + if (INTEL_INFO(dev)->gen < 5 || IS_VALLEYVIEW(dev)) + i9xx_set_fifo_underrun_reporting(dev, pipe, enable); else if (IS_GEN5(dev) || IS_GEN6(dev)) ironlake_set_fifo_underrun_reporting(dev, pipe, enable); else if (IS_GEN7(dev)) @@ -578,11 +643,17 @@ static u32 vlv_get_pipestat_enable_mask(struct drm_device *dev, u32 status_mask) u32 enable_mask = status_mask << 16; /* - * On pipe A we don't support the PSR interrupt yet, on pipe B the - * same bit MBZ. + * On pipe A we don't support the PSR interrupt yet, + * on pipe B and C the same bit MBZ. */ if (WARN_ON_ONCE(status_mask & PIPE_A_PSR_STATUS_VLV)) return 0; + /* + * On pipe B and C we don't support the PSR interrupt yet, on pipe + * A the same bit is for perf counters which we don't use either. + */ + if (WARN_ON_ONCE(status_mask & PIPE_B_PSR_STATUS_VLV)) + return 0; enable_mask &= ~(PIPE_FIFO_UNDERRUN_STATUS | SPRITE0_FLIP_DONE_INT_EN_VLV | @@ -669,6 +740,56 @@ i915_pipe_enabled(struct drm_device *dev, int pipe) } } +/* + * This timing diagram depicts the video signal in and + * around the vertical blanking period. + * + * Assumptions about the fictitious mode used in this example: + * vblank_start >= 3 + * vsync_start = vblank_start + 1 + * vsync_end = vblank_start + 2 + * vtotal = vblank_start + 3 + * + * start of vblank: + * latch double buffered registers + * increment frame counter (ctg+) + * generate start of vblank interrupt (gen4+) + * | + * | frame start: + * | generate frame start interrupt (aka. vblank interrupt) (gmch) + * | may be shifted forward 1-3 extra lines via PIPECONF + * | | + * | | start of vsync: + * | | generate vsync interrupt + * | | | + * ___xxxx___ ___xxxx___ ___xxxx___ ___xxxx___ ___xxxx___ ___xxxx + * . \hs/ . \hs/ \hs/ \hs/ . \hs/ + * ----va---> <-----------------vb--------------------> <--------va------------- + * | | <----vs-----> | + * -vbs-----> <---vbs+1---> <---vbs+2---> <-----0-----> <-----1-----> <-----2--- (scanline counter gen2) + * -vbs-2---> <---vbs-1---> <---vbs-----> <---vbs+1---> <---vbs+2---> <-----0--- (scanline counter gen3+) + * -vbs-2---> <---vbs-2---> <---vbs-1---> <---vbs-----> <---vbs+1---> <---vbs+2- (scanline counter hsw+ hdmi) + * | | | + * last visible pixel first visible pixel + * | increment frame counter (gen3/4) + * pixel counter = vblank_start * htotal pixel counter = 0 (gen3/4) + * + * x = horizontal active + * _ = horizontal blanking + * hs = horizontal sync + * va = vertical active + * vb = vertical blanking + * vs = vertical sync + * vbs = vblank_start (number) + * + * Summary: + * - most events happen at the start of horizontal sync + * - frame start happens at the start of horizontal blank, 1-4 lines + * (depending on PIPECONF settings) after the start of vblank + * - gen3/4 pixel and frame counter are synchronized with the start + * of horizontal active on the first line of vertical active + */ + static u32 i8xx_get_vblank_counter(struct drm_device *dev, int pipe) { /* Gen2 doesn't have a hardware frame counter */ @@ -683,7 +804,7 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) struct drm_i915_private *dev_priv = dev->dev_private; unsigned long high_frame; unsigned long low_frame; - u32 high1, high2, low, pixel, vbl_start; + u32 high1, high2, low, pixel, vbl_start, hsync_start, htotal; if (!i915_pipe_enabled(dev, pipe)) { DRM_DEBUG_DRIVER("trying to get vblank count for disabled " @@ -697,17 +818,28 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) const struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode; - vbl_start = mode->crtc_vblank_start * mode->crtc_htotal; + htotal = mode->crtc_htotal; + hsync_start = mode->crtc_hsync_start; + vbl_start = mode->crtc_vblank_start; + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + vbl_start = DIV_ROUND_UP(vbl_start, 2); } else { enum transcoder cpu_transcoder = (enum transcoder) pipe; - u32 htotal; htotal = ((I915_READ(HTOTAL(cpu_transcoder)) >> 16) & 0x1fff) + 1; + hsync_start = (I915_READ(HSYNC(cpu_transcoder)) & 0x1fff) + 1; vbl_start = (I915_READ(VBLANK(cpu_transcoder)) & 0x1fff) + 1; - - vbl_start *= htotal; + if ((I915_READ(PIPECONF(cpu_transcoder)) & + PIPECONF_INTERLACE_MASK) != PIPECONF_PROGRESSIVE) + vbl_start = DIV_ROUND_UP(vbl_start, 2); } + /* Convert to pixel count */ + vbl_start *= htotal; + + /* Start of vblank event occurs at start of hsync */ + vbl_start -= htotal - hsync_start; + high_frame = PIPEFRAME(pipe); low_frame = PIPEFRAMEPIXEL(pipe); @@ -757,9 +889,9 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc) struct drm_i915_private *dev_priv = dev->dev_private; const struct drm_display_mode *mode = &crtc->config.adjusted_mode; enum pipe pipe = crtc->pipe; - int vtotal = mode->crtc_vtotal; - int position; + int position, vtotal; + vtotal = mode->crtc_vtotal; if (mode->flags & DRM_MODE_FLAG_INTERLACE) vtotal /= 2; @@ -769,14 +901,10 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc) position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3; /* - * Scanline counter increments at leading edge of hsync, and - * it starts counting from vtotal-1 on the first active line. - * That means the scanline counter value is always one less - * than what we would expect. Ie. just after start of vblank, - * which also occurs at start of hsync (on the last active line), - * the scanline counter will read vblank_start-1. + * See update_scanline_offset() for the details on the + * scanline_offset adjustment. */ - return (position + 1) % vtotal; + return (position + crtc->scanline_offset) % vtotal; } static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, @@ -844,6 +972,18 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, vtotal *= htotal; /* + * In interlaced modes, the pixel counter counts all pixels, + * so one field will have htotal more pixels. In order to avoid + * the reported position from jumping backwards when the pixel + * counter is beyond the length of the shorter field, just + * clamp the position the length of the shorter field. This + * matches how the scanline counter based position works since + * the scanline counter doesn't count the two half lines. + */ + if (position >= vtotal) + position = vtotal - 1; + + /* * Start of vblank interrupt is triggered at start of hsync, * just prior to the first active line of vblank. However we * consider lines to start at the leading edge of horizontal @@ -1077,9 +1217,9 @@ static void ironlake_rps_change_irq_handler(struct drm_device *dev) } static void notify_ring(struct drm_device *dev, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { - if (ring->obj == NULL) + if (!intel_ring_initialized(ring)) return; trace_i915_gem_request_complete(ring); @@ -1098,8 +1238,12 @@ static void gen6_pm_rps_work(struct work_struct *work) spin_lock_irq(&dev_priv->irq_lock); pm_iir = dev_priv->rps.pm_iir; dev_priv->rps.pm_iir = 0; - /* Make sure not to corrupt PMIMR state used by ringbuffer code */ - snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + if (IS_BROADWELL(dev_priv->dev)) + bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + else { + /* Make sure not to corrupt PMIMR state used by ringbuffer */ + snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + } spin_unlock_irq(&dev_priv->irq_lock); /* Make sure we didn't queue anything we're not going to process. */ @@ -1296,6 +1440,19 @@ static void snb_gt_irq_handler(struct drm_device *dev, ivybridge_parity_error_irq_handler(dev, gt_iir); } +static void gen8_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir) +{ + if ((pm_iir & dev_priv->pm_rps_events) == 0) + return; + + spin_lock(&dev_priv->irq_lock); + dev_priv->rps.pm_iir |= pm_iir & dev_priv->pm_rps_events; + bdw_disable_pm_irq(dev_priv, pm_iir & dev_priv->pm_rps_events); + spin_unlock(&dev_priv->irq_lock); + + queue_work(dev_priv->wq, &dev_priv->rps.work); +} + static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev, struct drm_i915_private *dev_priv, u32 master_ctl) @@ -1334,6 +1491,17 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev, DRM_ERROR("The master control interrupt lied (GT1)!\n"); } + if (master_ctl & GEN8_GT_PM_IRQ) { + tmp = I915_READ(GEN8_GT_IIR(2)); + if (tmp & dev_priv->pm_rps_events) { + ret = IRQ_HANDLED; + gen8_rps_irq_handler(dev_priv, tmp); + I915_WRITE(GEN8_GT_IIR(2), + tmp & dev_priv->pm_rps_events); + } else + DRM_ERROR("The master control interrupt lied (PM)!\n"); + } + if (master_ctl & GEN8_GT_VECS_IRQ) { tmp = I915_READ(GEN8_GT_IIR(3)); if (tmp) { @@ -1598,6 +1766,9 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir) case PIPE_B: iir_bit = I915_DISPLAY_PIPE_B_EVENT_INTERRUPT; break; + case PIPE_C: + iir_bit = I915_DISPLAY_PIPE_C_EVENT_INTERRUPT; + break; } if (iir & iir_bit) mask |= dev_priv->pipestat_irq_mask[pipe]; @@ -1668,7 +1839,7 @@ static void i9xx_hpd_irq_handler(struct drm_device *dev) static irqreturn_t valleyview_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u32 iir, gt_iir, pm_iir; irqreturn_t ret = IRQ_NONE; @@ -1703,6 +1874,40 @@ out: return ret; } +static irqreturn_t cherryview_irq_handler(int irq, void *arg) +{ + struct drm_device *dev = arg; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 master_ctl, iir; + irqreturn_t ret = IRQ_NONE; + + for (;;) { + master_ctl = I915_READ(GEN8_MASTER_IRQ) & ~GEN8_MASTER_IRQ_CONTROL; + iir = I915_READ(VLV_IIR); + + if (master_ctl == 0 && iir == 0) + break; + + I915_WRITE(GEN8_MASTER_IRQ, 0); + + gen8_gt_irq_handler(dev, dev_priv, master_ctl); + + valleyview_pipestat_irq_handler(dev, iir); + + /* Consume port. Then clear IIR or we'll miss events */ + i9xx_hpd_irq_handler(dev); + + I915_WRITE(VLV_IIR, iir); + + I915_WRITE(GEN8_MASTER_IRQ, DE_MASTER_IRQ_CONTROL); + POSTING_READ(GEN8_MASTER_IRQ); + + ret = IRQ_HANDLED; + } + + return ret; +} + static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -1935,7 +2140,7 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir) static irqreturn_t ironlake_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u32 de_iir, gt_iir, de_ier, sde_ier = 0; irqreturn_t ret = IRQ_NONE; @@ -2111,7 +2316,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) static void i915_error_wake_up(struct drm_i915_private *dev_priv, bool reset_completed) { - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; /* @@ -2544,14 +2749,14 @@ static void gen8_disable_vblank(struct drm_device *dev, int pipe) } static u32 -ring_last_seqno(struct intel_ring_buffer *ring) +ring_last_seqno(struct intel_engine_cs *ring) { return list_entry(ring->request_list.prev, struct drm_i915_gem_request, list)->seqno; } static bool -ring_idle(struct intel_ring_buffer *ring, u32 seqno) +ring_idle(struct intel_engine_cs *ring, u32 seqno) { return (list_empty(&ring->request_list) || i915_seqno_passed(seqno, ring_last_seqno(ring))); @@ -2574,11 +2779,11 @@ ipehr_is_semaphore_wait(struct drm_device *dev, u32 ipehr) } } -static struct intel_ring_buffer * -semaphore_wait_to_signaller_ring(struct intel_ring_buffer *ring, u32 ipehr) +static struct intel_engine_cs * +semaphore_wait_to_signaller_ring(struct intel_engine_cs *ring, u32 ipehr) { struct drm_i915_private *dev_priv = ring->dev->dev_private; - struct intel_ring_buffer *signaller; + struct intel_engine_cs *signaller; int i; if (INTEL_INFO(dev_priv->dev)->gen >= 8) { @@ -2606,8 +2811,8 @@ semaphore_wait_to_signaller_ring(struct intel_ring_buffer *ring, u32 ipehr) return NULL; } -static struct intel_ring_buffer * -semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) +static struct intel_engine_cs * +semaphore_waits_for(struct intel_engine_cs *ring, u32 *seqno) { struct drm_i915_private *dev_priv = ring->dev->dev_private; u32 cmd, ipehr, head; @@ -2632,10 +2837,10 @@ semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) * our ring is smaller than what the hardware (and hence * HEAD_ADDR) allows. Also handles wrap-around. */ - head &= ring->size - 1; + head &= ring->buffer->size - 1; /* This here seems to blow up */ - cmd = ioread32(ring->virtual_start + head); + cmd = ioread32(ring->buffer->virtual_start + head); if (cmd == ipehr) break; @@ -2645,14 +2850,14 @@ semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno) if (!i) return NULL; - *seqno = ioread32(ring->virtual_start + head + 4) + 1; + *seqno = ioread32(ring->buffer->virtual_start + head + 4) + 1; return semaphore_wait_to_signaller_ring(ring, ipehr); } -static int semaphore_passed(struct intel_ring_buffer *ring) +static int semaphore_passed(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; - struct intel_ring_buffer *signaller; + struct intel_engine_cs *signaller; u32 seqno, ctl; ring->hangcheck.deadlock = true; @@ -2671,7 +2876,7 @@ static int semaphore_passed(struct intel_ring_buffer *ring) static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv) { - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; for_each_ring(ring, dev_priv, i) @@ -2679,7 +2884,7 @@ static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv) } static enum intel_ring_hangcheck_action -ring_stuck(struct intel_ring_buffer *ring, u64 acthd) +ring_stuck(struct intel_engine_cs *ring, u64 acthd) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2735,7 +2940,7 @@ static void i915_hangcheck_elapsed(unsigned long data) { struct drm_device *dev = (struct drm_device *)data; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; int i; int busy_count = 0, rings_hung = 0; bool stuck[I915_NUM_RINGS] = { 0 }; @@ -2974,6 +3179,37 @@ static void gen8_irq_preinstall(struct drm_device *dev) gen8_irq_reset(dev); } +static void cherryview_irq_preinstall(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe; + + I915_WRITE(GEN8_MASTER_IRQ, 0); + POSTING_READ(GEN8_MASTER_IRQ); + + GEN8_IRQ_RESET_NDX(GT, 0); + GEN8_IRQ_RESET_NDX(GT, 1); + GEN8_IRQ_RESET_NDX(GT, 2); + GEN8_IRQ_RESET_NDX(GT, 3); + + GEN5_IRQ_RESET(GEN8_PCU_); + + POSTING_READ(GEN8_PCU_IIR); + + I915_WRITE(DPINVGTT, DPINVGTT_STATUS_MASK_CHV); + + I915_WRITE(PORT_HOTPLUG_EN, 0); + I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); + + for_each_pipe(pipe) + I915_WRITE(PIPESTAT(pipe), 0xffff); + + I915_WRITE(VLV_IMR, 0xffffffff); + I915_WRITE(VLV_IER, 0x0); + I915_WRITE(VLV_IIR, 0xffffffff); + POSTING_READ(VLV_IIR); +} + static void ibx_hpd_irq_setup(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3252,6 +3488,8 @@ static void gen8_gt_irq_postinstall(struct drm_i915_private *dev_priv) for (i = 0; i < ARRAY_SIZE(gt_interrupts); i++) GEN8_IRQ_INIT_NDX(GT, i, ~gt_interrupts[i], gt_interrupts[i]); + + dev_priv->pm_irq_mask = 0xffffffff; } static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) @@ -3291,6 +3529,45 @@ static int gen8_irq_postinstall(struct drm_device *dev) return 0; } +static int cherryview_irq_postinstall(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 enable_mask = I915_DISPLAY_PORT_INTERRUPT | + I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | + I915_DISPLAY_PIPE_B_EVENT_INTERRUPT | + I915_DISPLAY_PIPE_C_EVENT_INTERRUPT; + u32 pipestat_enable = PLANE_FLIP_DONE_INT_STATUS_VLV | + PIPE_CRC_DONE_INTERRUPT_STATUS; + unsigned long irqflags; + int pipe; + + /* + * Leave vblank interrupts masked initially. enable/disable will + * toggle them based on usage. + */ + dev_priv->irq_mask = ~enable_mask; + + for_each_pipe(pipe) + I915_WRITE(PIPESTAT(pipe), 0xffff); + + spin_lock_irqsave(&dev_priv->irq_lock, irqflags); + i915_enable_pipestat(dev_priv, PIPE_A, PIPE_GMBUS_INTERRUPT_STATUS); + for_each_pipe(pipe) + i915_enable_pipestat(dev_priv, pipe, pipestat_enable); + spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); + + I915_WRITE(VLV_IIR, 0xffffffff); + I915_WRITE(VLV_IMR, dev_priv->irq_mask); + I915_WRITE(VLV_IER, enable_mask); + + gen8_gt_irq_postinstall(dev_priv); + + I915_WRITE(GEN8_MASTER_IRQ, MASTER_INTERRUPT_ENABLE); + POSTING_READ(GEN8_MASTER_IRQ); + + return 0; +} + static void gen8_irq_uninstall(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3336,6 +3613,57 @@ static void valleyview_irq_uninstall(struct drm_device *dev) POSTING_READ(VLV_IER); } +static void cherryview_irq_uninstall(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe; + + if (!dev_priv) + return; + + I915_WRITE(GEN8_MASTER_IRQ, 0); + POSTING_READ(GEN8_MASTER_IRQ); + +#define GEN8_IRQ_FINI_NDX(type, which) \ +do { \ + I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \ + I915_WRITE(GEN8_##type##_IER(which), 0); \ + I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \ + POSTING_READ(GEN8_##type##_IIR(which)); \ + I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \ +} while (0) + +#define GEN8_IRQ_FINI(type) \ +do { \ + I915_WRITE(GEN8_##type##_IMR, 0xffffffff); \ + I915_WRITE(GEN8_##type##_IER, 0); \ + I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \ + POSTING_READ(GEN8_##type##_IIR); \ + I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \ +} while (0) + + GEN8_IRQ_FINI_NDX(GT, 0); + GEN8_IRQ_FINI_NDX(GT, 1); + GEN8_IRQ_FINI_NDX(GT, 2); + GEN8_IRQ_FINI_NDX(GT, 3); + + GEN8_IRQ_FINI(PCU); + +#undef GEN8_IRQ_FINI +#undef GEN8_IRQ_FINI_NDX + + I915_WRITE(PORT_HOTPLUG_EN, 0); + I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT)); + + for_each_pipe(pipe) + I915_WRITE(PIPESTAT(pipe), 0xffff); + + I915_WRITE(VLV_IMR, 0xffffffff); + I915_WRITE(VLV_IER, 0x0); + I915_WRITE(VLV_IIR, 0xffffffff); + POSTING_READ(VLV_IIR); +} + static void ironlake_irq_uninstall(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3427,7 +3755,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev, static irqreturn_t i8xx_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u16 iir, new_iir; u32 pipe_stats[2]; @@ -3612,7 +3940,7 @@ static bool i915_handle_vblank(struct drm_device *dev, static irqreturn_t i915_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u32 iir, new_iir, pipe_stats[I915_MAX_PIPES]; unsigned long irqflags; @@ -3842,7 +4170,7 @@ static void i915_hpd_irq_setup(struct drm_device *dev) static irqreturn_t i965_irq_handler(int irq, void *arg) { - struct drm_device *dev = (struct drm_device *) arg; + struct drm_device *dev = arg; struct drm_i915_private *dev_priv = dev->dev_private; u32 iir, new_iir; u32 pipe_stats[I915_MAX_PIPES]; @@ -4041,7 +4369,15 @@ void intel_irq_init(struct drm_device *dev) dev->driver->get_scanout_position = i915_get_crtc_scanoutpos; } - if (IS_VALLEYVIEW(dev)) { + if (IS_CHERRYVIEW(dev)) { + dev->driver->irq_handler = cherryview_irq_handler; + dev->driver->irq_preinstall = cherryview_irq_preinstall; + dev->driver->irq_postinstall = cherryview_irq_postinstall; + dev->driver->irq_uninstall = cherryview_irq_uninstall; + dev->driver->enable_vblank = valleyview_enable_vblank; + dev->driver->disable_vblank = valleyview_disable_vblank; + dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup; + } else if (IS_VALLEYVIEW(dev)) { dev->driver->irq_handler = valleyview_irq_handler; dev->driver->irq_preinstall = valleyview_irq_preinstall; dev->driver->irq_postinstall = valleyview_irq_postinstall; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0eff337a5720..5122254e7213 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -29,6 +29,8 @@ #define _TRANSCODER(tran, a, b) ((a) + (tran)*((b)-(a))) #define _PORT(port, a, b) ((a) + (port)*((b)-(a))) +#define _PIPE3(pipe, a, b, c) (pipe < 2 ? _PIPE(pipe, a, b) : c) +#define _PORT3(port, a, b, c) (port < 2 ? _PORT(port, a, b) : c) #define _MASKED_BIT_ENABLE(a) (((a) << 16) | (a)) #define _MASKED_BIT_DISABLE(a) ((a) << 16) @@ -77,13 +79,19 @@ /* Graphics reset regs */ #define I965_GDRST 0xc0 /* PCI config register */ -#define ILK_GDSR 0x2ca4 /* MCHBAR offset */ #define GRDOM_FULL (0<<2) #define GRDOM_RENDER (1<<2) #define GRDOM_MEDIA (3<<2) #define GRDOM_MASK (3<<2) #define GRDOM_RESET_ENABLE (1<<0) +#define ILK_GDSR 0x2ca4 /* MCHBAR offset */ +#define ILK_GRDOM_FULL (0<<1) +#define ILK_GRDOM_RENDER (1<<1) +#define ILK_GRDOM_MEDIA (3<<1) +#define ILK_GRDOM_MASK (3<<1) +#define ILK_GRDOM_RESET_ENABLE (1<<0) + #define GEN6_MBCUNIT_SNPCR 0x900c /* for LLC config */ #define GEN6_MBC_SNPCR_SHIFT 21 #define GEN6_MBC_SNPCR_MASK (3<<21) @@ -92,6 +100,9 @@ #define GEN6_MBC_SNPCR_LOW (2<<21) #define GEN6_MBC_SNPCR_MIN (3<<21) /* only 1/16th of the cache is shared */ +#define VLV_G3DCTL 0x9024 +#define VLV_GSCKGCTL 0x9028 + #define GEN6_MBCTL 0x0907c #define GEN6_MBCTL_ENABLE_BOOT_FETCH (1 << 4) #define GEN6_MBCTL_CTX_FETCH_NEEDED (1 << 3) @@ -467,6 +478,7 @@ #define IOSF_PORT_PUNIT 0x4 #define IOSF_PORT_NC 0x11 #define IOSF_PORT_DPIO 0x12 +#define IOSF_PORT_DPIO_2 0x1a #define IOSF_PORT_GPIO_NC 0x13 #define IOSF_PORT_CCK 0x14 #define IOSF_PORT_CCU 0xA9 @@ -478,9 +490,6 @@ /* See configdb bunit SB addr map */ #define BUNIT_REG_BISOC 0x11 -#define PUNIT_OPCODE_REG_READ 6 -#define PUNIT_OPCODE_REG_WRITE 7 - #define PUNIT_REG_DSPFREQ 0x36 #define DSPFREQSTAT_SHIFT 30 #define DSPFREQSTAT_MASK (0x3 << DSPFREQSTAT_SHIFT) @@ -566,16 +575,91 @@ enum punit_power_well { #define DSI_PLL_M1_DIV_MASK (0x1ff << 0) #define CCK_DISPLAY_CLOCK_CONTROL 0x6b -/* - * DPIO - a special bus for various display related registers to hide behind +/** + * DOC: DPIO + * + * VLV and CHV have slightly peculiar display PHYs for driving DP/HDMI + * ports. DPIO is the name given to such a display PHY. These PHYs + * don't follow the standard programming model using direct MMIO + * registers, and instead their registers must be accessed trough IOSF + * sideband. VLV has one such PHY for driving ports B and C, and CHV + * adds another PHY for driving port D. Each PHY responds to specific + * IOSF-SB port. + * + * Each display PHY is made up of one or two channels. Each channel + * houses a common lane part which contains the PLL and other common + * logic. CH0 common lane also contains the IOSF-SB logic for the + * Common Register Interface (CRI) ie. the DPIO registers. CRI clock + * must be running when any DPIO registers are accessed. + * + * In addition to having their own registers, the PHYs are also + * controlled through some dedicated signals from the display + * controller. These include PLL reference clock enable, PLL enable, + * and CRI clock selection, for example. + * + * Eeach channel also has two splines (also called data lanes), and + * each spline is made up of one Physical Access Coding Sub-Layer + * (PCS) block and two TX lanes. So each channel has two PCS blocks + * and four TX lanes. The TX lanes are used as DP lanes or TMDS + * data/clock pairs depending on the output type. + * + * Additionally the PHY also contains an AUX lane with AUX blocks + * for each channel. This is used for DP AUX communication, but + * this fact isn't really relevant for the driver since AUX is + * controlled from the display controller side. No DPIO registers + * need to be accessed during AUX communication, + * + * Generally the common lane corresponds to the pipe and + * the spline (PCS/TX) correponds to the port. + * + * For dual channel PHY (VLV/CHV): * - * DPIO is VLV only. + * pipe A == CMN/PLL/REF CH0 * - * Note: digital port B is DDI0, digital pot C is DDI1 + * pipe B == CMN/PLL/REF CH1 + * + * port B == PCS/TX CH0 + * + * port C == PCS/TX CH1 + * + * This is especially important when we cross the streams + * ie. drive port B with pipe B, or port C with pipe A. + * + * For single channel PHY (CHV): + * + * pipe C == CMN/PLL/REF CH0 + * + * port D == PCS/TX CH0 + * + * Note: digital port B is DDI0, digital port C is DDI1, + * digital port D is DDI2 + */ +/* + * Dual channel PHY (VLV/CHV) + * --------------------------------- + * | CH0 | CH1 | + * | CMN/PLL/REF | CMN/PLL/REF | + * |---------------|---------------| Display PHY + * | PCS01 | PCS23 | PCS01 | PCS23 | + * |-------|-------|-------|-------| + * |TX0|TX1|TX2|TX3|TX0|TX1|TX2|TX3| + * --------------------------------- + * | DDI0 | DDI1 | DP/HDMI ports + * --------------------------------- + * + * Single channel PHY (CHV) + * ----------------- + * | CH0 | + * | CMN/PLL/REF | + * |---------------| Display PHY + * | PCS01 | PCS23 | + * |-------|-------| + * |TX0|TX1|TX2|TX3| + * ----------------- + * | DDI2 | DP/HDMI port + * ----------------- */ #define DPIO_DEVFN 0 -#define DPIO_OPCODE_REG_WRITE 1 -#define DPIO_OPCODE_REG_READ 0 #define DPIO_CTL (VLV_DISPLAY_BASE + 0x2110) #define DPIO_MODSEL1 (1<<3) /* if ref clk b == 27 */ @@ -652,14 +736,29 @@ enum punit_power_well { #define DPIO_PCS_TX_LANE1_RESET (1<<7) #define VLV_PCS_DW0(ch) _PORT(ch, _VLV_PCS_DW0_CH0, _VLV_PCS_DW0_CH1) +#define _VLV_PCS01_DW0_CH0 0x200 +#define _VLV_PCS23_DW0_CH0 0x400 +#define _VLV_PCS01_DW0_CH1 0x2600 +#define _VLV_PCS23_DW0_CH1 0x2800 +#define VLV_PCS01_DW0(ch) _PORT(ch, _VLV_PCS01_DW0_CH0, _VLV_PCS01_DW0_CH1) +#define VLV_PCS23_DW0(ch) _PORT(ch, _VLV_PCS23_DW0_CH0, _VLV_PCS23_DW0_CH1) + #define _VLV_PCS_DW1_CH0 0x8204 #define _VLV_PCS_DW1_CH1 0x8404 +#define CHV_PCS_REQ_SOFTRESET_EN (1<<23) #define DPIO_PCS_CLK_CRI_RXEB_EIOS_EN (1<<22) #define DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN (1<<21) #define DPIO_PCS_CLK_DATAWIDTH_SHIFT (6) #define DPIO_PCS_CLK_SOFT_RESET (1<<5) #define VLV_PCS_DW1(ch) _PORT(ch, _VLV_PCS_DW1_CH0, _VLV_PCS_DW1_CH1) +#define _VLV_PCS01_DW1_CH0 0x204 +#define _VLV_PCS23_DW1_CH0 0x404 +#define _VLV_PCS01_DW1_CH1 0x2604 +#define _VLV_PCS23_DW1_CH1 0x2804 +#define VLV_PCS01_DW1(ch) _PORT(ch, _VLV_PCS01_DW1_CH0, _VLV_PCS01_DW1_CH1) +#define VLV_PCS23_DW1(ch) _PORT(ch, _VLV_PCS23_DW1_CH0, _VLV_PCS23_DW1_CH1) + #define _VLV_PCS_DW8_CH0 0x8220 #define _VLV_PCS_DW8_CH1 0x8420 #define VLV_PCS_DW8(ch) _PORT(ch, _VLV_PCS_DW8_CH0, _VLV_PCS_DW8_CH1) @@ -675,6 +774,19 @@ enum punit_power_well { #define _VLV_PCS_DW9_CH1 0x8424 #define VLV_PCS_DW9(ch) _PORT(ch, _VLV_PCS_DW9_CH0, _VLV_PCS_DW9_CH1) +#define _CHV_PCS_DW10_CH0 0x8228 +#define _CHV_PCS_DW10_CH1 0x8428 +#define DPIO_PCS_SWING_CALC_TX0_TX2 (1<<30) +#define DPIO_PCS_SWING_CALC_TX1_TX3 (1<<31) +#define CHV_PCS_DW10(ch) _PORT(ch, _CHV_PCS_DW10_CH0, _CHV_PCS_DW10_CH1) + +#define _VLV_PCS01_DW10_CH0 0x0228 +#define _VLV_PCS23_DW10_CH0 0x0428 +#define _VLV_PCS01_DW10_CH1 0x2628 +#define _VLV_PCS23_DW10_CH1 0x2828 +#define VLV_PCS01_DW10(port) _PORT(port, _VLV_PCS01_DW10_CH0, _VLV_PCS01_DW10_CH1) +#define VLV_PCS23_DW10(port) _PORT(port, _VLV_PCS23_DW10_CH0, _VLV_PCS23_DW10_CH1) + #define _VLV_PCS_DW11_CH0 0x822c #define _VLV_PCS_DW11_CH1 0x842c #define VLV_PCS_DW11(ch) _PORT(ch, _VLV_PCS_DW11_CH0, _VLV_PCS_DW11_CH1) @@ -693,14 +805,21 @@ enum punit_power_well { #define _VLV_TX_DW2_CH0 0x8288 #define _VLV_TX_DW2_CH1 0x8488 +#define DPIO_SWING_MARGIN_SHIFT 16 +#define DPIO_SWING_MARGIN_MASK (0xff << DPIO_SWING_MARGIN_SHIFT) +#define DPIO_UNIQ_TRANS_SCALE_SHIFT 8 #define VLV_TX_DW2(ch) _PORT(ch, _VLV_TX_DW2_CH0, _VLV_TX_DW2_CH1) #define _VLV_TX_DW3_CH0 0x828c #define _VLV_TX_DW3_CH1 0x848c +/* The following bit for CHV phy */ +#define DPIO_TX_UNIQ_TRANS_SCALE_EN (1<<27) #define VLV_TX_DW3(ch) _PORT(ch, _VLV_TX_DW3_CH0, _VLV_TX_DW3_CH1) #define _VLV_TX_DW4_CH0 0x8290 #define _VLV_TX_DW4_CH1 0x8490 +#define DPIO_SWING_DEEMPH9P5_SHIFT 24 +#define DPIO_SWING_DEEMPH9P5_MASK (0xff << DPIO_SWING_DEEMPH9P5_SHIFT) #define VLV_TX_DW4(ch) _PORT(ch, _VLV_TX_DW4_CH0, _VLV_TX_DW4_CH1) #define _VLV_TX3_DW4_CH0 0x690 @@ -720,6 +839,73 @@ enum punit_power_well { #define _VLV_TX_DW14_CH1 0x84b8 #define VLV_TX_DW14(ch) _PORT(ch, _VLV_TX_DW14_CH0, _VLV_TX_DW14_CH1) +/* CHV dpPhy registers */ +#define _CHV_PLL_DW0_CH0 0x8000 +#define _CHV_PLL_DW0_CH1 0x8180 +#define CHV_PLL_DW0(ch) _PIPE(ch, _CHV_PLL_DW0_CH0, _CHV_PLL_DW0_CH1) + +#define _CHV_PLL_DW1_CH0 0x8004 +#define _CHV_PLL_DW1_CH1 0x8184 +#define DPIO_CHV_N_DIV_SHIFT 8 +#define DPIO_CHV_M1_DIV_BY_2 (0 << 0) +#define CHV_PLL_DW1(ch) _PIPE(ch, _CHV_PLL_DW1_CH0, _CHV_PLL_DW1_CH1) + +#define _CHV_PLL_DW2_CH0 0x8008 +#define _CHV_PLL_DW2_CH1 0x8188 +#define CHV_PLL_DW2(ch) _PIPE(ch, _CHV_PLL_DW2_CH0, _CHV_PLL_DW2_CH1) + +#define _CHV_PLL_DW3_CH0 0x800c +#define _CHV_PLL_DW3_CH1 0x818c +#define DPIO_CHV_FRAC_DIV_EN (1 << 16) +#define DPIO_CHV_FIRST_MOD (0 << 8) +#define DPIO_CHV_SECOND_MOD (1 << 8) +#define DPIO_CHV_FEEDFWD_GAIN_SHIFT 0 +#define CHV_PLL_DW3(ch) _PIPE(ch, _CHV_PLL_DW3_CH0, _CHV_PLL_DW3_CH1) + +#define _CHV_PLL_DW6_CH0 0x8018 +#define _CHV_PLL_DW6_CH1 0x8198 +#define DPIO_CHV_GAIN_CTRL_SHIFT 16 +#define DPIO_CHV_INT_COEFF_SHIFT 8 +#define DPIO_CHV_PROP_COEFF_SHIFT 0 +#define CHV_PLL_DW6(ch) _PIPE(ch, _CHV_PLL_DW6_CH0, _CHV_PLL_DW6_CH1) + +#define _CHV_CMN_DW13_CH0 0x8134 +#define _CHV_CMN_DW0_CH1 0x8080 +#define DPIO_CHV_S1_DIV_SHIFT 21 +#define DPIO_CHV_P1_DIV_SHIFT 13 /* 3 bits */ +#define DPIO_CHV_P2_DIV_SHIFT 8 /* 5 bits */ +#define DPIO_CHV_K_DIV_SHIFT 4 +#define DPIO_PLL_FREQLOCK (1 << 1) +#define DPIO_PLL_LOCK (1 << 0) +#define CHV_CMN_DW13(ch) _PIPE(ch, _CHV_CMN_DW13_CH0, _CHV_CMN_DW0_CH1) + +#define _CHV_CMN_DW14_CH0 0x8138 +#define _CHV_CMN_DW1_CH1 0x8084 +#define DPIO_AFC_RECAL (1 << 14) +#define DPIO_DCLKP_EN (1 << 13) +#define CHV_CMN_DW14(ch) _PIPE(ch, _CHV_CMN_DW14_CH0, _CHV_CMN_DW1_CH1) + +#define CHV_CMN_DW30 0x8178 +#define DPIO_LRC_BYPASS (1 << 3) + +#define _TXLANE(ch, lane, offset) ((ch ? 0x2400 : 0) + \ + (lane) * 0x200 + (offset)) + +#define CHV_TX_DW0(ch, lane) _TXLANE(ch, lane, 0x80) +#define CHV_TX_DW1(ch, lane) _TXLANE(ch, lane, 0x84) +#define CHV_TX_DW2(ch, lane) _TXLANE(ch, lane, 0x88) +#define CHV_TX_DW3(ch, lane) _TXLANE(ch, lane, 0x8c) +#define CHV_TX_DW4(ch, lane) _TXLANE(ch, lane, 0x90) +#define CHV_TX_DW5(ch, lane) _TXLANE(ch, lane, 0x94) +#define CHV_TX_DW6(ch, lane) _TXLANE(ch, lane, 0x98) +#define CHV_TX_DW7(ch, lane) _TXLANE(ch, lane, 0x9c) +#define CHV_TX_DW8(ch, lane) _TXLANE(ch, lane, 0xa0) +#define CHV_TX_DW9(ch, lane) _TXLANE(ch, lane, 0xa4) +#define CHV_TX_DW10(ch, lane) _TXLANE(ch, lane, 0xa8) +#define CHV_TX_DW11(ch, lane) _TXLANE(ch, lane, 0xac) +#define DPIO_FRC_LATENCY_SHFIT 8 +#define CHV_TX_DW14(ch, lane) _TXLANE(ch, lane, 0xb8) +#define DPIO_UPAR_SHIFT 30 /* * Fence registers */ @@ -786,9 +972,20 @@ enum punit_power_well { #define RING_MAX_IDLE(base) ((base)+0x54) #define RING_HWS_PGA(base) ((base)+0x80) #define RING_HWS_PGA_GEN6(base) ((base)+0x2080) -#define ARB_MODE 0x04030 + +#define GEN7_WR_WATERMARK 0x4028 +#define GEN7_GFX_PRIO_CTRL 0x402C +#define ARB_MODE 0x4030 #define ARB_MODE_SWIZZLE_SNB (1<<4) #define ARB_MODE_SWIZZLE_IVB (1<<5) +#define GEN7_GFX_PEND_TLB0 0x4034 +#define GEN7_GFX_PEND_TLB1 0x4038 +/* L3, CVS, ZTLB, RCC, CASC LRA min, max values */ +#define GEN7_LRA_LIMITS_BASE 0x403C +#define GEN7_LRA_LIMITS_REG_NUM 13 +#define GEN7_MEDIA_MAX_REQ_COUNT 0x4070 +#define GEN7_GFX_MAX_REQ_COUNT 0x4074 + #define GAMTARBMODE 0x04a08 #define ARB_MODE_BWGTLB_DISABLE (1<<9) #define ARB_MODE_SWIZZLE_BDW (1<<1) @@ -823,6 +1020,9 @@ enum punit_power_well { #define RING_WAIT_I8XX (1<<0) /* gen2, PRBx_HEAD */ #define RING_WAIT (1<<11) /* gen3+, PRBx_CTL */ #define RING_WAIT_SEMAPHORE (1<<10) /* gen6+ */ + +#define GEN7_TLB_RD_ADDR 0x4700 + #if 0 #define PRB0_TAIL 0x02030 #define PRB0_HEAD 0x02034 @@ -948,14 +1148,19 @@ enum punit_power_well { #define GFX_PPGTT_ENABLE (1<<9) #define VLV_DISPLAY_BASE 0x180000 +#define VLV_MIPI_BASE VLV_DISPLAY_BASE +#define VLV_GU_CTL0 (VLV_DISPLAY_BASE + 0x2030) +#define VLV_GU_CTL1 (VLV_DISPLAY_BASE + 0x2034) #define SCPD0 0x0209c /* 915+ only */ #define IER 0x020a0 #define IIR 0x020a4 #define IMR 0x020a8 #define ISR 0x020ac #define VLV_GUNIT_CLOCK_GATE (VLV_DISPLAY_BASE + 0x2060) +#define GINT_DIS (1<<22) #define GCFG_DIS (1<<8) +#define VLV_GUNIT_CLOCK_GATE2 (VLV_DISPLAY_BASE + 0x2064) #define VLV_IIR_RW (VLV_DISPLAY_BASE + 0x2084) #define VLV_IER (VLV_DISPLAY_BASE + 0x20a0) #define VLV_IIR (VLV_DISPLAY_BASE + 0x20a4) @@ -1084,6 +1289,7 @@ enum punit_power_well { #define GEN6_RC_SLEEP_PSMI_CONTROL 0x2050 #define GEN8_RC_SEMA_IDLE_MSG_DISABLE (1 << 12) +#define GEN8_FF_DOP_CLOCK_GATE_DISABLE (1<<10) #define GEN6_BSD_SLEEP_PSMI_CONTROL 0x12050 #define GEN6_BSD_SLEEP_MSG_DISABLE (1 << 0) @@ -1124,24 +1330,43 @@ enum punit_power_well { /* These are all the "old" interrupts */ #define ILK_BSD_USER_INTERRUPT (1<<5) + +#define I915_PM_INTERRUPT (1<<31) +#define I915_ISP_INTERRUPT (1<<22) +#define I915_LPE_PIPE_B_INTERRUPT (1<<21) +#define I915_LPE_PIPE_A_INTERRUPT (1<<20) +#define I915_MIPIB_INTERRUPT (1<<19) +#define I915_MIPIA_INTERRUPT (1<<18) #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT (1<<18) #define I915_DISPLAY_PORT_INTERRUPT (1<<17) +#define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT (1<<16) +#define I915_MASTER_ERROR_INTERRUPT (1<<15) #define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT (1<<15) +#define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT (1<<14) #define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT (1<<14) /* p-state */ +#define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT (1<<13) #define I915_HWB_OOM_INTERRUPT (1<<13) +#define I915_LPE_PIPE_C_INTERRUPT (1<<12) #define I915_SYNC_STATUS_INTERRUPT (1<<12) +#define I915_MISC_INTERRUPT (1<<11) #define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT (1<<11) +#define I915_DISPLAY_PIPE_C_VBLANK_INTERRUPT (1<<10) #define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT (1<<10) +#define I915_DISPLAY_PIPE_C_EVENT_INTERRUPT (1<<9) #define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT (1<<9) +#define I915_DISPLAY_PIPE_C_DPBM_INTERRUPT (1<<8) #define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT (1<<8) #define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT (1<<7) #define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT (1<<6) #define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT (1<<5) #define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT (1<<4) +#define I915_DISPLAY_PIPE_A_DPBM_INTERRUPT (1<<3) +#define I915_DISPLAY_PIPE_B_DPBM_INTERRUPT (1<<2) #define I915_DEBUG_INTERRUPT (1<<2) +#define I915_WINVALID_INTERRUPT (1<<1) #define I915_USER_INTERRUPT (1<<1) #define I915_ASLE_INTERRUPT (1<<0) -#define I915_BSD_USER_INTERRUPT (1 << 25) +#define I915_BSD_USER_INTERRUPT (1<<25) #define GEN6_BSD_RNCID 0x12198 @@ -1298,6 +1523,7 @@ enum punit_power_well { #define GMBUS_PORT_SSC 1 #define GMBUS_PORT_VGADDC 2 #define GMBUS_PORT_PANEL 3 +#define GMBUS_PORT_DPD_CHV 3 /* HDMID_CHV */ #define GMBUS_PORT_DPC 4 /* HDMIC */ #define GMBUS_PORT_DPB 5 /* SDVO, HDMIB */ #define GMBUS_PORT_DPD 6 /* HDMID */ @@ -1339,6 +1565,7 @@ enum punit_power_well { */ #define DPLL_A_OFFSET 0x6014 #define DPLL_B_OFFSET 0x6018 +#define CHV_DPLL_C_OFFSET 0x6030 #define DPLL(pipe) (dev_priv->info.dpll_offsets[pipe] + \ dev_priv->info.display_mmio_offset) @@ -1373,10 +1600,23 @@ enum punit_power_well { #define DPLL_LOCK_VLV (1<<15) #define DPLL_INTEGRATED_CRI_CLK_VLV (1<<14) #define DPLL_INTEGRATED_CLOCK_VLV (1<<13) +#define DPLL_SSC_REF_CLOCK_CHV (1<<13) #define DPLL_PORTC_READY_MASK (0xf << 4) #define DPLL_PORTB_READY_MASK (0xf) #define DPLL_FPA01_P1_POST_DIV_MASK_I830 0x001f0000 + +/* Additional CHV pll/phy registers */ +#define DPIO_PHY_STATUS (VLV_DISPLAY_BASE + 0x6240) +#define DPLL_PORTD_READY_MASK (0xf) +#define DISPLAY_PHY_CONTROL (VLV_DISPLAY_BASE + 0x60100) +#define PHY_COM_LANE_RESET_DEASSERT(phy, val) \ + ((phy == DPIO_PHY0) ? (val | 1) : (val | 2)) +#define PHY_COM_LANE_RESET_ASSERT(phy, val) \ + ((phy == DPIO_PHY0) ? (val & ~1) : (val & ~2)) +#define DISPLAY_PHY_STATUS (VLV_DISPLAY_BASE + 0x60104) +#define PHY_POWERGOOD(phy) ((phy == DPIO_PHY0) ? (1<<31) : (1<<30)) + /* * The i830 generation, in LVDS mode, defines P1 as the bit number set within * this field (only one bit may be set). @@ -1417,6 +1657,7 @@ enum punit_power_well { #define DPLL_A_MD_OFFSET 0x601c /* 965+ only */ #define DPLL_B_MD_OFFSET 0x6020 /* 965+ only */ +#define CHV_DPLL_C_MD_OFFSET 0x603c #define DPLL_MD(pipe) (dev_priv->info.dpll_md_offsets[pipe] + \ dev_priv->info.display_mmio_offset) @@ -1516,7 +1757,7 @@ enum punit_power_well { # define DPIOUNIT_CLOCK_GATE_DISABLE (1 << 6) /* 915-945 */ # define OVFUNIT_CLOCK_GATE_DISABLE (1 << 5) # define OVBUNIT_CLOCK_GATE_DISABLE (1 << 4) -/** +/* * This bit must be set on the 830 to prevent hangs when turning off the * overlay scaler. */ @@ -1536,12 +1777,12 @@ enum punit_power_well { # define COLOR_CALCULATOR_CLOCK_GATE_DISABLE (1 << 7) # define MOTION_COMP_CLOCK_GATE_DISABLE (1 << 6) # define MAG_CLOCK_GATE_DISABLE (1 << 5) -/** This bit must be unset on 855,865 */ +/* This bit must be unset on 855,865 */ # define MECI_CLOCK_GATE_DISABLE (1 << 4) # define DCMP_CLOCK_GATE_DISABLE (1 << 3) # define MEC_CLOCK_GATE_DISABLE (1 << 2) # define MECO_CLOCK_GATE_DISABLE (1 << 1) -/** This bit must be set on 855,865. */ +/* This bit must be set on 855,865. */ # define SV_CLOCK_GATE_DISABLE (1 << 0) # define I915_MPEG_CLOCK_GATE_DISABLE (1 << 16) # define I915_VLD_IP_PR_CLOCK_GATE_DISABLE (1 << 15) @@ -1562,14 +1803,14 @@ enum punit_power_well { # define I915_BY_CLOCK_GATE_DISABLE (1 << 0) # define I965_RCZ_CLOCK_GATE_DISABLE (1 << 30) -/** This bit must always be set on 965G/965GM */ +/* This bit must always be set on 965G/965GM */ # define I965_RCC_CLOCK_GATE_DISABLE (1 << 29) # define I965_RCPB_CLOCK_GATE_DISABLE (1 << 28) # define I965_DAP_CLOCK_GATE_DISABLE (1 << 27) # define I965_ROC_CLOCK_GATE_DISABLE (1 << 26) # define I965_GW_CLOCK_GATE_DISABLE (1 << 25) # define I965_TD_CLOCK_GATE_DISABLE (1 << 24) -/** This bit must always be set on 965G */ +/* This bit must always be set on 965G */ # define I965_ISC_CLOCK_GATE_DISABLE (1 << 23) # define I965_IC_CLOCK_GATE_DISABLE (1 << 22) # define I965_EU_CLOCK_GATE_DISABLE (1 << 21) @@ -1594,6 +1835,10 @@ enum punit_power_well { #define VF_UNIT_CLOCK_GATE_DISABLE (1 << 9) #define GS_UNIT_CLOCK_GATE_DISABLE (1 << 7) #define CL_UNIT_CLOCK_GATE_DISABLE (1 << 6) + +#define VDECCLK_GATE_D 0x620C /* g4x only */ +#define VCP_UNIT_CLOCK_GATE_DISABLE (1 << 4) + #define RAMCLK_GATE_D 0x6210 /* CRL only */ #define DEUC 0x6214 /* CRL only */ @@ -1613,6 +1858,7 @@ enum punit_power_well { */ #define PALETTE_A_OFFSET 0xa000 #define PALETTE_B_OFFSET 0xa800 +#define CHV_PALETTE_C_OFFSET 0xc000 #define PALETTE(pipe) (dev_priv->info.palette_offsets[pipe] + \ dev_priv->info.display_mmio_offset) @@ -1635,7 +1881,7 @@ enum punit_power_well { /* Memory controller frequency in MCHBAR for Haswell (possible SNB+) */ #define DCLK (MCHBAR_MIRROR_BASE_SNB + 0x5e04) -/** 915-945 and GM965 MCH register controlling DRAM channel access */ +/* 915-945 and GM965 MCH register controlling DRAM channel access */ #define DCC 0x10200 #define DCC_ADDRESSING_MODE_SINGLE_CHANNEL (0 << 0) #define DCC_ADDRESSING_MODE_DUAL_CHANNEL_ASYMMETRIC (1 << 0) @@ -1644,15 +1890,15 @@ enum punit_power_well { #define DCC_CHANNEL_XOR_DISABLE (1 << 10) #define DCC_CHANNEL_XOR_BIT_17 (1 << 9) -/** Pineview MCH register contains DDR3 setting */ +/* Pineview MCH register contains DDR3 setting */ #define CSHRDDR3CTL 0x101a8 #define CSHRDDR3CTL_DDR3 (1 << 2) -/** 965 MCH register controlling DRAM channel configuration */ +/* 965 MCH register controlling DRAM channel configuration */ #define C0DRB3 0x10206 #define C1DRB3 0x10606 -/** snb MCH registers for reading the DRAM channel configuration */ +/* snb MCH registers for reading the DRAM channel configuration */ #define MAD_DIMM_C0 (MCHBAR_MIRROR_BASE_SNB + 0x5004) #define MAD_DIMM_C1 (MCHBAR_MIRROR_BASE_SNB + 0x5008) #define MAD_DIMM_C2 (MCHBAR_MIRROR_BASE_SNB + 0x500C) @@ -1674,7 +1920,7 @@ enum punit_power_well { #define MAD_DIMM_A_SIZE_SHIFT 0 #define MAD_DIMM_A_SIZE_MASK (0xff << MAD_DIMM_A_SIZE_SHIFT) -/** snb MCH registers for priority tuning */ +/* snb MCH registers for priority tuning */ #define MCH_SSKPD (MCHBAR_MIRROR_BASE_SNB + 0x5d10) #define MCH_SSKPD_WM0_MASK 0x3f #define MCH_SSKPD_WM0_VAL 0xc @@ -2102,6 +2348,7 @@ enum punit_power_well { #define TRANSCODER_A_OFFSET 0x60000 #define TRANSCODER_B_OFFSET 0x61000 #define TRANSCODER_C_OFFSET 0x62000 +#define CHV_TRANSCODER_C_OFFSET 0x63000 #define TRANSCODER_EDP_OFFSET 0x6f000 #define _TRANSCODER2(pipe, reg) (dev_priv->info.trans_offsets[(pipe)] - \ @@ -2326,6 +2573,7 @@ enum punit_power_well { #define GEN3_SDVOC 0x61160 #define GEN4_HDMIB GEN3_SDVOB #define GEN4_HDMIC GEN3_SDVOC +#define CHV_HDMID 0x6116C #define PCH_SDVOB 0xe1140 #define PCH_HDMIB PCH_SDVOB #define PCH_HDMIC 0xe1150 @@ -2346,7 +2594,7 @@ enum punit_power_well { #define SDVO_PIPE_B_SELECT (1 << 30) #define SDVO_STALL_SELECT (1 << 29) #define SDVO_INTERRUPT_ENABLE (1 << 26) -/** +/* * 915G/GM SDVO pixel multiplier. * Programmed value is multiplier - 1, up to 5x. * \sa DPLL_MD_UDI_MULTIPLIER_MASK @@ -2386,6 +2634,10 @@ enum punit_power_well { #define SDVO_PIPE_SEL_CPT(pipe) ((pipe) << 29) #define SDVO_PIPE_SEL_MASK_CPT (3 << 29) +/* CHV SDVO/HDMI bits: */ +#define SDVO_PIPE_SEL_CHV(pipe) ((pipe) << 24) +#define SDVO_PIPE_SEL_MASK_CHV (3 << 24) + /* DVO port control */ #define DVOA 0x61120 @@ -2656,65 +2908,65 @@ enum punit_power_well { /* TV port control */ #define TV_CTL 0x68000 -/** Enables the TV encoder */ +/* Enables the TV encoder */ # define TV_ENC_ENABLE (1 << 31) -/** Sources the TV encoder input from pipe B instead of A. */ +/* Sources the TV encoder input from pipe B instead of A. */ # define TV_ENC_PIPEB_SELECT (1 << 30) -/** Outputs composite video (DAC A only) */ +/* Outputs composite video (DAC A only) */ # define TV_ENC_OUTPUT_COMPOSITE (0 << 28) -/** Outputs SVideo video (DAC B/C) */ +/* Outputs SVideo video (DAC B/C) */ # define TV_ENC_OUTPUT_SVIDEO (1 << 28) -/** Outputs Component video (DAC A/B/C) */ +/* Outputs Component video (DAC A/B/C) */ # define TV_ENC_OUTPUT_COMPONENT (2 << 28) -/** Outputs Composite and SVideo (DAC A/B/C) */ +/* Outputs Composite and SVideo (DAC A/B/C) */ # define TV_ENC_OUTPUT_SVIDEO_COMPOSITE (3 << 28) # define TV_TRILEVEL_SYNC (1 << 21) -/** Enables slow sync generation (945GM only) */ +/* Enables slow sync generation (945GM only) */ # define TV_SLOW_SYNC (1 << 20) -/** Selects 4x oversampling for 480i and 576p */ +/* Selects 4x oversampling for 480i and 576p */ # define TV_OVERSAMPLE_4X (0 << 18) -/** Selects 2x oversampling for 720p and 1080i */ +/* Selects 2x oversampling for 720p and 1080i */ # define TV_OVERSAMPLE_2X (1 << 18) -/** Selects no oversampling for 1080p */ +/* Selects no oversampling for 1080p */ # define TV_OVERSAMPLE_NONE (2 << 18) -/** Selects 8x oversampling */ +/* Selects 8x oversampling */ # define TV_OVERSAMPLE_8X (3 << 18) -/** Selects progressive mode rather than interlaced */ +/* Selects progressive mode rather than interlaced */ # define TV_PROGRESSIVE (1 << 17) -/** Sets the colorburst to PAL mode. Required for non-M PAL modes. */ +/* Sets the colorburst to PAL mode. Required for non-M PAL modes. */ # define TV_PAL_BURST (1 << 16) -/** Field for setting delay of Y compared to C */ +/* Field for setting delay of Y compared to C */ # define TV_YC_SKEW_MASK (7 << 12) -/** Enables a fix for 480p/576p standard definition modes on the 915GM only */ +/* Enables a fix for 480p/576p standard definition modes on the 915GM only */ # define TV_ENC_SDP_FIX (1 << 11) -/** +/* * Enables a fix for the 915GM only. * * Not sure what it does. */ # define TV_ENC_C0_FIX (1 << 10) -/** Bits that must be preserved by software */ +/* Bits that must be preserved by software */ # define TV_CTL_SAVE ((1 << 11) | (3 << 9) | (7 << 6) | 0xf) # define TV_FUSE_STATE_MASK (3 << 4) -/** Read-only state that reports all features enabled */ +/* Read-only state that reports all features enabled */ # define TV_FUSE_STATE_ENABLED (0 << 4) -/** Read-only state that reports that Macrovision is disabled in hardware*/ +/* Read-only state that reports that Macrovision is disabled in hardware*/ # define TV_FUSE_STATE_NO_MACROVISION (1 << 4) -/** Read-only state that reports that TV-out is disabled in hardware. */ +/* Read-only state that reports that TV-out is disabled in hardware. */ # define TV_FUSE_STATE_DISABLED (2 << 4) -/** Normal operation */ +/* Normal operation */ # define TV_TEST_MODE_NORMAL (0 << 0) -/** Encoder test pattern 1 - combo pattern */ +/* Encoder test pattern 1 - combo pattern */ # define TV_TEST_MODE_PATTERN_1 (1 << 0) -/** Encoder test pattern 2 - full screen vertical 75% color bars */ +/* Encoder test pattern 2 - full screen vertical 75% color bars */ # define TV_TEST_MODE_PATTERN_2 (2 << 0) -/** Encoder test pattern 3 - full screen horizontal 75% color bars */ +/* Encoder test pattern 3 - full screen horizontal 75% color bars */ # define TV_TEST_MODE_PATTERN_3 (3 << 0) -/** Encoder test pattern 4 - random noise */ +/* Encoder test pattern 4 - random noise */ # define TV_TEST_MODE_PATTERN_4 (4 << 0) -/** Encoder test pattern 5 - linear color ramps */ +/* Encoder test pattern 5 - linear color ramps */ # define TV_TEST_MODE_PATTERN_5 (5 << 0) -/** +/* * This test mode forces the DACs to 50% of full output. * * This is used for load detection in combination with TVDAC_SENSE_MASK @@ -2724,35 +2976,35 @@ enum punit_power_well { #define TV_DAC 0x68004 # define TV_DAC_SAVE 0x00ffff00 -/** +/* * Reports that DAC state change logic has reported change (RO). * * This gets cleared when TV_DAC_STATE_EN is cleared */ # define TVDAC_STATE_CHG (1 << 31) # define TVDAC_SENSE_MASK (7 << 28) -/** Reports that DAC A voltage is above the detect threshold */ +/* Reports that DAC A voltage is above the detect threshold */ # define TVDAC_A_SENSE (1 << 30) -/** Reports that DAC B voltage is above the detect threshold */ +/* Reports that DAC B voltage is above the detect threshold */ # define TVDAC_B_SENSE (1 << 29) -/** Reports that DAC C voltage is above the detect threshold */ +/* Reports that DAC C voltage is above the detect threshold */ # define TVDAC_C_SENSE (1 << 28) -/** +/* * Enables DAC state detection logic, for load-based TV detection. * * The PLL of the chosen pipe (in TV_CTL) must be running, and the encoder set * to off, for load detection to work. */ # define TVDAC_STATE_CHG_EN (1 << 27) -/** Sets the DAC A sense value to high */ +/* Sets the DAC A sense value to high */ # define TVDAC_A_SENSE_CTL (1 << 26) -/** Sets the DAC B sense value to high */ +/* Sets the DAC B sense value to high */ # define TVDAC_B_SENSE_CTL (1 << 25) -/** Sets the DAC C sense value to high */ +/* Sets the DAC C sense value to high */ # define TVDAC_C_SENSE_CTL (1 << 24) -/** Overrides the ENC_ENABLE and DAC voltage levels */ +/* Overrides the ENC_ENABLE and DAC voltage levels */ # define DAC_CTL_OVERRIDE (1 << 7) -/** Sets the slew rate. Must be preserved in software */ +/* Sets the slew rate. Must be preserved in software */ # define ENC_TVDAC_SLEW_FAST (1 << 6) # define DAC_A_1_3_V (0 << 4) # define DAC_A_1_1_V (1 << 4) @@ -2767,7 +3019,7 @@ enum punit_power_well { # define DAC_C_0_7_V (2 << 0) # define DAC_C_MASK (3 << 0) -/** +/* * CSC coefficients are stored in a floating point format with 9 bits of * mantissa and 2 or 3 bits of exponent. The exponent is represented as 2**-n, * where 2-bit exponents are unsigned n, and 3-bit exponents are signed n with @@ -2782,7 +3034,7 @@ enum punit_power_well { #define TV_CSC_Y2 0x68014 # define TV_BY_MASK 0x07ff0000 # define TV_BY_SHIFT 16 -/** +/* * Y attenuation for component video. * * Stored in 1.9 fixed point. @@ -2799,7 +3051,7 @@ enum punit_power_well { #define TV_CSC_U2 0x6801c # define TV_BU_MASK 0x07ff0000 # define TV_BU_SHIFT 16 -/** +/* * U attenuation for component video. * * Stored in 1.9 fixed point. @@ -2816,7 +3068,7 @@ enum punit_power_well { #define TV_CSC_V2 0x68024 # define TV_BV_MASK 0x07ff0000 # define TV_BV_SHIFT 16 -/** +/* * V attenuation for component video. * * Stored in 1.9 fixed point. @@ -2825,74 +3077,74 @@ enum punit_power_well { # define TV_AV_SHIFT 0 #define TV_CLR_KNOBS 0x68028 -/** 2s-complement brightness adjustment */ +/* 2s-complement brightness adjustment */ # define TV_BRIGHTNESS_MASK 0xff000000 # define TV_BRIGHTNESS_SHIFT 24 -/** Contrast adjustment, as a 2.6 unsigned floating point number */ +/* Contrast adjustment, as a 2.6 unsigned floating point number */ # define TV_CONTRAST_MASK 0x00ff0000 # define TV_CONTRAST_SHIFT 16 -/** Saturation adjustment, as a 2.6 unsigned floating point number */ +/* Saturation adjustment, as a 2.6 unsigned floating point number */ # define TV_SATURATION_MASK 0x0000ff00 # define TV_SATURATION_SHIFT 8 -/** Hue adjustment, as an integer phase angle in degrees */ +/* Hue adjustment, as an integer phase angle in degrees */ # define TV_HUE_MASK 0x000000ff # define TV_HUE_SHIFT 0 #define TV_CLR_LEVEL 0x6802c -/** Controls the DAC level for black */ +/* Controls the DAC level for black */ # define TV_BLACK_LEVEL_MASK 0x01ff0000 # define TV_BLACK_LEVEL_SHIFT 16 -/** Controls the DAC level for blanking */ +/* Controls the DAC level for blanking */ # define TV_BLANK_LEVEL_MASK 0x000001ff # define TV_BLANK_LEVEL_SHIFT 0 #define TV_H_CTL_1 0x68030 -/** Number of pixels in the hsync. */ +/* Number of pixels in the hsync. */ # define TV_HSYNC_END_MASK 0x1fff0000 # define TV_HSYNC_END_SHIFT 16 -/** Total number of pixels minus one in the line (display and blanking). */ +/* Total number of pixels minus one in the line (display and blanking). */ # define TV_HTOTAL_MASK 0x00001fff # define TV_HTOTAL_SHIFT 0 #define TV_H_CTL_2 0x68034 -/** Enables the colorburst (needed for non-component color) */ +/* Enables the colorburst (needed for non-component color) */ # define TV_BURST_ENA (1 << 31) -/** Offset of the colorburst from the start of hsync, in pixels minus one. */ +/* Offset of the colorburst from the start of hsync, in pixels minus one. */ # define TV_HBURST_START_SHIFT 16 # define TV_HBURST_START_MASK 0x1fff0000 -/** Length of the colorburst */ +/* Length of the colorburst */ # define TV_HBURST_LEN_SHIFT 0 # define TV_HBURST_LEN_MASK 0x0001fff #define TV_H_CTL_3 0x68038 -/** End of hblank, measured in pixels minus one from start of hsync */ +/* End of hblank, measured in pixels minus one from start of hsync */ # define TV_HBLANK_END_SHIFT 16 # define TV_HBLANK_END_MASK 0x1fff0000 -/** Start of hblank, measured in pixels minus one from start of hsync */ +/* Start of hblank, measured in pixels minus one from start of hsync */ # define TV_HBLANK_START_SHIFT 0 # define TV_HBLANK_START_MASK 0x0001fff #define TV_V_CTL_1 0x6803c -/** XXX */ +/* XXX */ # define TV_NBR_END_SHIFT 16 # define TV_NBR_END_MASK 0x07ff0000 -/** XXX */ +/* XXX */ # define TV_VI_END_F1_SHIFT 8 # define TV_VI_END_F1_MASK 0x00003f00 -/** XXX */ +/* XXX */ # define TV_VI_END_F2_SHIFT 0 # define TV_VI_END_F2_MASK 0x0000003f #define TV_V_CTL_2 0x68040 -/** Length of vsync, in half lines */ +/* Length of vsync, in half lines */ # define TV_VSYNC_LEN_MASK 0x07ff0000 # define TV_VSYNC_LEN_SHIFT 16 -/** Offset of the start of vsync in field 1, measured in one less than the +/* Offset of the start of vsync in field 1, measured in one less than the * number of half lines. */ # define TV_VSYNC_START_F1_MASK 0x00007f00 # define TV_VSYNC_START_F1_SHIFT 8 -/** +/* * Offset of the start of vsync in field 2, measured in one less than the * number of half lines. */ @@ -2900,17 +3152,17 @@ enum punit_power_well { # define TV_VSYNC_START_F2_SHIFT 0 #define TV_V_CTL_3 0x68044 -/** Enables generation of the equalization signal */ +/* Enables generation of the equalization signal */ # define TV_EQUAL_ENA (1 << 31) -/** Length of vsync, in half lines */ +/* Length of vsync, in half lines */ # define TV_VEQ_LEN_MASK 0x007f0000 # define TV_VEQ_LEN_SHIFT 16 -/** Offset of the start of equalization in field 1, measured in one less than +/* Offset of the start of equalization in field 1, measured in one less than * the number of half lines. */ # define TV_VEQ_START_F1_MASK 0x0007f00 # define TV_VEQ_START_F1_SHIFT 8 -/** +/* * Offset of the start of equalization in field 2, measured in one less than * the number of half lines. */ @@ -2918,13 +3170,13 @@ enum punit_power_well { # define TV_VEQ_START_F2_SHIFT 0 #define TV_V_CTL_4 0x68048 -/** +/* * Offset to start of vertical colorburst, measured in one less than the * number of lines from vertical start. */ # define TV_VBURST_START_F1_MASK 0x003f0000 # define TV_VBURST_START_F1_SHIFT 16 -/** +/* * Offset to the end of vertical colorburst, measured in one less than the * number of lines from the start of NBR. */ @@ -2932,13 +3184,13 @@ enum punit_power_well { # define TV_VBURST_END_F1_SHIFT 0 #define TV_V_CTL_5 0x6804c -/** +/* * Offset to start of vertical colorburst, measured in one less than the * number of lines from vertical start. */ # define TV_VBURST_START_F2_MASK 0x003f0000 # define TV_VBURST_START_F2_SHIFT 16 -/** +/* * Offset to the end of vertical colorburst, measured in one less than the * number of lines from the start of NBR. */ @@ -2946,13 +3198,13 @@ enum punit_power_well { # define TV_VBURST_END_F2_SHIFT 0 #define TV_V_CTL_6 0x68050 -/** +/* * Offset to start of vertical colorburst, measured in one less than the * number of lines from vertical start. */ # define TV_VBURST_START_F3_MASK 0x003f0000 # define TV_VBURST_START_F3_SHIFT 16 -/** +/* * Offset to the end of vertical colorburst, measured in one less than the * number of lines from the start of NBR. */ @@ -2960,13 +3212,13 @@ enum punit_power_well { # define TV_VBURST_END_F3_SHIFT 0 #define TV_V_CTL_7 0x68054 -/** +/* * Offset to start of vertical colorburst, measured in one less than the * number of lines from vertical start. */ # define TV_VBURST_START_F4_MASK 0x003f0000 # define TV_VBURST_START_F4_SHIFT 16 -/** +/* * Offset to the end of vertical colorburst, measured in one less than the * number of lines from the start of NBR. */ @@ -2974,56 +3226,56 @@ enum punit_power_well { # define TV_VBURST_END_F4_SHIFT 0 #define TV_SC_CTL_1 0x68060 -/** Turns on the first subcarrier phase generation DDA */ +/* Turns on the first subcarrier phase generation DDA */ # define TV_SC_DDA1_EN (1 << 31) -/** Turns on the first subcarrier phase generation DDA */ +/* Turns on the first subcarrier phase generation DDA */ # define TV_SC_DDA2_EN (1 << 30) -/** Turns on the first subcarrier phase generation DDA */ +/* Turns on the first subcarrier phase generation DDA */ # define TV_SC_DDA3_EN (1 << 29) -/** Sets the subcarrier DDA to reset frequency every other field */ +/* Sets the subcarrier DDA to reset frequency every other field */ # define TV_SC_RESET_EVERY_2 (0 << 24) -/** Sets the subcarrier DDA to reset frequency every fourth field */ +/* Sets the subcarrier DDA to reset frequency every fourth field */ # define TV_SC_RESET_EVERY_4 (1 << 24) -/** Sets the subcarrier DDA to reset frequency every eighth field */ +/* Sets the subcarrier DDA to reset frequency every eighth field */ # define TV_SC_RESET_EVERY_8 (2 << 24) -/** Sets the subcarrier DDA to never reset the frequency */ +/* Sets the subcarrier DDA to never reset the frequency */ # define TV_SC_RESET_NEVER (3 << 24) -/** Sets the peak amplitude of the colorburst.*/ +/* Sets the peak amplitude of the colorburst.*/ # define TV_BURST_LEVEL_MASK 0x00ff0000 # define TV_BURST_LEVEL_SHIFT 16 -/** Sets the increment of the first subcarrier phase generation DDA */ +/* Sets the increment of the first subcarrier phase generation DDA */ # define TV_SCDDA1_INC_MASK 0x00000fff # define TV_SCDDA1_INC_SHIFT 0 #define TV_SC_CTL_2 0x68064 -/** Sets the rollover for the second subcarrier phase generation DDA */ +/* Sets the rollover for the second subcarrier phase generation DDA */ # define TV_SCDDA2_SIZE_MASK 0x7fff0000 # define TV_SCDDA2_SIZE_SHIFT 16 -/** Sets the increent of the second subcarrier phase generation DDA */ +/* Sets the increent of the second subcarrier phase generation DDA */ # define TV_SCDDA2_INC_MASK 0x00007fff # define TV_SCDDA2_INC_SHIFT 0 #define TV_SC_CTL_3 0x68068 -/** Sets the rollover for the third subcarrier phase generation DDA */ +/* Sets the rollover for the third subcarrier phase generation DDA */ # define TV_SCDDA3_SIZE_MASK 0x7fff0000 # define TV_SCDDA3_SIZE_SHIFT 16 -/** Sets the increent of the third subcarrier phase generation DDA */ +/* Sets the increent of the third subcarrier phase generation DDA */ # define TV_SCDDA3_INC_MASK 0x00007fff # define TV_SCDDA3_INC_SHIFT 0 #define TV_WIN_POS 0x68070 -/** X coordinate of the display from the start of horizontal active */ +/* X coordinate of the display from the start of horizontal active */ # define TV_XPOS_MASK 0x1fff0000 # define TV_XPOS_SHIFT 16 -/** Y coordinate of the display from the start of vertical active (NBR) */ +/* Y coordinate of the display from the start of vertical active (NBR) */ # define TV_YPOS_MASK 0x00000fff # define TV_YPOS_SHIFT 0 #define TV_WIN_SIZE 0x68074 -/** Horizontal size of the display window, measured in pixels*/ +/* Horizontal size of the display window, measured in pixels*/ # define TV_XSIZE_MASK 0x1fff0000 # define TV_XSIZE_SHIFT 16 -/** +/* * Vertical size of the display window, measured in pixels. * * Must be even for interlaced modes. @@ -3032,28 +3284,28 @@ enum punit_power_well { # define TV_YSIZE_SHIFT 0 #define TV_FILTER_CTL_1 0x68080 -/** +/* * Enables automatic scaling calculation. * * If set, the rest of the registers are ignored, and the calculated values can * be read back from the register. */ # define TV_AUTO_SCALE (1 << 31) -/** +/* * Disables the vertical filter. * * This is required on modes more than 1024 pixels wide */ # define TV_V_FILTER_BYPASS (1 << 29) -/** Enables adaptive vertical filtering */ +/* Enables adaptive vertical filtering */ # define TV_VADAPT (1 << 28) # define TV_VADAPT_MODE_MASK (3 << 26) -/** Selects the least adaptive vertical filtering mode */ +/* Selects the least adaptive vertical filtering mode */ # define TV_VADAPT_MODE_LEAST (0 << 26) -/** Selects the moderately adaptive vertical filtering mode */ +/* Selects the moderately adaptive vertical filtering mode */ # define TV_VADAPT_MODE_MODERATE (1 << 26) -/** Selects the most adaptive vertical filtering mode */ +/* Selects the most adaptive vertical filtering mode */ # define TV_VADAPT_MODE_MOST (3 << 26) -/** +/* * Sets the horizontal scaling factor. * * This should be the fractional part of the horizontal scaling factor divided @@ -3065,14 +3317,14 @@ enum punit_power_well { # define TV_HSCALE_FRAC_SHIFT 0 #define TV_FILTER_CTL_2 0x68084 -/** +/* * Sets the integer part of the 3.15 fixed-point vertical scaling factor. * * TV_VSCALE should be (src height - 1) / ((interlace * dest height) - 1) */ # define TV_VSCALE_INT_MASK 0x00038000 # define TV_VSCALE_INT_SHIFT 15 -/** +/* * Sets the fractional part of the 3.15 fixed-point vertical scaling factor. * * \sa TV_VSCALE_INT_MASK @@ -3081,7 +3333,7 @@ enum punit_power_well { # define TV_VSCALE_FRAC_SHIFT 0 #define TV_FILTER_CTL_3 0x68088 -/** +/* * Sets the integer part of the 3.15 fixed-point vertical scaling factor. * * TV_VSCALE should be (src height - 1) / (1/4 * (dest height - 1)) @@ -3090,7 +3342,7 @@ enum punit_power_well { */ # define TV_VSCALE_IP_INT_MASK 0x00038000 # define TV_VSCALE_IP_INT_SHIFT 15 -/** +/* * Sets the fractional part of the 3.15 fixed-point vertical scaling factor. * * For progressive modes, TV_VSCALE_IP_INT should be set to zeroes. @@ -3102,26 +3354,26 @@ enum punit_power_well { #define TV_CC_CONTROL 0x68090 # define TV_CC_ENABLE (1 << 31) -/** +/* * Specifies which field to send the CC data in. * * CC data is usually sent in field 0. */ # define TV_CC_FID_MASK (1 << 27) # define TV_CC_FID_SHIFT 27 -/** Sets the horizontal position of the CC data. Usually 135. */ +/* Sets the horizontal position of the CC data. Usually 135. */ # define TV_CC_HOFF_MASK 0x03ff0000 # define TV_CC_HOFF_SHIFT 16 -/** Sets the vertical position of the CC data. Usually 21 */ +/* Sets the vertical position of the CC data. Usually 21 */ # define TV_CC_LINE_MASK 0x0000003f # define TV_CC_LINE_SHIFT 0 #define TV_CC_DATA 0x68094 # define TV_CC_RDY (1 << 31) -/** Second word of CC data to be transmitted. */ +/* Second word of CC data to be transmitted. */ # define TV_CC_DATA_2_MASK 0x007f0000 # define TV_CC_DATA_2_SHIFT 16 -/** First word of CC data to be transmitted. */ +/* First word of CC data to be transmitted. */ # define TV_CC_DATA_1_MASK 0x0000007f # define TV_CC_DATA_1_SHIFT 0 @@ -3143,6 +3395,8 @@ enum punit_power_well { #define DP_PORT_EN (1 << 31) #define DP_PIPEB_SELECT (1 << 30) #define DP_PIPE_MASK (1 << 30) +#define DP_PIPE_SELECT_CHV(pipe) ((pipe) << 16) +#define DP_PIPE_MASK_CHV (3 << 16) /* Link training mode - select a suitable mode for each stage */ #define DP_LINK_TRAIN_PAT_1 (0 << 28) @@ -3190,32 +3444,32 @@ enum punit_power_well { #define DP_PLL_FREQ_160MHZ (1 << 16) #define DP_PLL_FREQ_MASK (3 << 16) -/** locked once port is enabled */ +/* locked once port is enabled */ #define DP_PORT_REVERSAL (1 << 15) /* eDP */ #define DP_PLL_ENABLE (1 << 14) -/** sends the clock on lane 15 of the PEG for debug */ +/* sends the clock on lane 15 of the PEG for debug */ #define DP_CLOCK_OUTPUT_ENABLE (1 << 13) #define DP_SCRAMBLING_DISABLE (1 << 12) #define DP_SCRAMBLING_DISABLE_IRONLAKE (1 << 7) -/** limit RGB values to avoid confusing TVs */ +/* limit RGB values to avoid confusing TVs */ #define DP_COLOR_RANGE_16_235 (1 << 8) -/** Turn on the audio link */ +/* Turn on the audio link */ #define DP_AUDIO_OUTPUT_ENABLE (1 << 6) -/** vs and hs sync polarity */ +/* vs and hs sync polarity */ #define DP_SYNC_VS_HIGH (1 << 4) #define DP_SYNC_HS_HIGH (1 << 3) -/** A fantasy */ +/* A fantasy */ #define DP_DETECTED (1 << 2) -/** The aux channel provides a way to talk to the +/* The aux channel provides a way to talk to the * signal sink for DDC etc. Max packet size supported * is 20 bytes in each direction, hence the 5 fixed * data registers @@ -3377,6 +3631,7 @@ enum punit_power_well { #define SPRITE1_FLIP_DONE_INT_EN_VLV (1UL<<30) #define PIPE_CRC_ERROR_ENABLE (1UL<<29) #define PIPE_CRC_DONE_ENABLE (1UL<<28) +#define PERF_COUNTER2_INTERRUPT_EN (1UL<<27) #define PIPE_GMBUS_EVENT_ENABLE (1UL<<27) #define PLANE_FLIP_DONE_INT_EN_VLV (1UL<<26) #define PIPE_HOTPLUG_INTERRUPT_ENABLE (1UL<<26) @@ -3388,8 +3643,10 @@ enum punit_power_well { #define PIPE_ODD_FIELD_INTERRUPT_ENABLE (1UL<<21) #define PIPE_EVEN_FIELD_INTERRUPT_ENABLE (1UL<<20) #define PIPE_B_PSR_INTERRUPT_ENABLE_VLV (1UL<<19) +#define PERF_COUNTER_INTERRUPT_EN (1UL<<19) #define PIPE_HOTPLUG_TV_INTERRUPT_ENABLE (1UL<<18) /* pre-965 */ #define PIPE_START_VBLANK_INTERRUPT_ENABLE (1UL<<18) /* 965 or later */ +#define PIPE_FRAMESTART_INTERRUPT_ENABLE (1UL<<17) #define PIPE_VBLANK_INTERRUPT_ENABLE (1UL<<17) #define PIPEA_HBLANK_INT_EN_VLV (1UL<<16) #define PIPE_OVERLAY_UPDATED_ENABLE (1UL<<16) @@ -3397,6 +3654,7 @@ enum punit_power_well { #define SPRITE0_FLIP_DONE_INT_STATUS_VLV (1UL<<14) #define PIPE_CRC_ERROR_INTERRUPT_STATUS (1UL<<13) #define PIPE_CRC_DONE_INTERRUPT_STATUS (1UL<<12) +#define PERF_COUNTER2_INTERRUPT_STATUS (1UL<<11) #define PIPE_GMBUS_INTERRUPT_STATUS (1UL<<11) #define PLANE_FLIP_DONE_INT_STATUS_VLV (1UL<<10) #define PIPE_HOTPLUG_INTERRUPT_STATUS (1UL<<10) @@ -3405,20 +3663,25 @@ enum punit_power_well { #define PIPE_DPST_EVENT_STATUS (1UL<<7) #define PIPE_LEGACY_BLC_EVENT_STATUS (1UL<<6) #define PIPE_A_PSR_STATUS_VLV (1UL<<6) +#define PIPE_LEGACY_BLC_EVENT_STATUS (1UL<<6) #define PIPE_ODD_FIELD_INTERRUPT_STATUS (1UL<<5) #define PIPE_EVEN_FIELD_INTERRUPT_STATUS (1UL<<4) #define PIPE_B_PSR_STATUS_VLV (1UL<<3) +#define PERF_COUNTER_INTERRUPT_STATUS (1UL<<3) #define PIPE_HOTPLUG_TV_INTERRUPT_STATUS (1UL<<2) /* pre-965 */ #define PIPE_START_VBLANK_INTERRUPT_STATUS (1UL<<2) /* 965 or later */ +#define PIPE_FRAMESTART_INTERRUPT_STATUS (1UL<<1) #define PIPE_VBLANK_INTERRUPT_STATUS (1UL<<1) +#define PIPE_HBLANK_INT_STATUS (1UL<<0) #define PIPE_OVERLAY_UPDATED_STATUS (1UL<<0) #define PIPESTAT_INT_ENABLE_MASK 0x7fff0000 #define PIPESTAT_INT_STATUS_MASK 0x0000ffff -#define PIPE_A_OFFSET 0x70000 -#define PIPE_B_OFFSET 0x71000 -#define PIPE_C_OFFSET 0x72000 +#define PIPE_A_OFFSET 0x70000 +#define PIPE_B_OFFSET 0x71000 +#define PIPE_C_OFFSET 0x72000 +#define CHV_PIPE_C_OFFSET 0x74000 /* * There's actually no pipe EDP. Some pipe registers have * simply shifted from the pipe to the transcoder, while @@ -3456,14 +3719,25 @@ enum punit_power_well { #define SPRITED_FLIP_DONE_INT_EN (1<<26) #define SPRITEC_FLIP_DONE_INT_EN (1<<25) #define PLANEB_FLIP_DONE_INT_EN (1<<24) +#define PIPE_PSR_INT_EN (1<<22) #define PIPEA_LINE_COMPARE_INT_EN (1<<21) #define PIPEA_HLINE_INT_EN (1<<20) #define PIPEA_VBLANK_INT_EN (1<<19) #define SPRITEB_FLIP_DONE_INT_EN (1<<18) #define SPRITEA_FLIP_DONE_INT_EN (1<<17) #define PLANEA_FLIPDONE_INT_EN (1<<16) - -#define DPINVGTT (VLV_DISPLAY_BASE + 0x7002c) /* VLV only */ +#define PIPEC_LINE_COMPARE_INT_EN (1<<13) +#define PIPEC_HLINE_INT_EN (1<<12) +#define PIPEC_VBLANK_INT_EN (1<<11) +#define SPRITEF_FLIPDONE_INT_EN (1<<10) +#define SPRITEE_FLIPDONE_INT_EN (1<<9) +#define PLANEC_FLIPDONE_INT_EN (1<<8) + +#define DPINVGTT (VLV_DISPLAY_BASE + 0x7002c) /* VLV/CHV only */ +#define SPRITEF_INVALID_GTT_INT_EN (1<<27) +#define SPRITEE_INVALID_GTT_INT_EN (1<<26) +#define PLANEC_INVALID_GTT_INT_EN (1<<25) +#define CURSORC_INVALID_GTT_INT_EN (1<<24) #define CURSORB_INVALID_GTT_INT_EN (1<<23) #define CURSORA_INVALID_GTT_INT_EN (1<<22) #define SPRITED_INVALID_GTT_INT_EN (1<<21) @@ -3473,6 +3747,11 @@ enum punit_power_well { #define SPRITEA_INVALID_GTT_INT_EN (1<<17) #define PLANEA_INVALID_GTT_INT_EN (1<<16) #define DPINVGTT_EN_MASK 0xff0000 +#define DPINVGTT_EN_MASK_CHV 0xfff0000 +#define SPRITEF_INVALID_GTT_STATUS (1<<11) +#define SPRITEE_INVALID_GTT_STATUS (1<<10) +#define PLANEC_INVALID_GTT_STATUS (1<<9) +#define CURSORC_INVALID_GTT_STATUS (1<<8) #define CURSORB_INVALID_GTT_STATUS (1<<7) #define CURSORA_INVALID_GTT_STATUS (1<<6) #define SPRITED_INVALID_GTT_STATUS (1<<5) @@ -3482,6 +3761,7 @@ enum punit_power_well { #define SPRITEA_INVALID_GTT_STATUS (1<<1) #define PLANEA_INVALID_GTT_STATUS (1<<0) #define DPINVGTT_STATUS_MASK 0xff +#define DPINVGTT_STATUS_MASK_CHV 0xfff #define DSPARB 0x70030 #define DSPARB_CSTART_MASK (0x7f << 7) @@ -3521,14 +3801,43 @@ enum punit_power_well { #define DDL_CURSORA_PRECISION_32 (1<<31) #define DDL_CURSORA_PRECISION_16 (0<<31) #define DDL_CURSORA_SHIFT 24 +#define DDL_SPRITEB_PRECISION_32 (1<<23) +#define DDL_SPRITEB_PRECISION_16 (0<<23) +#define DDL_SPRITEB_SHIFT 16 +#define DDL_SPRITEA_PRECISION_32 (1<<15) +#define DDL_SPRITEA_PRECISION_16 (0<<15) +#define DDL_SPRITEA_SHIFT 8 #define DDL_PLANEA_PRECISION_32 (1<<7) #define DDL_PLANEA_PRECISION_16 (0<<7) +#define DDL_PLANEA_SHIFT 0 + #define VLV_DDL2 (VLV_DISPLAY_BASE + 0x70054) #define DDL_CURSORB_PRECISION_32 (1<<31) #define DDL_CURSORB_PRECISION_16 (0<<31) #define DDL_CURSORB_SHIFT 24 +#define DDL_SPRITED_PRECISION_32 (1<<23) +#define DDL_SPRITED_PRECISION_16 (0<<23) +#define DDL_SPRITED_SHIFT 16 +#define DDL_SPRITEC_PRECISION_32 (1<<15) +#define DDL_SPRITEC_PRECISION_16 (0<<15) +#define DDL_SPRITEC_SHIFT 8 #define DDL_PLANEB_PRECISION_32 (1<<7) #define DDL_PLANEB_PRECISION_16 (0<<7) +#define DDL_PLANEB_SHIFT 0 + +#define VLV_DDL3 (VLV_DISPLAY_BASE + 0x70058) +#define DDL_CURSORC_PRECISION_32 (1<<31) +#define DDL_CURSORC_PRECISION_16 (0<<31) +#define DDL_CURSORC_SHIFT 24 +#define DDL_SPRITEF_PRECISION_32 (1<<23) +#define DDL_SPRITEF_PRECISION_16 (0<<23) +#define DDL_SPRITEF_SHIFT 16 +#define DDL_SPRITEE_PRECISION_32 (1<<15) +#define DDL_SPRITEE_PRECISION_16 (0<<15) +#define DDL_SPRITEE_SHIFT 8 +#define DDL_PLANEC_PRECISION_32 (1<<7) +#define DDL_PLANEC_PRECISION_16 (0<<7) +#define DDL_PLANEC_SHIFT 0 /* FIFO watermark sizes etc */ #define G4X_FIFO_LINE_SIZE 64 @@ -3639,9 +3948,10 @@ enum punit_power_well { #define _PIPEA_FRMCOUNT_GM45 0x70040 #define _PIPEA_FLIPCOUNT_GM45 0x70044 #define PIPE_FRMCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FRMCOUNT_GM45) +#define PIPE_FLIPCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FLIPCOUNT_GM45) /* Cursor A & B regs */ -#define _CURACNTR (dev_priv->info.display_mmio_offset + 0x70080) +#define _CURACNTR 0x70080 /* Old style CUR*CNTR flags (desktop 8xx) */ #define CURSOR_ENABLE 0x80000000 #define CURSOR_GAMMA_ENABLE 0x40000000 @@ -3668,28 +3978,34 @@ enum punit_power_well { #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 _CURABASE 0x70084 +#define _CURAPOS 0x70088 #define CURSOR_POS_MASK 0x007FF #define CURSOR_POS_SIGN 0x8000 #define CURSOR_X_SHIFT 0 #define CURSOR_Y_SHIFT 16 #define CURSIZE 0x700a0 -#define _CURBCNTR (dev_priv->info.display_mmio_offset + 0x700c0) -#define _CURBBASE (dev_priv->info.display_mmio_offset + 0x700c4) -#define _CURBPOS (dev_priv->info.display_mmio_offset + 0x700c8) +#define _CURBCNTR 0x700c0 +#define _CURBBASE 0x700c4 +#define _CURBPOS 0x700c8 #define _CURBCNTR_IVB 0x71080 #define _CURBBASE_IVB 0x71084 #define _CURBPOS_IVB 0x71088 -#define CURCNTR(pipe) _PIPE(pipe, _CURACNTR, _CURBCNTR) -#define CURBASE(pipe) _PIPE(pipe, _CURABASE, _CURBBASE) -#define CURPOS(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS) +#define _CURSOR2(pipe, reg) (dev_priv->info.cursor_offsets[(pipe)] - \ + dev_priv->info.cursor_offsets[PIPE_A] + (reg) + \ + dev_priv->info.display_mmio_offset) + +#define CURCNTR(pipe) _CURSOR2(pipe, _CURACNTR) +#define CURBASE(pipe) _CURSOR2(pipe, _CURABASE) +#define CURPOS(pipe) _CURSOR2(pipe, _CURAPOS) -#define CURCNTR_IVB(pipe) _PIPE(pipe, _CURACNTR, _CURBCNTR_IVB) -#define CURBASE_IVB(pipe) _PIPE(pipe, _CURABASE, _CURBBASE_IVB) -#define CURPOS_IVB(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS_IVB) +#define CURSOR_A_OFFSET 0x70080 +#define CURSOR_B_OFFSET 0x700c0 +#define CHV_CURSOR_C_OFFSET 0x700e0 +#define IVB_CURSOR_B_OFFSET 0x71080 +#define IVB_CURSOR_C_OFFSET 0x72080 /* Display A control */ #define _DSPACNTR 0x70180 @@ -4194,6 +4510,7 @@ enum punit_power_well { #define GEN8_DE_PIPE_A_IRQ (1<<16) #define GEN8_DE_PIPE_IRQ(pipe) (1<<(16+pipe)) #define GEN8_GT_VECS_IRQ (1<<6) +#define GEN8_GT_PM_IRQ (1<<4) #define GEN8_GT_VCS2_IRQ (1<<3) #define GEN8_GT_VCS1_IRQ (1<<2) #define GEN8_GT_BCS_IRQ (1<<1) @@ -4933,6 +5250,8 @@ enum punit_power_well { #define PORT_TRANS_SEL_CPT(pipe) ((pipe) << 29) #define PORT_TO_PIPE(val) (((val) & (1<<30)) >> 30) #define PORT_TO_PIPE_CPT(val) (((val) & PORT_TRANS_SEL_MASK) >> 29) +#define SDVO_PORT_TO_PIPE_CHV(val) (((val) & (3<<24)) >> 24) +#define DP_PORT_TO_PIPE_CHV(val) (((val) & (3<<16)) >> 16) #define TRANS_DP_CTL_A 0xe0300 #define TRANS_DP_CTL_B 0xe1300 @@ -4989,6 +5308,8 @@ enum punit_power_well { #define EDP_LINK_TRAIN_VOL_EMP_MASK_IVB (0x3f<<22) +#define VLV_PMWGICZ 0x1300a4 + #define FORCEWAKE 0xA18C #define FORCEWAKE_VLV 0x1300b0 #define FORCEWAKE_ACK_VLV 0x1300b4 @@ -5012,6 +5333,7 @@ enum punit_power_well { #define FORCEWAKE_MT_ACK 0x130040 #define ECOBUS 0xa180 #define FORCEWAKE_MT_ENABLE (1<<5) +#define VLV_SPAREG2H 0xA194 #define GTFIFODBG 0x120000 #define GT_FIFO_SBDROPERR (1<<6) @@ -5031,6 +5353,7 @@ enum punit_power_well { #define HSW_EDRAM_PRESENT 0x120010 #define GEN6_UCGCTL1 0x9400 +# define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE (1 << 16) # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE (1 << 5) # define GEN6_CSUNIT_CLOCK_GATE_DISABLE (1 << 7) @@ -5041,12 +5364,19 @@ enum punit_power_well { # define GEN6_RCPBUNIT_CLOCK_GATE_DISABLE (1 << 12) # define GEN6_RCCUNIT_CLOCK_GATE_DISABLE (1 << 11) +#define GEN6_UCGCTL3 0x9408 + #define GEN7_UCGCTL4 0x940c #define GEN7_L3BANK2X_CLOCK_GATE_DISABLE (1<<25) +#define GEN6_RCGCTL1 0x9410 +#define GEN6_RCGCTL2 0x9414 +#define GEN6_RSTCTL 0x9420 + #define GEN8_UCGCTL6 0x9430 #define GEN8_SDEUNIT_CLOCK_GATE_DISABLE (1<<14) +#define GEN6_GFXPAUSE 0xA000 #define GEN6_RPNSWREQ 0xA008 #define GEN6_TURBO_DISABLE (1<<31) #define GEN6_FREQUENCY(x) ((x)<<25) @@ -5099,6 +5429,9 @@ enum punit_power_well { #define GEN6_RP_UP_EI 0xA068 #define GEN6_RP_DOWN_EI 0xA06C #define GEN6_RP_IDLE_HYSTERSIS 0xA070 +#define GEN6_RPDEUHWTC 0xA080 +#define GEN6_RPDEUC 0xA084 +#define GEN6_RPDEUCSW 0xA088 #define GEN6_RC_STATE 0xA094 #define GEN6_RC1_WAKE_RATE_LIMIT 0xA098 #define GEN6_RC6_WAKE_RATE_LIMIT 0xA09C @@ -5106,11 +5439,15 @@ enum punit_power_well { #define GEN6_RC_EVALUATION_INTERVAL 0xA0A8 #define GEN6_RC_IDLE_HYSTERSIS 0xA0AC #define GEN6_RC_SLEEP 0xA0B0 +#define GEN6_RCUBMABDTMR 0xA0B0 #define GEN6_RC1e_THRESHOLD 0xA0B4 #define GEN6_RC6_THRESHOLD 0xA0B8 #define GEN6_RC6p_THRESHOLD 0xA0BC +#define VLV_RCEDATA 0xA0BC #define GEN6_RC6pp_THRESHOLD 0xA0C0 #define GEN6_PMINTRMSK 0xA168 +#define GEN8_PMINTR_REDIRECT_TO_NON_DISP (1<<31) +#define VLV_PWRDWNUPCTL 0xA294 #define GEN6_PMISR 0x44020 #define GEN6_PMIMR 0x44024 /* rps_lock */ @@ -5127,6 +5464,9 @@ enum punit_power_well { GEN6_PM_RP_DOWN_THRESHOLD | \ GEN6_PM_RP_DOWN_TIMEOUT) +#define GEN7_GT_SCRATCH_BASE 0x4F100 +#define GEN7_GT_SCRATCH_REG_NUM 8 + #define VLV_GTLC_SURVIVABILITY_REG 0x130098 #define VLV_GFX_CLK_STATUS_BIT (1<<3) #define VLV_GFX_CLK_FORCE_ON_BIT (1<<2) diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 56785e8fb2eb..043123c77a1f 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -328,8 +328,6 @@ int i915_save_state(struct drm_device *dev) } } - intel_disable_gt_powersave(dev); - /* Cache mode state */ if (INTEL_INFO(dev)->gen < 7) dev_priv->regfile.saveCACHE_MODE_0 = I915_READ(CACHE_MODE_0); diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index 3620997e43f5..86ce39aad0ff 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -186,7 +186,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj, struct drm_minor *dminor = dev_to_drm_minor(dev); struct drm_device *drm_dev = dminor->dev; struct drm_i915_private *dev_priv = drm_dev->dev_private; - struct i915_hw_context *ctx; + struct intel_context *ctx; u32 *temp = NULL; /* Just here to make handling failures easy */ int slice = (int)(uintptr_t)attr->private; int ret; diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index b29d7b1828f1..f5aa0067755a 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -326,8 +326,8 @@ TRACE_EVENT(i915_gem_evict_vm, ); TRACE_EVENT(i915_gem_ring_sync_to, - TP_PROTO(struct intel_ring_buffer *from, - struct intel_ring_buffer *to, + TP_PROTO(struct intel_engine_cs *from, + struct intel_engine_cs *to, u32 seqno), TP_ARGS(from, to, seqno), @@ -352,7 +352,7 @@ TRACE_EVENT(i915_gem_ring_sync_to, ); TRACE_EVENT(i915_gem_ring_dispatch, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno, u32 flags), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno, u32 flags), TP_ARGS(ring, seqno, flags), TP_STRUCT__entry( @@ -375,7 +375,7 @@ TRACE_EVENT(i915_gem_ring_dispatch, ); TRACE_EVENT(i915_gem_ring_flush, - TP_PROTO(struct intel_ring_buffer *ring, u32 invalidate, u32 flush), + TP_PROTO(struct intel_engine_cs *ring, u32 invalidate, u32 flush), TP_ARGS(ring, invalidate, flush), TP_STRUCT__entry( @@ -398,7 +398,7 @@ TRACE_EVENT(i915_gem_ring_flush, ); DECLARE_EVENT_CLASS(i915_gem_request, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno), TP_STRUCT__entry( @@ -418,12 +418,12 @@ DECLARE_EVENT_CLASS(i915_gem_request, ); DEFINE_EVENT(i915_gem_request, i915_gem_request_add, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno) ); TRACE_EVENT(i915_gem_request_complete, - TP_PROTO(struct intel_ring_buffer *ring), + TP_PROTO(struct intel_engine_cs *ring), TP_ARGS(ring), TP_STRUCT__entry( @@ -443,12 +443,12 @@ TRACE_EVENT(i915_gem_request_complete, ); DEFINE_EVENT(i915_gem_request, i915_gem_request_retire, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno) ); TRACE_EVENT(i915_gem_request_wait_begin, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno), TP_STRUCT__entry( @@ -477,12 +477,12 @@ TRACE_EVENT(i915_gem_request_wait_begin, ); DEFINE_EVENT(i915_gem_request, i915_gem_request_wait_end, - TP_PROTO(struct intel_ring_buffer *ring, u32 seqno), + TP_PROTO(struct intel_engine_cs *ring, u32 seqno), TP_ARGS(ring, seqno) ); DECLARE_EVENT_CLASS(i915_ring, - TP_PROTO(struct intel_ring_buffer *ring), + TP_PROTO(struct intel_engine_cs *ring), TP_ARGS(ring), TP_STRUCT__entry( @@ -499,12 +499,12 @@ DECLARE_EVENT_CLASS(i915_ring, ); DEFINE_EVENT(i915_ring, i915_ring_wait_begin, - TP_PROTO(struct intel_ring_buffer *ring), + TP_PROTO(struct intel_engine_cs *ring), TP_ARGS(ring) ); DEFINE_EVENT(i915_ring, i915_ring_wait_end, - TP_PROTO(struct intel_ring_buffer *ring), + TP_PROTO(struct intel_engine_cs *ring), TP_ARGS(ring) ); diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 0ad4e9600063..b17b9c7c769f 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -364,55 +364,6 @@ void hsw_fdi_link_train(struct drm_crtc *crtc) DRM_ERROR("FDI link training failed!\n"); } -static void intel_ddi_mode_set(struct intel_encoder *encoder) -{ - struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); - int port = intel_ddi_get_encoder_port(encoder); - int pipe = crtc->pipe; - int type = encoder->type; - struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode; - - DRM_DEBUG_KMS("Preparing DDI mode on port %c, pipe %c\n", - port_name(port), pipe_name(pipe)); - - crtc->eld_vld = false; - if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) { - struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); - struct intel_digital_port *intel_dig_port = - enc_to_dig_port(&encoder->base); - - intel_dp->DP = intel_dig_port->saved_port_bits | - DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW; - intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count); - - if (intel_dp->has_audio) { - DRM_DEBUG_DRIVER("DP audio on pipe %c on DDI\n", - pipe_name(crtc->pipe)); - - /* write eld */ - DRM_DEBUG_DRIVER("DP audio: write eld information\n"); - intel_write_eld(&encoder->base, adjusted_mode); - } - } else if (type == INTEL_OUTPUT_HDMI) { - struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); - - if (intel_hdmi->has_audio) { - /* Proper support for digital audio needs a new logic - * and a new set of registers, so we leave it for future - * patch bombing. - */ - DRM_DEBUG_DRIVER("HDMI audio on pipe %c on DDI\n", - pipe_name(crtc->pipe)); - - /* write eld */ - DRM_DEBUG_DRIVER("HDMI audio: write eld information\n"); - intel_write_eld(&encoder->base, adjusted_mode); - } - - intel_hdmi->set_infoframes(&encoder->base, adjusted_mode); - } -} - static struct intel_encoder * intel_ddi_get_crtc_encoder(struct drm_crtc *crtc) { @@ -1062,9 +1013,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc) } if (type == INTEL_OUTPUT_HDMI) { - struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); - - if (intel_hdmi->has_hdmi_sink) + if (intel_crtc->config.has_hdmi_sink) temp |= TRANS_DDI_MODE_SELECT_HDMI; else temp |= TRANS_DDI_MODE_SELECT_DVI; @@ -1293,28 +1242,48 @@ void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc) static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; - struct drm_crtc *crtc = encoder->crtc; struct drm_i915_private *dev_priv = encoder->dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_crtc *crtc = to_intel_crtc(encoder->crtc); enum port port = intel_ddi_get_encoder_port(intel_encoder); int type = intel_encoder->type; + if (crtc->config.has_audio) { + DRM_DEBUG_DRIVER("Audio on pipe %c on DDI\n", + pipe_name(crtc->pipe)); + + /* write eld */ + DRM_DEBUG_DRIVER("DDI audio: write eld information\n"); + intel_write_eld(encoder, &crtc->config.adjusted_mode); + } + if (type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); intel_edp_panel_on(intel_dp); } - WARN_ON(intel_crtc->ddi_pll_sel == PORT_CLK_SEL_NONE); - I915_WRITE(PORT_CLK_SEL(port), intel_crtc->ddi_pll_sel); + WARN_ON(crtc->ddi_pll_sel == PORT_CLK_SEL_NONE); + I915_WRITE(PORT_CLK_SEL(port), crtc->ddi_pll_sel); if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + struct intel_digital_port *intel_dig_port = + enc_to_dig_port(encoder); + + intel_dp->DP = intel_dig_port->saved_port_bits | + DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW; + intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count); intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); intel_dp_start_link_train(intel_dp); intel_dp_complete_link_train(intel_dp); if (port != PORT_A) intel_dp_stop_link_train(intel_dp); + } else if (type == INTEL_OUTPUT_HDMI) { + struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + + intel_hdmi->set_infoframes(encoder, + crtc->config.has_hdmi_sink, + &crtc->config.adjusted_mode); } } @@ -1385,7 +1354,8 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder) intel_edp_psr_enable(intel_dp); } - if (intel_crtc->eld_vld && type != INTEL_OUTPUT_EDP) { + if (intel_crtc->config.has_audio) { + intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO); tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); tmp |= ((AUDIO_OUTPUT_ENABLE_A | AUDIO_ELD_VALID_A) << (pipe * 4)); I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp); @@ -1403,11 +1373,14 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder) struct drm_i915_private *dev_priv = dev->dev_private; uint32_t tmp; - if (intel_crtc->eld_vld && type != INTEL_OUTPUT_EDP) { + /* We can't touch HSW_AUD_PIN_ELD_CP_VLD uncionditionally because this + * register is part of the power well on Haswell. */ + if (intel_crtc->config.has_audio) { tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); tmp &= ~((AUDIO_OUTPUT_ENABLE_A | AUDIO_ELD_VALID_A) << (pipe * 4)); I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp); + intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO); } if (type == INTEL_OUTPUT_EDP) { @@ -1580,6 +1553,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder, switch (temp & TRANS_DDI_MODE_SELECT_MASK) { case TRANS_DDI_MODE_SELECT_HDMI: + pipe_config->has_hdmi_sink = true; case TRANS_DDI_MODE_SELECT_DVI: case TRANS_DDI_MODE_SELECT_FDI: break; @@ -1592,6 +1566,12 @@ void intel_ddi_get_config(struct intel_encoder *encoder, break; } + if (intel_display_power_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { + temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); + if (temp & (AUDIO_OUTPUT_ENABLE_A << (intel_crtc->pipe * 4))) + pipe_config->has_audio = true; + } + if (encoder->type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp_bpp && pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) { /* @@ -1708,7 +1688,6 @@ void intel_ddi_init(struct drm_device *dev, enum port port) DRM_MODE_ENCODER_TMDS); intel_encoder->compute_config = intel_ddi_compute_config; - intel_encoder->mode_set = intel_ddi_mode_set; intel_encoder->enable = intel_enable_ddi; intel_encoder->pre_enable = intel_ddi_pre_enable; intel_encoder->disable = intel_disable_ddi; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 72b5c34d8ce7..90f4f05c3000 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -41,6 +41,9 @@ #include <drm/drm_crtc_helper.h> #include <linux/dma_remapping.h> +#define DIV_ROUND_CLOSEST_ULL(ll, d) \ + ({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; }) + static void intel_increase_pllclock(struct drm_crtc *crtc); static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on); @@ -55,6 +58,15 @@ static int intel_framebuffer_init(struct drm_device *dev, struct intel_framebuffer *ifb, struct drm_mode_fb_cmd2 *mode_cmd, struct drm_i915_gem_object *obj); +static void intel_dp_set_m_n(struct intel_crtc *crtc); +static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc); +static void intel_set_pipe_timings(struct intel_crtc *intel_crtc); +static void intel_cpu_transcoder_set_m_n(struct intel_crtc *crtc, + struct intel_link_m_n *m_n); +static void ironlake_set_pipeconf(struct drm_crtc *crtc); +static void haswell_set_pipeconf(struct drm_crtc *crtc); +static void intel_set_pipe_csc(struct drm_crtc *crtc); +static void vlv_prepare_pll(struct intel_crtc *crtc); typedef struct { int min, max; @@ -328,6 +340,22 @@ static const intel_limit_t intel_limits_vlv = { .p2 = { .p2_slow = 2, .p2_fast = 20 }, /* slow=min, fast=max */ }; +static const intel_limit_t intel_limits_chv = { + /* + * These are the data rate limits (measured in fast clocks) + * since those are the strictest limits we have. The fast + * clock and actual rate limits are more relaxed, so checking + * them would make no difference. + */ + .dot = { .min = 25000 * 5, .max = 540000 * 5}, + .vco = { .min = 4860000, .max = 6700000 }, + .n = { .min = 1, .max = 1 }, + .m1 = { .min = 2, .max = 2 }, + .m2 = { .min = 24 << 22, .max = 175 << 22 }, + .p1 = { .min = 2, .max = 4 }, + .p2 = { .p2_slow = 1, .p2_fast = 14 }, +}; + static void vlv_clock(int refclk, intel_clock_t *clock) { clock->m = clock->m1 * clock->m2; @@ -412,6 +440,8 @@ static const intel_limit_t *intel_limit(struct drm_crtc *crtc, int refclk) limit = &intel_limits_pineview_lvds; else limit = &intel_limits_pineview_sdvo; + } else if (IS_CHERRYVIEW(dev)) { + limit = &intel_limits_chv; } else if (IS_VALLEYVIEW(dev)) { limit = &intel_limits_vlv; } else if (!IS_GEN2(dev)) { @@ -456,6 +486,17 @@ static void i9xx_clock(int refclk, intel_clock_t *clock) clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p); } +static void chv_clock(int refclk, intel_clock_t *clock) +{ + clock->m = clock->m1 * clock->m2; + clock->p = clock->p1 * clock->p2; + if (WARN_ON(clock->n == 0 || clock->p == 0)) + return; + clock->vco = DIV_ROUND_CLOSEST_ULL((uint64_t)refclk * clock->m, + clock->n << 22); + clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p); +} + #define INTELPllInvalid(s) do { /* DRM_DEBUG(s); */ return false; } while (0) /** * Returns whether the given set of divisors are valid for a given refclk with @@ -731,6 +772,58 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc, return found; } +static bool +chv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc, + int target, int refclk, intel_clock_t *match_clock, + intel_clock_t *best_clock) +{ + struct drm_device *dev = crtc->dev; + intel_clock_t clock; + uint64_t m2; + int found = false; + + memset(best_clock, 0, sizeof(*best_clock)); + + /* + * Based on hardware doc, the n always set to 1, and m1 always + * set to 2. If requires to support 200Mhz refclk, we need to + * revisit this because n may not 1 anymore. + */ + clock.n = 1, clock.m1 = 2; + target *= 5; /* fast clock */ + + for (clock.p1 = limit->p1.max; clock.p1 >= limit->p1.min; clock.p1--) { + for (clock.p2 = limit->p2.p2_fast; + clock.p2 >= limit->p2.p2_slow; + clock.p2 -= clock.p2 > 10 ? 2 : 1) { + + clock.p = clock.p1 * clock.p2; + + m2 = DIV_ROUND_CLOSEST_ULL(((uint64_t)target * clock.p * + clock.n) << 22, refclk * clock.m1); + + if (m2 > INT_MAX/clock.m1) + continue; + + clock.m2 = m2; + + chv_clock(refclk, &clock); + + if (!intel_PLL_is_valid(dev, limit, &clock)) + continue; + + /* based on hardware requirement, prefer bigger p + */ + if (clock.p > best_clock->p) { + *best_clock = clock; + found = true; + } + } + } + + return found; +} + bool intel_crtc_active(struct drm_crtc *crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); @@ -878,7 +971,7 @@ bool ibx_digital_port_connected(struct drm_i915_private *dev_priv, u32 bit; if (HAS_PCH_IBX(dev_priv->dev)) { - switch(port->port) { + switch (port->port) { case PORT_B: bit = SDE_PORTB_HOTPLUG; break; @@ -892,7 +985,7 @@ bool ibx_digital_port_connected(struct drm_i915_private *dev_priv, return true; } } else { - switch(port->port) { + switch (port->port) { case PORT_B: bit = SDE_PORTB_HOTPLUG_CPT; break; @@ -1097,10 +1190,8 @@ static void assert_cursor(struct drm_i915_private *dev_priv, if (IS_845G(dev) || IS_I865G(dev)) cur_state = I915_READ(_CURACNTR) & CURSOR_ENABLE; - else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) - cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; else - cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE; + cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE; WARN(cur_state != state, "cursor on pipe %c assertion failure (expected %s, current %s)\n", @@ -1253,6 +1344,9 @@ static bool dp_pipe_enabled(struct drm_i915_private *dev_priv, u32 trans_dp_ctl = I915_READ(trans_dp_ctl_reg); if ((trans_dp_ctl & TRANS_DP_PORT_SEL_MASK) != port_sel) return false; + } else if (IS_CHERRYVIEW(dev_priv->dev)) { + if ((val & DP_PIPE_MASK_CHV) != DP_PIPE_SELECT_CHV(pipe)) + return false; } else { if ((val & DP_PIPE_MASK) != (pipe << 30)) return false; @@ -1269,6 +1363,9 @@ static bool hdmi_pipe_enabled(struct drm_i915_private *dev_priv, if (HAS_PCH_CPT(dev_priv->dev)) { if ((val & SDVO_PIPE_SEL_MASK_CPT) != SDVO_PIPE_SEL_CPT(pipe)) return false; + } else if (IS_CHERRYVIEW(dev_priv->dev)) { + if ((val & SDVO_PIPE_SEL_MASK_CHV) != SDVO_PIPE_SEL_CHV(pipe)) + return false; } else { if ((val & SDVO_PIPE_SEL_MASK) != SDVO_PIPE_SEL(pipe)) return false; @@ -1367,7 +1464,17 @@ static void intel_init_dpio(struct drm_device *dev) if (!IS_VALLEYVIEW(dev)) return; - DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO; + /* + * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C), + * CHV x1 PHY (DP/HDMI D) + * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C) + */ + if (IS_CHERRYVIEW(dev)) { + DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2; + DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO; + } else { + DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO; + } } static void intel_reset_dpio(struct drm_device *dev) @@ -1385,17 +1492,42 @@ static void intel_reset_dpio(struct drm_device *dev) DPLL_REFA_CLK_ENABLE_VLV | DPLL_INTEGRATED_CRI_CLK_VLV); - /* - * From VLV2A0_DP_eDP_DPIO_driver_vbios_notes_10.docx - - * 6. De-assert cmn_reset/side_reset. Same as VLV X0. - * a. GUnit 0x2110 bit[0] set to 1 (def 0) - * b. The other bits such as sfr settings / modesel may all be set - * to 0. - * - * This should only be done on init and resume from S3 with both - * PLLs disabled, or we risk losing DPIO and PLL synchronization. - */ - I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) | DPIO_CMNRST); + if (IS_CHERRYVIEW(dev)) { + enum dpio_phy phy; + u32 val; + + for (phy = DPIO_PHY0; phy < I915_NUM_PHYS_VLV; phy++) { + /* Poll for phypwrgood signal */ + if (wait_for(I915_READ(DISPLAY_PHY_STATUS) & + PHY_POWERGOOD(phy), 1)) + DRM_ERROR("Display PHY %d is not power up\n", phy); + + /* + * Deassert common lane reset for PHY. + * + * This should only be done on init and resume from S3 + * with both PLLs disabled, or we risk losing DPIO and + * PLL synchronization. + */ + val = I915_READ(DISPLAY_PHY_CONTROL); + I915_WRITE(DISPLAY_PHY_CONTROL, + PHY_COM_LANE_RESET_DEASSERT(phy, val)); + } + + } else { + /* + * From VLV2A0_DP_eDP_DPIO_driver_vbios_notes_10.docx - + * 6. De-assert cmn_reset/side_reset. Same as VLV X0. + * a. GUnit 0x2110 bit[0] set to 1 (def 0) + * b. The other bits such as sfr settings / modesel may all + * be set to 0. + * + * This should only be done on init and resume from S3 with + * both PLLs disabled, or we risk losing DPIO and PLL + * synchronization. + */ + I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) | DPIO_CMNRST); + } } static void vlv_enable_pll(struct intel_crtc *crtc) @@ -1436,6 +1568,44 @@ static void vlv_enable_pll(struct intel_crtc *crtc) udelay(150); /* wait for warmup */ } +static void chv_enable_pll(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe = crtc->pipe; + enum dpio_channel port = vlv_pipe_to_channel(pipe); + u32 tmp; + + assert_pipe_disabled(dev_priv, crtc->pipe); + + BUG_ON(!IS_CHERRYVIEW(dev_priv->dev)); + + mutex_lock(&dev_priv->dpio_lock); + + /* Enable back the 10bit clock to display controller */ + tmp = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port)); + tmp |= DPIO_DCLKP_EN; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), tmp); + + /* + * Need to wait > 100ns between dclkp clock enable bit and PLL enable. + */ + udelay(1); + + /* Enable PLL */ + I915_WRITE(DPLL(pipe), crtc->config.dpll_hw_state.dpll); + + /* Check PLL is locked */ + if (wait_for(((I915_READ(DPLL(pipe)) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1)) + DRM_ERROR("PLL %d failed to lock\n", pipe); + + /* not sure when this should be written */ + I915_WRITE(DPLL_MD(pipe), crtc->config.dpll_hw_state.dpll_md); + POSTING_READ(DPLL_MD(pipe)); + + mutex_unlock(&dev_priv->dpio_lock); +} + static void i9xx_enable_pll(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; @@ -1519,45 +1689,92 @@ static void vlv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) val = DPLL_INTEGRATED_CRI_CLK_VLV | DPLL_REFA_CLK_ENABLE_VLV; I915_WRITE(DPLL(pipe), val); POSTING_READ(DPLL(pipe)); + +} + +static void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe) +{ + enum dpio_channel port = vlv_pipe_to_channel(pipe); + u32 val; + + /* Make sure the pipe isn't still relying on us */ + assert_pipe_disabled(dev_priv, pipe); + + /* Set PLL en = 0 */ + val = DPLL_SSC_REF_CLOCK_CHV; + if (pipe != PIPE_A) + val |= DPLL_INTEGRATED_CRI_CLK_VLV; + I915_WRITE(DPLL(pipe), val); + POSTING_READ(DPLL(pipe)); + + mutex_lock(&dev_priv->dpio_lock); + + /* Disable 10bit clock to display controller */ + val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port)); + val &= ~DPIO_DCLKP_EN; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), val); + + mutex_unlock(&dev_priv->dpio_lock); } void vlv_wait_port_ready(struct drm_i915_private *dev_priv, struct intel_digital_port *dport) { u32 port_mask; + int dpll_reg; switch (dport->port) { case PORT_B: port_mask = DPLL_PORTB_READY_MASK; + dpll_reg = DPLL(0); break; case PORT_C: port_mask = DPLL_PORTC_READY_MASK; + dpll_reg = DPLL(0); + break; + case PORT_D: + port_mask = DPLL_PORTD_READY_MASK; + dpll_reg = DPIO_PHY_STATUS; break; default: BUG(); } - if (wait_for((I915_READ(DPLL(0)) & port_mask) == 0, 1000)) + if (wait_for((I915_READ(dpll_reg) & port_mask) == 0, 1000)) WARN(1, "timed out waiting for port %c ready: 0x%08x\n", - port_name(dport->port), I915_READ(DPLL(0))); + port_name(dport->port), I915_READ(dpll_reg)); +} + +static void intel_prepare_shared_dpll(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc); + + WARN_ON(!pll->refcount); + if (pll->active == 0) { + DRM_DEBUG_DRIVER("setting up %s\n", pll->name); + WARN_ON(pll->on); + assert_shared_dpll_disabled(dev_priv, pll); + + pll->mode_set(dev_priv, pll); + } } /** - * ironlake_enable_shared_dpll - enable PCH PLL + * intel_enable_shared_dpll - enable PCH PLL * @dev_priv: i915 private structure * @pipe: pipe PLL to enable * * The PCH PLL needs to be enabled before the PCH transcoder, since it * drives the transcoder clock. */ -static void ironlake_enable_shared_dpll(struct intel_crtc *crtc) +static void intel_enable_shared_dpll(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc); - /* PCH PLLs only available on ILK, SNB and IVB */ - BUG_ON(INTEL_INFO(dev)->gen < 5); if (WARN_ON(pll == NULL)) return; @@ -1891,7 +2108,6 @@ static void intel_enable_primary_hw_plane(struct drm_i915_private *dev_priv, I915_WRITE(reg, val | DISPLAY_PLANE_ENABLE); intel_flush_primary_plane(dev_priv, plane); - intel_wait_for_vblank(dev_priv->dev, pipe); } /** @@ -1921,7 +2137,6 @@ static void intel_disable_primary_hw_plane(struct drm_i915_private *dev_priv, I915_WRITE(reg, val & ~DISPLAY_PLANE_ENABLE); intel_flush_primary_plane(dev_priv, plane); - intel_wait_for_vblank(dev_priv->dev, pipe); } static bool need_vtd_wa(struct drm_device *dev) @@ -1944,7 +2159,7 @@ static int intel_align_height(struct drm_device *dev, int height, bool tiled) int intel_pin_and_fence_fb_obj(struct drm_device *dev, struct drm_i915_gem_object *obj, - struct intel_ring_buffer *pipelined) + struct intel_engine_cs *pipelined) { struct drm_i915_private *dev_priv = dev->dev_private; u32 alignment; @@ -2124,7 +2339,7 @@ static void intel_find_plane_obj(struct intel_crtc *intel_crtc, * Failed to alloc the obj, check to see if we should share * an fb with another CRTC instead */ - list_for_each_entry(c, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, c) { i = to_intel_crtc(c); if (c == &intel_crtc->base) @@ -2142,9 +2357,9 @@ static void intel_find_plane_obj(struct intel_crtc *intel_crtc, } } -static int i9xx_update_primary_plane(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y) +static void i9xx_update_primary_plane(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + int x, int y) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2230,13 +2445,11 @@ static int i9xx_update_primary_plane(struct drm_crtc *crtc, } else I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset); POSTING_READ(reg); - - return 0; } -static int ironlake_update_primary_plane(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - int x, int y) +static void ironlake_update_primary_plane(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + int x, int y) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -2314,8 +2527,6 @@ static int ironlake_update_primary_plane(struct drm_crtc *crtc, I915_WRITE(DSPLINOFF(plane), linear_offset); } POSTING_READ(reg); - - return 0; } /* Assume fb object is pinned & idle & fenced and just update base pointers */ @@ -2330,7 +2541,9 @@ intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb, dev_priv->display.disable_fbc(dev); intel_increase_pllclock(crtc); - return dev_priv->display.update_primary_plane(crtc, fb, x, y); + dev_priv->display.update_primary_plane(crtc, fb, x, y); + + return 0; } void intel_display_handle_reset(struct drm_device *dev) @@ -2352,7 +2565,7 @@ void intel_display_handle_reset(struct drm_device *dev) * pending_flip_queue really got woken up. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); enum plane plane = intel_crtc->plane; @@ -2360,7 +2573,7 @@ void intel_display_handle_reset(struct drm_device *dev) intel_finish_page_flip_plane(dev, plane); } - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { struct intel_crtc *intel_crtc = to_intel_crtc(crtc); mutex_lock(&crtc->mutex); @@ -2489,14 +2702,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, intel_crtc->config.pipe_src_h = adjusted_mode->crtc_vdisplay; } - ret = dev_priv->display.update_primary_plane(crtc, fb, x, y); - if (ret) { - mutex_lock(&dev->struct_mutex); - intel_unpin_fb_obj(to_intel_framebuffer(fb)->obj); - mutex_unlock(&dev->struct_mutex); - DRM_ERROR("failed to update base address\n"); - return ret; - } + dev_priv->display.update_primary_plane(crtc, fb, x, y); old_fb = crtc->primary->fb; crtc->primary->fb = fb; @@ -3033,9 +3239,8 @@ static void ironlake_fdi_disable(struct drm_crtc *crtc) udelay(100); /* Ironlake workaround, disable clock pointer after downing FDI */ - if (HAS_PCH_IBX(dev)) { + if (HAS_PCH_IBX(dev)) I915_WRITE(FDI_RX_CHICKEN(pipe), FDI_RX_PHASE_SYNC_POINTER_OVR); - } /* still set train pattern 1 */ reg = FDI_TX_CTL(pipe); @@ -3073,7 +3278,7 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev) * cannot claim and pin a new fb without at least acquring the * struct_mutex and so serialising with us. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { if (atomic_read(&crtc->unpin_work_count) == 0) continue; @@ -3086,7 +3291,7 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev) return false; } -static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) +void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -3096,8 +3301,9 @@ static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) WARN_ON(waitqueue_active(&dev_priv->pending_flip_queue)); - wait_event(dev_priv->pending_flip_queue, - !intel_crtc_has_pending_flip(crtc)); + WARN_ON(wait_event_timeout(dev_priv->pending_flip_queue, + !intel_crtc_has_pending_flip(crtc), + 60*HZ) == 0); mutex_lock(&dev->struct_mutex); intel_finish_fb(crtc->primary->fb); @@ -3310,7 +3516,7 @@ static void ironlake_pch_enable(struct drm_crtc *crtc) * Note that enable_shared_dpll tries to do the right thing, but * get_shared_dpll unconditionally resets the pll - we need that to have * the right LVDS enable sequence. */ - ironlake_enable_shared_dpll(intel_crtc); + intel_enable_shared_dpll(intel_crtc); /* set transcoder timing, panel must allow it */ assert_panel_unlocked(dev_priv, pipe); @@ -3414,6 +3620,8 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc) DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n", crtc->base.base.id, pll->name); + WARN_ON(pll->refcount); + goto found; } @@ -3447,20 +3655,13 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc) return NULL; found: + if (pll->refcount == 0) + pll->hw_state = crtc->config.dpll_hw_state; + crtc->config.shared_dpll = i; DRM_DEBUG_DRIVER("using %s for pipe %c\n", pll->name, pipe_name(crtc->pipe)); - if (pll->active == 0) { - memcpy(&pll->hw_state, &crtc->config.dpll_hw_state, - sizeof(pll->hw_state)); - - DRM_DEBUG_DRIVER("setting up %s\n", pll->name); - WARN_ON(pll->on); - assert_shared_dpll_disabled(dev_priv, pll); - - pll->mode_set(dev_priv, pll); - } pll->refcount++; return pll; @@ -3531,17 +3732,17 @@ static void intel_disable_planes(struct drm_crtc *crtc) void hsw_enable_ips(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = crtc->base.dev->dev_private; + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; if (!crtc->config.ips_enabled) return; - /* We can only enable IPS after we enable a plane and wait for a vblank. - * We guarantee that the plane is enabled by calling intel_enable_ips - * only after intel_enable_plane. And intel_enable_plane already waits - * for a vblank, so all we need to do here is to enable the IPS bit. */ + /* We can only enable IPS after we enable a plane and wait for a vblank */ + intel_wait_for_vblank(dev, crtc->pipe); + assert_plane_enabled(dev_priv, crtc->plane); - if (IS_BROADWELL(crtc->base.dev)) { + if (IS_BROADWELL(dev)) { mutex_lock(&dev_priv->rps.hw_lock); WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0xc0000000)); mutex_unlock(&dev_priv->rps.hw_lock); @@ -3634,7 +3835,49 @@ static void intel_crtc_load_lut(struct drm_crtc *crtc) hsw_enable_ips(intel_crtc); } -static void ilk_crtc_enable_planes(struct drm_crtc *crtc) +static void intel_crtc_dpms_overlay(struct intel_crtc *intel_crtc, bool enable) +{ + if (!enable && intel_crtc->overlay) { + struct drm_device *dev = intel_crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + mutex_lock(&dev->struct_mutex); + dev_priv->mm.interruptible = false; + (void) intel_overlay_switch_off(intel_crtc->overlay); + dev_priv->mm.interruptible = true; + mutex_unlock(&dev->struct_mutex); + } + + /* Let userspace switch the overlay on again. In most cases userspace + * has to recompute where to put it anyway. + */ +} + +/** + * i9xx_fixup_plane - ugly workaround for G45 to fire up the hardware + * cursor plane briefly if not already running after enabling the display + * plane. + * This workaround avoids occasional blank screens when self refresh is + * enabled. + */ +static void +g4x_fixup_plane(struct drm_i915_private *dev_priv, enum pipe pipe) +{ + u32 cntl = I915_READ(CURCNTR(pipe)); + + if ((cntl & CURSOR_MODE) == 0) { + u32 fw_bcl_self = I915_READ(FW_BLC_SELF); + + I915_WRITE(FW_BLC_SELF, fw_bcl_self & ~FW_BLC_SELF_EN); + I915_WRITE(CURCNTR(pipe), CURSOR_MODE_64_ARGB_AX); + intel_wait_for_vblank(dev_priv->dev, pipe); + I915_WRITE(CURCNTR(pipe), cntl); + I915_WRITE(CURBASE(pipe), I915_READ(CURBASE(pipe))); + I915_WRITE(FW_BLC_SELF, fw_bcl_self); + } +} + +static void intel_crtc_enable_planes(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -3644,16 +3887,21 @@ static void ilk_crtc_enable_planes(struct drm_crtc *crtc) intel_enable_primary_hw_plane(dev_priv, plane, pipe); intel_enable_planes(crtc); + /* The fixup needs to happen before cursor is enabled */ + if (IS_G4X(dev)) + g4x_fixup_plane(dev_priv, pipe); intel_crtc_update_cursor(crtc, true); + intel_crtc_dpms_overlay(intel_crtc, true); hsw_enable_ips(intel_crtc); mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); + intel_edp_psr_update(dev); mutex_unlock(&dev->struct_mutex); } -static void ilk_crtc_disable_planes(struct drm_crtc *crtc) +static void intel_crtc_disable_planes(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -3662,13 +3910,14 @@ static void ilk_crtc_disable_planes(struct drm_crtc *crtc) int plane = intel_crtc->plane; intel_crtc_wait_for_pending_flips(crtc); - drm_vblank_off(dev, pipe); + drm_crtc_vblank_off(crtc); if (dev_priv->fbc.plane == plane) intel_disable_fbc(dev); hsw_disable_ips(intel_crtc); + intel_crtc_dpms_overlay(intel_crtc, false); intel_crtc_update_cursor(crtc, false); intel_disable_planes(crtc); intel_disable_primary_hw_plane(dev_priv, plane, pipe); @@ -3681,12 +3930,35 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_encoder *encoder; int pipe = intel_crtc->pipe; + enum plane plane = intel_crtc->plane; WARN_ON(!crtc->enabled); if (intel_crtc->active) return; + if (intel_crtc->config.has_pch_encoder) + intel_prepare_shared_dpll(intel_crtc); + + if (intel_crtc->config.has_dp_encoder) + intel_dp_set_m_n(intel_crtc); + + intel_set_pipe_timings(intel_crtc); + + if (intel_crtc->config.has_pch_encoder) { + intel_cpu_transcoder_set_m_n(intel_crtc, + &intel_crtc->config.fdi_m_n); + } + + ironlake_set_pipeconf(crtc); + + /* Set up the display plane register */ + I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE); + POSTING_READ(DSPCNTR(plane)); + + dev_priv->display.update_primary_plane(crtc, crtc->primary->fb, + crtc->x, crtc->y); + intel_crtc->active = true; intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); @@ -3726,17 +3998,9 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc) if (HAS_PCH_CPT(dev)) cpt_verify_modeset(dev, intel_crtc->pipe); - ilk_crtc_enable_planes(crtc); + intel_crtc_enable_planes(crtc); - /* - * There seems to be a race in PCH platform hw (at least on some - * outputs) where an enabled pipe still completes any pageflip right - * away (as if the pipe is off) instead of waiting for vblank. As soon - * as the first vblank happend, everything works as expected. Hence just - * wait for one vblank before returning to avoid strange things - * happening. - */ - intel_wait_for_vblank(dev, intel_crtc->pipe); + drm_crtc_vblank_on(crtc); } /* IPS only exists on ULT machines and is tied to pipe A. */ @@ -3758,7 +4022,7 @@ static void haswell_mode_set_planes_workaround(struct intel_crtc *crtc) /* We want to get the other_active_crtc only if there's only 1 other * active crtc. */ - list_for_each_entry(crtc_it, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc_it) { if (!crtc_it->active || crtc_it == crtc) continue; @@ -3781,12 +4045,34 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_encoder *encoder; int pipe = intel_crtc->pipe; + enum plane plane = intel_crtc->plane; WARN_ON(!crtc->enabled); if (intel_crtc->active) return; + if (intel_crtc->config.has_dp_encoder) + intel_dp_set_m_n(intel_crtc); + + intel_set_pipe_timings(intel_crtc); + + if (intel_crtc->config.has_pch_encoder) { + intel_cpu_transcoder_set_m_n(intel_crtc, + &intel_crtc->config.fdi_m_n); + } + + haswell_set_pipeconf(crtc); + + intel_set_pipe_csc(crtc); + + /* Set up the display plane register */ + I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE | DISPPLANE_PIPE_CSC_ENABLE); + POSTING_READ(DSPCNTR(plane)); + + dev_priv->display.update_primary_plane(crtc, crtc->primary->fb, + crtc->x, crtc->y); + intel_crtc->active = true; intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); @@ -3827,7 +4113,9 @@ static void haswell_crtc_enable(struct drm_crtc *crtc) /* If we change the relative order between pipe/planes enabling, we need * to change the workaround. */ haswell_mode_set_planes_workaround(intel_crtc); - ilk_crtc_enable_planes(crtc); + intel_crtc_enable_planes(crtc); + + drm_crtc_vblank_on(crtc); } static void ironlake_pfit_disable(struct intel_crtc *crtc) @@ -3857,7 +4145,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) if (!intel_crtc->active) return; - ilk_crtc_disable_planes(crtc); + intel_crtc_disable_planes(crtc); for_each_encoder_on_crtc(dev, crtc, encoder) encoder->disable(encoder); @@ -3905,6 +4193,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); + intel_edp_psr_update(dev); mutex_unlock(&dev->struct_mutex); } @@ -3920,7 +4209,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) if (!intel_crtc->active) return; - ilk_crtc_disable_planes(crtc); + intel_crtc_disable_planes(crtc); for_each_encoder_on_crtc(dev, crtc, encoder) { intel_opregion_notify_encoder(encoder, false); @@ -3952,6 +4241,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); + intel_edp_psr_update(dev); mutex_unlock(&dev->struct_mutex); } @@ -3966,48 +4256,6 @@ static void haswell_crtc_off(struct drm_crtc *crtc) intel_ddi_put_crtc_pll(crtc); } -static void intel_crtc_dpms_overlay(struct intel_crtc *intel_crtc, bool enable) -{ - if (!enable && intel_crtc->overlay) { - struct drm_device *dev = intel_crtc->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - - mutex_lock(&dev->struct_mutex); - dev_priv->mm.interruptible = false; - (void) intel_overlay_switch_off(intel_crtc->overlay); - dev_priv->mm.interruptible = true; - mutex_unlock(&dev->struct_mutex); - } - - /* Let userspace switch the overlay on again. In most cases userspace - * has to recompute where to put it anyway. - */ -} - -/** - * i9xx_fixup_plane - ugly workaround for G45 to fire up the hardware - * cursor plane briefly if not already running after enabling the display - * plane. - * This workaround avoids occasional blank screens when self refresh is - * enabled. - */ -static void -g4x_fixup_plane(struct drm_i915_private *dev_priv, enum pipe pipe) -{ - u32 cntl = I915_READ(CURCNTR(pipe)); - - if ((cntl & CURSOR_MODE) == 0) { - u32 fw_bcl_self = I915_READ(FW_BLC_SELF); - - I915_WRITE(FW_BLC_SELF, fw_bcl_self & ~FW_BLC_SELF_EN); - I915_WRITE(CURCNTR(pipe), CURSOR_MODE_64_ARGB_AX); - intel_wait_for_vblank(dev_priv->dev, pipe); - I915_WRITE(CURCNTR(pipe), cntl); - I915_WRITE(CURBASE(pipe), I915_READ(CURBASE(pipe))); - I915_WRITE(FW_BLC_SELF, fw_bcl_self); - } -} - static void i9xx_pfit_enable(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; @@ -4119,7 +4367,7 @@ static void modeset_update_crtc_power_domains(struct drm_device *dev) * First get all needed power domains, then put all unneeded, to avoid * any unnecessary toggling of the power wells. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { enum intel_display_power_domain domain; if (!crtc->base.enabled) @@ -4131,7 +4379,7 @@ static void modeset_update_crtc_power_domains(struct drm_device *dev) intel_display_power_get(dev_priv, domain); } - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { enum intel_display_power_domain domain; for_each_power_domain(domain, crtc->enabled_power_domains) @@ -4265,8 +4513,7 @@ static int intel_mode_max_pixclk(struct drm_i915_private *dev_priv) struct intel_crtc *intel_crtc; int max_pixclk = 0; - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, intel_crtc) { if (intel_crtc->new_enabled) max_pixclk = max(max_pixclk, intel_crtc->new_config->adjusted_mode.crtc_clock); @@ -4287,8 +4534,7 @@ static void valleyview_modeset_global_pipes(struct drm_device *dev, return; /* disable/enable all currently active pipes while we change cdclk */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, - base.head) + for_each_intel_crtc(dev, intel_crtc) if (intel_crtc->base.enabled) *prepare_pipes |= (1 << intel_crtc->pipe); } @@ -4313,22 +4559,55 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc) int pipe = intel_crtc->pipe; int plane = intel_crtc->plane; bool is_dsi; + u32 dspcntr; WARN_ON(!crtc->enabled); if (intel_crtc->active) return; + vlv_prepare_pll(intel_crtc); + + /* Set up the display plane register */ + dspcntr = DISPPLANE_GAMMA_ENABLE; + + if (intel_crtc->config.has_dp_encoder) + intel_dp_set_m_n(intel_crtc); + + intel_set_pipe_timings(intel_crtc); + + /* pipesrc and dspsize control the size that is scaled from, + * which should always be the user's requested size. + */ + I915_WRITE(DSPSIZE(plane), + ((intel_crtc->config.pipe_src_h - 1) << 16) | + (intel_crtc->config.pipe_src_w - 1)); + I915_WRITE(DSPPOS(plane), 0); + + i9xx_set_pipeconf(intel_crtc); + + I915_WRITE(DSPCNTR(plane), dspcntr); + POSTING_READ(DSPCNTR(plane)); + + dev_priv->display.update_primary_plane(crtc, crtc->primary->fb, + crtc->x, crtc->y); + intel_crtc->active = true; + intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); + for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->pre_pll_enable) encoder->pre_pll_enable(encoder); is_dsi = intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI); - if (!is_dsi) - vlv_enable_pll(intel_crtc); + if (!is_dsi) { + if (IS_CHERRYVIEW(dev)) + chv_enable_pll(intel_crtc); + else + vlv_enable_pll(intel_crtc); + } for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->pre_enable) @@ -4340,17 +4619,25 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc) intel_update_watermarks(crtc); intel_enable_pipe(intel_crtc); - intel_wait_for_vblank(dev_priv->dev, pipe); - intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); - - intel_enable_primary_hw_plane(dev_priv, plane, pipe); - intel_enable_planes(crtc); - intel_crtc_update_cursor(crtc, true); - - intel_update_fbc(dev); for_each_encoder_on_crtc(dev, crtc, encoder) encoder->enable(encoder); + + intel_crtc_enable_planes(crtc); + + drm_crtc_vblank_on(crtc); + + /* Underruns don't raise interrupts, so check manually. */ + i9xx_check_fifo_underruns(dev); +} + +static void i9xx_set_pll_dividers(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + I915_WRITE(FP0(crtc->pipe), crtc->config.dpll_hw_state.fp0); + I915_WRITE(FP1(crtc->pipe), crtc->config.dpll_hw_state.fp1); } static void i9xx_crtc_enable(struct drm_crtc *crtc) @@ -4361,14 +4648,49 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc) struct intel_encoder *encoder; int pipe = intel_crtc->pipe; int plane = intel_crtc->plane; + u32 dspcntr; WARN_ON(!crtc->enabled); if (intel_crtc->active) return; + i9xx_set_pll_dividers(intel_crtc); + + /* Set up the display plane register */ + dspcntr = DISPPLANE_GAMMA_ENABLE; + + if (pipe == 0) + dspcntr &= ~DISPPLANE_SEL_PIPE_MASK; + else + dspcntr |= DISPPLANE_SEL_PIPE_B; + + if (intel_crtc->config.has_dp_encoder) + intel_dp_set_m_n(intel_crtc); + + intel_set_pipe_timings(intel_crtc); + + /* pipesrc and dspsize control the size that is scaled from, + * which should always be the user's requested size. + */ + I915_WRITE(DSPSIZE(plane), + ((intel_crtc->config.pipe_src_h - 1) << 16) | + (intel_crtc->config.pipe_src_w - 1)); + I915_WRITE(DSPPOS(plane), 0); + + i9xx_set_pipeconf(intel_crtc); + + I915_WRITE(DSPCNTR(plane), dspcntr); + POSTING_READ(DSPCNTR(plane)); + + dev_priv->display.update_primary_plane(crtc, crtc->primary->fb, + crtc->x, crtc->y); + intel_crtc->active = true; + if (!IS_GEN2(dev)) + intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); + for_each_encoder_on_crtc(dev, crtc, encoder) if (encoder->pre_enable) encoder->pre_enable(encoder); @@ -4381,23 +4703,26 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc) intel_update_watermarks(crtc); intel_enable_pipe(intel_crtc); - intel_wait_for_vblank(dev_priv->dev, pipe); - intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); - intel_enable_primary_hw_plane(dev_priv, plane, pipe); - intel_enable_planes(crtc); - /* The fixup needs to happen before cursor is enabled */ - if (IS_G4X(dev)) - g4x_fixup_plane(dev_priv, pipe); - intel_crtc_update_cursor(crtc, true); + for_each_encoder_on_crtc(dev, crtc, encoder) + encoder->enable(encoder); - /* Give the overlay scaler a chance to enable if it's on this pipe */ - intel_crtc_dpms_overlay(intel_crtc, true); + intel_crtc_enable_planes(crtc); - intel_update_fbc(dev); + /* + * Gen2 reports pipe underruns whenever all planes are disabled. + * So don't enable underrun reporting before at least some planes + * are enabled. + * FIXME: Need to fix the logic to work when we turn off all planes + * but leave the pipe running. + */ + if (IS_GEN2(dev)) + intel_set_cpu_fifo_underrun_reporting(dev, pipe, true); - for_each_encoder_on_crtc(dev, crtc, encoder) - encoder->enable(encoder); + drm_crtc_vblank_on(crtc); + + /* Underruns don't raise interrupts, so check manually. */ + i9xx_check_fifo_underruns(dev); } static void i9xx_pfit_disable(struct intel_crtc *crtc) @@ -4422,27 +4747,31 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc) struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_encoder *encoder; int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; if (!intel_crtc->active) return; - for_each_encoder_on_crtc(dev, crtc, encoder) - encoder->disable(encoder); + /* + * Gen2 reports pipe underruns whenever all planes are disabled. + * So diasble underrun reporting before all the planes get disabled. + * FIXME: Need to fix the logic to work when we turn off all planes + * but leave the pipe running. + */ + if (IS_GEN2(dev)) + intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); - /* Give the overlay scaler a chance to disable if it's on this pipe */ - intel_crtc_wait_for_pending_flips(crtc); - drm_vblank_off(dev, pipe); + intel_crtc_disable_planes(crtc); - if (dev_priv->fbc.plane == plane) - intel_disable_fbc(dev); + for_each_encoder_on_crtc(dev, crtc, encoder) + encoder->disable(encoder); - intel_crtc_dpms_overlay(intel_crtc, false); - intel_crtc_update_cursor(crtc, false); - intel_disable_planes(crtc); - intel_disable_primary_hw_plane(dev_priv, plane, pipe); + /* + * On gen2 planes are double buffered but the pipe isn't, so we must + * wait for planes to fully turn off before disabling the pipe. + */ + if (IS_GEN2(dev)) + intel_wait_for_vblank(dev, pipe); - intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); intel_disable_pipe(dev_priv, pipe); i9xx_pfit_disable(intel_crtc); @@ -4451,15 +4780,25 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc) if (encoder->post_disable) encoder->post_disable(encoder); - if (IS_VALLEYVIEW(dev) && !intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI)) - vlv_disable_pll(dev_priv, pipe); - else if (!IS_VALLEYVIEW(dev)) - i9xx_disable_pll(dev_priv, pipe); + if (!intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI)) { + if (IS_CHERRYVIEW(dev)) + chv_disable_pll(dev_priv, pipe); + else if (IS_VALLEYVIEW(dev)) + vlv_disable_pll(dev_priv, pipe); + else + i9xx_disable_pll(dev_priv, pipe); + } + + if (!IS_GEN2(dev)) + intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); intel_crtc->active = false; intel_update_watermarks(crtc); + mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); + intel_edp_psr_update(dev); + mutex_unlock(&dev->struct_mutex); } static void i9xx_crtc_off(struct drm_crtc *crtc) @@ -4522,13 +4861,11 @@ static void intel_crtc_disable(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct drm_connector *connector; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); /* crtc should still be enabled when we disable it. */ WARN_ON(!crtc->enabled); dev_priv->display.crtc_disable(crtc); - intel_crtc->eld_vld = false; intel_crtc_update_sarea(crtc, false); dev_priv->display.off(crtc); @@ -4996,8 +5333,6 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc, intel_clock_t *reduced_clock) { struct drm_device *dev = crtc->base.dev; - struct drm_i915_private *dev_priv = dev->dev_private; - int pipe = crtc->pipe; u32 fp, fp2 = 0; if (IS_PINEVIEW(dev)) { @@ -5010,17 +5345,14 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc, fp2 = i9xx_dpll_compute_fp(reduced_clock); } - I915_WRITE(FP0(pipe), fp); crtc->config.dpll_hw_state.fp0 = fp; crtc->lowfreq_avail = false; if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) && reduced_clock && i915.powersave) { - I915_WRITE(FP1(pipe), fp2); crtc->config.dpll_hw_state.fp1 = fp2; crtc->lowfreq_avail = true; } else { - I915_WRITE(FP1(pipe), fp); crtc->config.dpll_hw_state.fp1 = fp; } } @@ -5098,12 +5430,34 @@ static void intel_dp_set_m_n(struct intel_crtc *crtc) static void vlv_update_pll(struct intel_crtc *crtc) { + u32 dpll, dpll_md; + + /* + * Enable DPIO clock input. We should never disable the reference + * clock for pipe B, since VGA hotplug / manual detection depends + * on it. + */ + dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV | + DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV; + /* We should never disable this, set it here for state tracking */ + if (crtc->pipe == PIPE_B) + dpll |= DPLL_INTEGRATED_CRI_CLK_VLV; + dpll |= DPLL_VCO_ENABLE; + crtc->config.dpll_hw_state.dpll = dpll; + + dpll_md = (crtc->config.pixel_multiplier - 1) + << DPLL_MD_UDI_MULTIPLIER_SHIFT; + crtc->config.dpll_hw_state.dpll_md = dpll_md; +} + +static void vlv_prepare_pll(struct intel_crtc *crtc) +{ struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; int pipe = crtc->pipe; - u32 dpll, mdiv; + u32 mdiv; u32 bestn, bestm1, bestm2, bestp1, bestp2; - u32 coreclk, reg_val, dpll_md; + u32 coreclk, reg_val; mutex_lock(&dev_priv->dpio_lock); @@ -5116,7 +5470,7 @@ static void vlv_update_pll(struct intel_crtc *crtc) /* See eDP HDMI DPIO driver vbios notes doc */ /* PLL B needs special handling */ - if (pipe) + if (pipe == PIPE_B) vlv_pllb_recal_opamp(dev_priv, pipe); /* Set up Tx target for periodic Rcomp update */ @@ -5160,7 +5514,7 @@ static void vlv_update_pll(struct intel_crtc *crtc) if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_EDP) || intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT)) { /* Use SSC source */ - if (!pipe) + if (pipe == PIPE_A) vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe), 0x0df40000); else @@ -5168,7 +5522,7 @@ static void vlv_update_pll(struct intel_crtc *crtc) 0x0df70000); } else { /* HDMI or VGA */ /* Use bend source */ - if (!pipe) + if (pipe == PIPE_A) vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe), 0x0df70000); else @@ -5184,23 +5538,84 @@ static void vlv_update_pll(struct intel_crtc *crtc) vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW7(pipe), coreclk); vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW11(pipe), 0x87871000); + mutex_unlock(&dev_priv->dpio_lock); +} + +static void chv_update_pll(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe = crtc->pipe; + int dpll_reg = DPLL(crtc->pipe); + enum dpio_channel port = vlv_pipe_to_channel(pipe); + u32 loopfilter, intcoeff; + u32 bestn, bestm1, bestm2, bestp1, bestp2, bestm2_frac; + int refclk; + + crtc->config.dpll_hw_state.dpll = DPLL_SSC_REF_CLOCK_CHV | + DPLL_REFA_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS | + DPLL_VCO_ENABLE; + if (pipe != PIPE_A) + crtc->config.dpll_hw_state.dpll |= DPLL_INTEGRATED_CRI_CLK_VLV; + + crtc->config.dpll_hw_state.dpll_md = + (crtc->config.pixel_multiplier - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT; + + bestn = crtc->config.dpll.n; + bestm2_frac = crtc->config.dpll.m2 & 0x3fffff; + bestm1 = crtc->config.dpll.m1; + bestm2 = crtc->config.dpll.m2 >> 22; + bestp1 = crtc->config.dpll.p1; + bestp2 = crtc->config.dpll.p2; /* - * Enable DPIO clock input. We should never disable the reference - * clock for pipe B, since VGA hotplug / manual detection depends - * on it. + * Enable Refclk and SSC */ - dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV | - DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV; - /* We should never disable this, set it here for state tracking */ - if (pipe == PIPE_B) - dpll |= DPLL_INTEGRATED_CRI_CLK_VLV; - dpll |= DPLL_VCO_ENABLE; - crtc->config.dpll_hw_state.dpll = dpll; + I915_WRITE(dpll_reg, + crtc->config.dpll_hw_state.dpll & ~DPLL_VCO_ENABLE); - dpll_md = (crtc->config.pixel_multiplier - 1) - << DPLL_MD_UDI_MULTIPLIER_SHIFT; - crtc->config.dpll_hw_state.dpll_md = dpll_md; + mutex_lock(&dev_priv->dpio_lock); + + /* p1 and p2 divider */ + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW13(port), + 5 << DPIO_CHV_S1_DIV_SHIFT | + bestp1 << DPIO_CHV_P1_DIV_SHIFT | + bestp2 << DPIO_CHV_P2_DIV_SHIFT | + 1 << DPIO_CHV_K_DIV_SHIFT); + + /* Feedback post-divider - m2 */ + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW0(port), bestm2); + + /* Feedback refclk divider - n and m1 */ + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW1(port), + DPIO_CHV_M1_DIV_BY_2 | + 1 << DPIO_CHV_N_DIV_SHIFT); + + /* M2 fraction division */ + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW2(port), bestm2_frac); + + /* M2 fraction division enable */ + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW3(port), + DPIO_CHV_FRAC_DIV_EN | + (2 << DPIO_CHV_FEEDFWD_GAIN_SHIFT)); + + /* Loop filter */ + refclk = i9xx_get_refclk(&crtc->base, 0); + loopfilter = 5 << DPIO_CHV_PROP_COEFF_SHIFT | + 2 << DPIO_CHV_GAIN_CTRL_SHIFT; + if (refclk == 100000) + intcoeff = 11; + else if (refclk == 38400) + intcoeff = 10; + else + intcoeff = 9; + loopfilter |= intcoeff << DPIO_CHV_INT_COEFF_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW6(port), loopfilter); + + /* AFC Recal */ + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), + vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port)) | + DPIO_AFC_RECAL); mutex_unlock(&dev_priv->dpio_lock); } @@ -5518,16 +5933,12 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; int refclk, num_connectors = 0; intel_clock_t clock, reduced_clock; - u32 dspcntr; bool ok, has_reduced_clock = false; bool is_lvds = false, is_dsi = false; struct intel_encoder *encoder; const intel_limit_t *limit; - int ret; for_each_encoder_on_crtc(dev, crtc, encoder) { switch (encoder->type) { @@ -5543,7 +5954,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, } if (is_dsi) - goto skip_dpll; + return 0; if (!intel_crtc->config.clock_set) { refclk = i9xx_get_refclk(crtc, num_connectors); @@ -5588,46 +5999,17 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, i8xx_update_pll(intel_crtc, has_reduced_clock ? &reduced_clock : NULL, num_connectors); + } else if (IS_CHERRYVIEW(dev)) { + chv_update_pll(intel_crtc); } else if (IS_VALLEYVIEW(dev)) { vlv_update_pll(intel_crtc); } else { i9xx_update_pll(intel_crtc, has_reduced_clock ? &reduced_clock : NULL, - num_connectors); - } - -skip_dpll: - /* Set up the display plane register */ - dspcntr = DISPPLANE_GAMMA_ENABLE; - - if (!IS_VALLEYVIEW(dev)) { - if (pipe == 0) - dspcntr &= ~DISPPLANE_SEL_PIPE_MASK; - else - dspcntr |= DISPPLANE_SEL_PIPE_B; + num_connectors); } - if (intel_crtc->config.has_dp_encoder) - intel_dp_set_m_n(intel_crtc); - - intel_set_pipe_timings(intel_crtc); - - /* pipesrc and dspsize control the size that is scaled from, - * which should always be the user's requested size. - */ - I915_WRITE(DSPSIZE(plane), - ((intel_crtc->config.pipe_src_h - 1) << 16) | - (intel_crtc->config.pipe_src_w - 1)); - I915_WRITE(DSPPOS(plane), 0); - - i9xx_set_pipeconf(intel_crtc); - - I915_WRITE(DSPCNTR(plane), dspcntr); - POSTING_READ(DSPCNTR(plane)); - - ret = intel_pipe_set_base(crtc, x, y, fb); - - return ret; + return 0; } static void i9xx_get_pfit_config(struct intel_crtc *crtc, @@ -5747,6 +6129,36 @@ static void i9xx_get_plane_config(struct intel_crtc *crtc, } +static void chv_crtc_clock_get(struct intel_crtc *crtc, + struct intel_crtc_config *pipe_config) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int pipe = pipe_config->cpu_transcoder; + enum dpio_channel port = vlv_pipe_to_channel(pipe); + intel_clock_t clock; + u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2; + int refclk = 100000; + + mutex_lock(&dev_priv->dpio_lock); + cmn_dw13 = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW13(port)); + pll_dw0 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW0(port)); + pll_dw1 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW1(port)); + pll_dw2 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW2(port)); + mutex_unlock(&dev_priv->dpio_lock); + + clock.m1 = (pll_dw1 & 0x7) == DPIO_CHV_M1_DIV_BY_2 ? 2 : 0; + clock.m2 = ((pll_dw0 & 0xff) << 22) | (pll_dw2 & 0x3fffff); + clock.n = (pll_dw1 >> DPIO_CHV_N_DIV_SHIFT) & 0xf; + clock.p1 = (cmn_dw13 >> DPIO_CHV_P1_DIV_SHIFT) & 0x7; + clock.p2 = (cmn_dw13 >> DPIO_CHV_P2_DIV_SHIFT) & 0x1f; + + chv_clock(refclk, &clock); + + /* clock.dot is the fast clock */ + pipe_config->port_clock = clock.dot / 5; +} + static bool i9xx_get_pipe_config(struct intel_crtc *crtc, struct intel_crtc_config *pipe_config) { @@ -5781,6 +6193,9 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, } } + if (IS_VALLEYVIEW(dev) && (tmp & PIPECONF_COLOR_RANGE_SELECT)) + pipe_config->limited_color_range = true; + if (INTEL_INFO(dev)->gen < 4) pipe_config->double_wide = tmp & PIPECONF_DOUBLE_WIDE; @@ -5816,7 +6231,9 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, DPLL_PORTB_READY_MASK); } - if (IS_VALLEYVIEW(dev)) + if (IS_CHERRYVIEW(dev)) + chv_crtc_clock_get(crtc, pipe_config); + else if (IS_VALLEYVIEW(dev)) vlv_crtc_clock_get(crtc, pipe_config); else i9xx_crtc_clock_get(crtc, pipe_config); @@ -5937,8 +6354,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) if (intel_panel_use_ssc(dev_priv) && can_ssc) { DRM_DEBUG_KMS("Using SSC on eDP\n"); val |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD; - } - else + } else val |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; } else val |= DREF_CPU_SOURCE_OUTPUT_DISABLE; @@ -6517,10 +6933,7 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, struct drm_framebuffer *fb) { struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int pipe = intel_crtc->pipe; - int plane = intel_crtc->plane; int num_connectors = 0; intel_clock_t clock, reduced_clock; u32 dpll = 0, fp = 0, fp2 = 0; @@ -6528,7 +6941,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, bool is_lvds = false; struct intel_encoder *encoder; struct intel_shared_dpll *pll; - int ret; for_each_encoder_on_crtc(dev, crtc, encoder) { switch (encoder->type) { @@ -6578,36 +6990,18 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, pll = intel_get_shared_dpll(intel_crtc); if (pll == NULL) { DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n", - pipe_name(pipe)); + pipe_name(intel_crtc->pipe)); return -EINVAL; } } else intel_put_shared_dpll(intel_crtc); - if (intel_crtc->config.has_dp_encoder) - intel_dp_set_m_n(intel_crtc); - if (is_lvds && has_reduced_clock && i915.powersave) intel_crtc->lowfreq_avail = true; else intel_crtc->lowfreq_avail = false; - intel_set_pipe_timings(intel_crtc); - - if (intel_crtc->config.has_pch_encoder) { - intel_cpu_transcoder_set_m_n(intel_crtc, - &intel_crtc->config.fdi_m_n); - } - - ironlake_set_pipeconf(crtc); - - /* Set up the display plane register */ - I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE); - POSTING_READ(DSPCNTR(plane)); - - ret = intel_pipe_set_base(crtc, x, y, fb); - - return ret; + return 0; } static void intel_pch_transcoder_get_m_n(struct intel_crtc *crtc, @@ -6785,6 +7179,9 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, break; } + if (tmp & PIPECONF_COLOR_RANGE_SELECT) + pipe_config->limited_color_range = true; + if (I915_READ(PCH_TRANSCONF(crtc->pipe)) & TRANS_ENABLE) { struct intel_shared_dpll *pll; @@ -6835,7 +7232,7 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) struct intel_ddi_plls *plls = &dev_priv->ddi_plls; struct intel_crtc *crtc; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) + for_each_intel_crtc(dev, crtc) WARN(crtc->active, "CRTC for pipe %c enabled\n", pipe_name(crtc->pipe)); @@ -7070,39 +7467,15 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc, int x, int y, struct drm_framebuffer *fb) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int plane = intel_crtc->plane; - int ret; if (!intel_ddi_pll_select(intel_crtc)) return -EINVAL; intel_ddi_pll_enable(intel_crtc); - if (intel_crtc->config.has_dp_encoder) - intel_dp_set_m_n(intel_crtc); - intel_crtc->lowfreq_avail = false; - intel_set_pipe_timings(intel_crtc); - - if (intel_crtc->config.has_pch_encoder) { - intel_cpu_transcoder_set_m_n(intel_crtc, - &intel_crtc->config.fdi_m_n); - } - - haswell_set_pipeconf(crtc); - - intel_set_pipe_csc(crtc); - - /* Set up the display plane register */ - I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE | DISPPLANE_PIPE_CSC_ENABLE); - POSTING_READ(DSPCNTR(plane)); - - ret = intel_pipe_set_base(crtc, x, y, fb); - - return ret; + return 0; } static bool haswell_get_pipe_config(struct intel_crtc *crtc, @@ -7182,40 +7555,6 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, return true; } -static int intel_crtc_mode_set(struct drm_crtc *crtc, - int x, int y, - struct drm_framebuffer *fb) -{ - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_encoder *encoder; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_display_mode *mode = &intel_crtc->config.requested_mode; - int pipe = intel_crtc->pipe; - int ret; - - drm_vblank_pre_modeset(dev, pipe); - - ret = dev_priv->display.crtc_mode_set(crtc, x, y, fb); - - drm_vblank_post_modeset(dev, pipe); - - if (ret != 0) - return ret; - - for_each_encoder_on_crtc(dev, crtc, encoder) { - DRM_DEBUG_KMS("[ENCODER:%d:%s] set [MODE:%d:%s]\n", - encoder->base.base.id, - drm_get_encoder_name(&encoder->base), - mode->base.id, mode->name); - - if (encoder->mode_set) - encoder->mode_set(encoder); - } - - return 0; -} - static struct { int clock; u32 config; @@ -7330,7 +7669,6 @@ static void haswell_write_eld(struct drm_connector *connector, { struct drm_i915_private *dev_priv = connector->dev->dev_private; uint8_t *eld = connector->eld; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); uint32_t eldv; uint32_t i; int len; @@ -7369,7 +7707,6 @@ static void haswell_write_eld(struct drm_connector *connector, DRM_DEBUG_DRIVER("ELD on pipe %c\n", pipe_name(pipe)); eldv = AUDIO_ELD_VALID_A << (pipe * 4); - intel_crtc->eld_vld = true; if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) { DRM_DEBUG_DRIVER("ELD: DisplayPort detected\n"); @@ -7610,7 +7947,7 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base) if (intel_crtc->cursor_visible != visible) { int16_t width = intel_crtc->cursor_width; - uint32_t cntl = I915_READ(CURCNTR_IVB(pipe)); + uint32_t cntl = I915_READ(CURCNTR(pipe)); if (base) { cntl &= ~CURSOR_MODE; cntl |= MCURSOR_GAMMA_ENABLE; @@ -7636,14 +7973,14 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base) cntl |= CURSOR_PIPE_CSC_ENABLE; cntl &= ~CURSOR_TRICKLE_FEED_DISABLE; } - I915_WRITE(CURCNTR_IVB(pipe), cntl); + I915_WRITE(CURCNTR(pipe), cntl); intel_crtc->cursor_visible = visible; } /* and commit changes on next vblank */ - POSTING_READ(CURCNTR_IVB(pipe)); - I915_WRITE(CURBASE_IVB(pipe), base); - POSTING_READ(CURBASE_IVB(pipe)); + POSTING_READ(CURCNTR(pipe)); + I915_WRITE(CURBASE(pipe), base); + POSTING_READ(CURBASE(pipe)); } /* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */ @@ -7690,16 +8027,14 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, if (!visible && !intel_crtc->cursor_visible) return; - if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev)) { - I915_WRITE(CURPOS_IVB(pipe), pos); + I915_WRITE(CURPOS(pipe), pos); + + if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev)) ivb_update_cursor(crtc, base); - } else { - I915_WRITE(CURPOS(pipe), pos); - if (IS_845G(dev) || IS_I865G(dev)) - i845_update_cursor(crtc, base); - else - i9xx_update_cursor(crtc, base); - } + else if (IS_845G(dev) || IS_I865G(dev)) + i845_update_cursor(crtc, base); + else + i9xx_update_cursor(crtc, base); } static int intel_crtc_cursor_set(struct drm_crtc *crtc, @@ -8015,7 +8350,7 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector, } /* Find an unused one (if possible) */ - list_for_each_entry(possible_crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, possible_crtc) { i++; if (!(encoder->possible_crtcs & (1 << i))) continue; @@ -8406,7 +8741,7 @@ void intel_mark_idle(struct drm_device *dev) if (!i915.powersave) goto out; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { if (!crtc->primary->fb) continue; @@ -8421,7 +8756,7 @@ out: } void intel_mark_fb_busy(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { struct drm_device *dev = obj->base.dev; struct drm_crtc *crtc; @@ -8429,7 +8764,7 @@ void intel_mark_fb_busy(struct drm_i915_gem_object *obj, if (!i915.powersave) return; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { if (!crtc->primary->fb) continue; @@ -8517,7 +8852,7 @@ static void do_intel_finish_page_flip(struct drm_device *dev, if (work->event) drm_send_vblank_event(dev, intel_crtc->pipe, work->event); - drm_vblank_put(dev, intel_crtc->pipe); + drm_crtc_vblank_put(crtc); spin_unlock_irqrestore(&dev->event_lock, flags); @@ -8544,6 +8879,48 @@ void intel_finish_page_flip_plane(struct drm_device *dev, int plane) do_intel_finish_page_flip(dev, crtc); } +/* Is 'a' after or equal to 'b'? */ +static bool g4x_flip_count_after_eq(u32 a, u32 b) +{ + return !((a - b) & 0x80000000); +} + +static bool page_flip_finished(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + + /* + * The relevant registers doen't exist on pre-ctg. + * As the flip done interrupt doesn't trigger for mmio + * flips on gmch platforms, a flip count check isn't + * really needed there. But since ctg has the registers, + * include it in the check anyway. + */ + if (INTEL_INFO(dev)->gen < 5 && !IS_G4X(dev)) + return true; + + /* + * A DSPSURFLIVE check isn't enough in case the mmio and CS flips + * used the same base address. In that case the mmio flip might + * have completed, but the CS hasn't even executed the flip yet. + * + * A flip count check isn't enough as the CS might have updated + * the base address just after start of vblank, but before we + * managed to process the interrupt. This means we'd complete the + * CS flip too soon. + * + * Combining both checks should get us a good enough result. It may + * still happen that the CS flip has been executed, but has not + * yet actually completed. But in case the base address is the same + * anyway, we don't really care. + */ + return (I915_READ(DSPSURFLIVE(crtc->plane)) & ~0xfff) == + crtc->unpin_work->gtt_offset && + g4x_flip_count_after_eq(I915_READ(PIPE_FLIPCOUNT_GM45(crtc->pipe)), + crtc->unpin_work->flip_count); +} + void intel_prepare_page_flip(struct drm_device *dev, int plane) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -8556,12 +8933,12 @@ void intel_prepare_page_flip(struct drm_device *dev, int plane) * is also accompanied by a spurious intel_prepare_page_flip(). */ spin_lock_irqsave(&dev->event_lock, flags); - if (intel_crtc->unpin_work) + if (intel_crtc->unpin_work && page_flip_finished(intel_crtc)) atomic_inc_not_zero(&intel_crtc->unpin_work->pending); spin_unlock_irqrestore(&dev->event_lock, flags); } -inline static void intel_mark_page_flip_active(struct intel_crtc *intel_crtc) +static inline void intel_mark_page_flip_active(struct intel_crtc *intel_crtc) { /* Ensure that the work item is consistent when activating it ... */ smp_wmb(); @@ -8574,21 +8951,16 @@ static int intel_gen2_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); u32 flip_mask; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; int ret; - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - ret = intel_ring_begin(ring, 6); if (ret) - goto err_unpin; + return ret; /* Can't queue multiple flips, so wait for the previous * one to finish before executing the next. @@ -8602,38 +8974,28 @@ static int intel_gen2_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset); intel_ring_emit(ring, 0); /* aux display base address, unused */ intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_gen3_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); u32 flip_mask; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; int ret; - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - ret = intel_ring_begin(ring, 6); if (ret) - goto err_unpin; + return ret; if (intel_crtc->plane) flip_mask = MI_WAIT_FOR_PLANE_B_FLIP; @@ -8644,38 +9006,29 @@ static int intel_gen3_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset); intel_ring_emit(ring, MI_NOOP); intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_gen4_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); uint32_t pf, pipesrc; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; int ret; - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - ret = intel_ring_begin(ring, 4); if (ret) - goto err_unpin; + return ret; /* i965+ uses the linear or tiled offsets from the * Display Registers (which do not change across a page-flip) @@ -8684,8 +9037,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev, intel_ring_emit(ring, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0]); - intel_ring_emit(ring, - (i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) | + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset | obj->tiling_mode); /* XXX Enabling the panel-fitter across page-flip is so far @@ -8699,37 +9051,28 @@ static int intel_gen4_queue_flip(struct drm_device *dev, intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_gen6_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { 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[RCS]; uint32_t pf, pipesrc; int ret; - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - ret = intel_ring_begin(ring, 4); if (ret) - goto err_unpin; + return ret; intel_ring_emit(ring, MI_DISPLAY_FLIP | MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode); - intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset); + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset); /* Contrary to the suggestions in the documentation, * "Enable Panel Fitter" does not seem to be required when page @@ -8744,34 +9087,20 @@ static int intel_gen6_queue_flip(struct drm_device *dev, intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_gen7_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { - struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_ring_buffer *ring; uint32_t plane_bit = 0; int len, ret; - ring = obj->ring; - if (IS_VALLEYVIEW(dev) || ring == NULL || ring->id != RCS) - ring = &dev_priv->ring[BCS]; - - ret = intel_pin_and_fence_fb_obj(dev, obj, ring); - if (ret) - goto err; - - switch(intel_crtc->plane) { + switch (intel_crtc->plane) { case PLANE_A: plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_A; break; @@ -8783,8 +9112,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev, break; default: WARN_ONCE(1, "unknown plane in flip command\n"); - ret = -ENODEV; - goto err_unpin; + return -ENODEV; } len = 4; @@ -8811,11 +9139,11 @@ static int intel_gen7_queue_flip(struct drm_device *dev, */ ret = intel_ring_cacheline_align(ring); if (ret) - goto err_unpin; + return ret; ret = intel_ring_begin(ring, len); if (ret) - goto err_unpin; + return ret; /* 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 @@ -8848,23 +9176,19 @@ static int intel_gen7_queue_flip(struct drm_device *dev, 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); + intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset); intel_ring_emit(ring, (MI_NOOP)); intel_mark_page_flip_active(intel_crtc); __intel_ring_advance(ring); return 0; - -err_unpin: - intel_unpin_fb_obj(obj); -err: - return ret; } static int intel_default_queue_flip(struct drm_device *dev, struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_i915_gem_object *obj, + struct intel_engine_cs *ring, uint32_t flags) { return -ENODEV; @@ -8881,6 +9205,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, struct drm_i915_gem_object *obj = to_intel_framebuffer(fb)->obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_unpin_work *work; + struct intel_engine_cs *ring; unsigned long flags; int ret; @@ -8909,7 +9234,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, work->old_fb_obj = to_intel_framebuffer(old_fb)->obj; INIT_WORK(&work->work, intel_unpin_work_fn); - ret = drm_vblank_get(dev, intel_crtc->pipe); + ret = drm_crtc_vblank_get(crtc); if (ret) goto free_work; @@ -8918,7 +9243,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, if (intel_crtc->unpin_work) { spin_unlock_irqrestore(&dev->event_lock, flags); kfree(work); - drm_vblank_put(dev, intel_crtc->pipe); + drm_crtc_vblank_put(crtc); DRM_DEBUG_DRIVER("flip queue: crtc already busy\n"); return -EBUSY; @@ -8946,10 +9271,30 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, atomic_inc(&intel_crtc->unpin_work_count); intel_crtc->reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter); - ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, page_flip_flags); + if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev)) + work->flip_count = I915_READ(PIPE_FLIPCOUNT_GM45(intel_crtc->pipe)) + 1; + + if (IS_VALLEYVIEW(dev)) { + ring = &dev_priv->ring[BCS]; + } else if (INTEL_INFO(dev)->gen >= 7) { + ring = obj->ring; + if (ring == NULL || ring->id != RCS) + ring = &dev_priv->ring[BCS]; + } else { + ring = &dev_priv->ring[RCS]; + } + + ret = intel_pin_and_fence_fb_obj(dev, obj, ring); if (ret) goto cleanup_pending; + work->gtt_offset = + i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset; + + ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring, page_flip_flags); + if (ret) + goto cleanup_unpin; + intel_disable_fbc(dev); intel_mark_fb_busy(obj, NULL); mutex_unlock(&dev->struct_mutex); @@ -8958,6 +9303,8 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, return 0; +cleanup_unpin: + intel_unpin_fb_obj(obj); cleanup_pending: atomic_dec(&intel_crtc->unpin_work_count); crtc->primary->fb = old_fb; @@ -8970,7 +9317,7 @@ cleanup: intel_crtc->unpin_work = NULL; spin_unlock_irqrestore(&dev->event_lock, flags); - drm_vblank_put(dev, intel_crtc->pipe); + drm_crtc_vblank_put(crtc); free_work: kfree(work); @@ -9013,8 +9360,7 @@ static void intel_modeset_update_staged_output_state(struct drm_device *dev) to_intel_crtc(encoder->base.crtc); } - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { crtc->new_enabled = crtc->base.enabled; if (crtc->new_enabled) @@ -9045,14 +9391,13 @@ static void intel_modeset_commit_output_state(struct drm_device *dev) encoder->base.crtc = &encoder->new_crtc->base; } - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { crtc->base.enabled = crtc->new_enabled; } } static void -connected_sink_compute_bpp(struct intel_connector * connector, +connected_sink_compute_bpp(struct intel_connector *connector, struct intel_crtc_config *pipe_config) { int bpp = pipe_config->pipe_bpp; @@ -9400,8 +9745,7 @@ intel_modeset_affected_pipes(struct drm_crtc *crtc, unsigned *modeset_pipes, } /* Check for pipes that will be enabled/disabled ... */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, intel_crtc) { if (intel_crtc->base.enabled == intel_crtc->new_enabled) continue; @@ -9474,8 +9818,7 @@ intel_modeset_update_state(struct drm_device *dev, unsigned prepare_pipes) intel_modeset_commit_output_state(dev); /* Double check state. */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, intel_crtc) { WARN_ON(intel_crtc->base.enabled != intel_crtc_in_use(&intel_crtc->base)); WARN_ON(intel_crtc->new_config && intel_crtc->new_config != &intel_crtc->config); @@ -9604,6 +9947,12 @@ intel_pipe_config_compare(struct drm_device *dev, PIPE_CONF_CHECK_I(adjusted_mode.crtc_vsync_end); PIPE_CONF_CHECK_I(pixel_multiplier); + PIPE_CONF_CHECK_I(has_hdmi_sink); + if ((INTEL_INFO(dev)->gen < 8 && !IS_HASWELL(dev)) || + IS_VALLEYVIEW(dev)) + PIPE_CONF_CHECK_I(limited_color_range); + + PIPE_CONF_CHECK_I(has_audio); PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags, DRM_MODE_FLAG_INTERLACE); @@ -9753,8 +10102,7 @@ check_crtc_state(struct drm_device *dev) struct intel_encoder *encoder; struct intel_crtc_config pipe_config; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { bool enabled = false; bool active = false; @@ -9843,8 +10191,7 @@ check_shared_dpll_state(struct drm_device *dev) "pll on state mismatch (expected %i, found %i)\n", pll->on, active); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { if (crtc->base.enabled && intel_crtc_to_shared_dpll(crtc) == pll) enabled_crtcs++; if (crtc->active && intel_crtc_to_shared_dpll(crtc) == pll) @@ -9884,6 +10231,44 @@ void ironlake_check_encoder_dotclock(const struct intel_crtc_config *pipe_config pipe_config->adjusted_mode.crtc_clock, dotclock); } +static void update_scanline_offset(struct intel_crtc *crtc) +{ + struct drm_device *dev = crtc->base.dev; + + /* + * The scanline counter increments at the leading edge of hsync. + * + * On most platforms it starts counting from vtotal-1 on the + * first active line. That means the scanline counter value is + * always one less than what we would expect. Ie. just after + * start of vblank, which also occurs at start of hsync (on the + * last active line), the scanline counter will read vblank_start-1. + * + * On gen2 the scanline counter starts counting from 1 instead + * of vtotal-1, so we have to subtract one (or rather add vtotal-1 + * to keep the value positive), instead of adding one. + * + * On HSW+ the behaviour of the scanline counter depends on the output + * type. For DP ports it behaves like most other platforms, but on HDMI + * there's an extra 1 line difference. So we need to add two instead of + * one to the value. + */ + if (IS_GEN2(dev)) { + const struct drm_display_mode *mode = &crtc->config.adjusted_mode; + int vtotal; + + vtotal = mode->crtc_vtotal; + if (mode->flags & DRM_MODE_FLAG_INTERLACE) + vtotal /= 2; + + crtc->scanline_offset = vtotal - 1; + } else if (HAS_DDI(dev) && + intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI)) { + crtc->scanline_offset = 2; + } else + crtc->scanline_offset = 1; +} + static int __intel_set_mode(struct drm_crtc *crtc, struct drm_display_mode *mode, int x, int y, struct drm_framebuffer *fb) @@ -9975,15 +10360,38 @@ static int __intel_set_mode(struct drm_crtc *crtc, * on the DPLL. */ for_each_intel_crtc_masked(dev, modeset_pipes, intel_crtc) { - ret = intel_crtc_mode_set(&intel_crtc->base, - x, y, fb); + struct drm_framebuffer *old_fb; + + mutex_lock(&dev->struct_mutex); + ret = intel_pin_and_fence_fb_obj(dev, + to_intel_framebuffer(fb)->obj, + NULL); + if (ret != 0) { + DRM_ERROR("pin & fence failed\n"); + mutex_unlock(&dev->struct_mutex); + goto done; + } + old_fb = crtc->primary->fb; + if (old_fb) + intel_unpin_fb_obj(to_intel_framebuffer(old_fb)->obj); + mutex_unlock(&dev->struct_mutex); + + crtc->primary->fb = fb; + crtc->x = x; + crtc->y = y; + + ret = dev_priv->display.crtc_mode_set(&intel_crtc->base, + x, y, fb); if (ret) goto done; } /* Now enable the clocks, plane, pipe, and connectors that we set up. */ - for_each_intel_crtc_masked(dev, prepare_pipes, intel_crtc) + for_each_intel_crtc_masked(dev, prepare_pipes, intel_crtc) { + update_scanline_offset(intel_crtc); + dev_priv->display.crtc_enable(&intel_crtc->base); + } /* FIXME: add subpixel order */ done: @@ -10059,7 +10467,7 @@ static int intel_set_config_save_state(struct drm_device *dev, * restored, not the drivers personal bookkeeping. */ count = 0; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { config->save_crtc_enabled[count++] = crtc->enabled; } @@ -10085,7 +10493,7 @@ static void intel_set_config_restore_state(struct drm_device *dev, int count; count = 0; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { crtc->new_enabled = config->save_crtc_enabled[count++]; if (crtc->new_enabled) @@ -10275,8 +10683,7 @@ intel_modeset_stage_output_state(struct drm_device *dev, } /* Now we've also updated encoder->new_crtc for all encoders. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { crtc->new_enabled = false; list_for_each_entry(encoder, @@ -10489,7 +10896,7 @@ static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv, struct intel_crtc *crtc; /* Make sure no transcoder isn't still depending on us. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, crtc) { if (intel_crtc_to_shared_dpll(crtc) == pll) assert_pch_transcoder_disabled(dev_priv, crtc->pipe); } @@ -10572,6 +10979,8 @@ static void intel_crtc_init(struct drm_device *dev, int pipe) dev_priv->pipe_to_crtc_mapping[intel_crtc->pipe] = &intel_crtc->base; drm_crtc_helper_add(&intel_crtc->base, &intel_helper_funcs); + + WARN_ON(drm_crtc_index(&intel_crtc->base) != intel_crtc->pipe); } enum pipe intel_get_pipe_from_connector(struct intel_connector *connector) @@ -10674,7 +11083,7 @@ static void intel_setup_outputs(struct drm_device *dev) intel_lvds_init(dev); - if (!IS_ULT(dev)) + if (!IS_ULT(dev) && !IS_CHERRYVIEW(dev)) intel_crt_init(dev); if (HAS_DDI(dev)) { @@ -10738,6 +11147,15 @@ static void intel_setup_outputs(struct drm_device *dev) intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C); } + if (IS_CHERRYVIEW(dev)) { + if (I915_READ(VLV_DISPLAY_BASE + CHV_HDMID) & SDVO_DETECTED) { + intel_hdmi_init(dev, VLV_DISPLAY_BASE + CHV_HDMID, + PORT_D); + if (I915_READ(VLV_DISPLAY_BASE + DP_D) & DP_DETECTED) + intel_dp_init(dev, VLV_DISPLAY_BASE + DP_D, PORT_D); + } + } + intel_dsi_init(dev); } else if (SUPPORTS_DIGITAL_OUTPUTS(dev)) { bool found = false; @@ -10967,6 +11385,8 @@ static void intel_init_display(struct drm_device *dev) if (HAS_PCH_SPLIT(dev) || IS_G4X(dev)) dev_priv->display.find_dpll = g4x_find_best_dpll; + else if (IS_CHERRYVIEW(dev)) + dev_priv->display.find_dpll = chv_find_best_dpll; else if (IS_VALLEYVIEW(dev)) dev_priv->display.find_dpll = vlv_find_best_dpll; else if (IS_PINEVIEW(dev)) @@ -11340,8 +11760,7 @@ void intel_modeset_init(struct drm_device *dev) intel_modeset_setup_hw_state(dev, false); mutex_unlock(&dev->mode_config.mutex); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { if (!crtc->active) continue; @@ -11430,6 +11849,12 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) reg = PIPECONF(crtc->config.cpu_transcoder); I915_WRITE(reg, I915_READ(reg) & ~PIPECONF_FRAME_START_DELAY_MASK); + /* restore vblank interrupts to correct state */ + if (crtc->active) + drm_vblank_on(dev, crtc->pipe); + else + drm_vblank_off(dev, crtc->pipe); + /* We need to sanitize the plane -> pipe mapping first because this will * disable the crtc (and hence change the state) if it is wrong. Note * that gen4+ has a fixed plane -> pipe mapping. */ @@ -11499,16 +11924,25 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc) encoder->base.crtc = NULL; } } - if (crtc->active) { + + if (crtc->active || IS_VALLEYVIEW(dev) || INTEL_INFO(dev)->gen < 5) { /* * We start out with underrun reporting disabled to avoid races. * For correct bookkeeping mark this on active crtcs. * + * Also on gmch platforms we dont have any hardware bits to + * disable the underrun reporting. Which means we need to start + * out with underrun reporting disabled also on inactive pipes, + * since otherwise we'll complain about the garbage we read when + * e.g. coming up after runtime pm. + * * No protection against concurrent access is required - at * worst a fifo underrun happens which also sets this to false. */ crtc->cpu_fifo_underrun_disabled = true; crtc->pch_fifo_underrun_disabled = true; + + update_scanline_offset(crtc); } } @@ -11602,8 +12036,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) struct intel_connector *connector; int i; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { memset(&crtc->config, 0, sizeof(crtc->config)); crtc->config.quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE; @@ -11628,8 +12061,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) pll->on = pll->get_hw_state(dev_priv, pll, &pll->hw_state); pll->active = 0; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { if (crtc->active && intel_crtc_to_shared_dpll(crtc) == pll) pll->active++; } @@ -11694,8 +12126,7 @@ void intel_modeset_setup_hw_state(struct drm_device *dev, * Note that this could go away if we move to using crtc_config * checking everywhere. */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, - base.head) { + for_each_intel_crtc(dev, crtc) { if (crtc->active && i915.fastboot) { intel_mode_from_pipe_config(&crtc->base.mode, &crtc->config); DRM_DEBUG_KMS("[CRTC:%d] found active mode: ", @@ -11771,7 +12202,7 @@ void intel_modeset_gem_init(struct drm_device *dev) * for this. */ mutex_lock(&dev->struct_mutex); - list_for_each_entry(c, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, c) { if (!c->primary->fb) continue; @@ -11817,7 +12248,7 @@ void intel_modeset_cleanup(struct drm_device *dev) intel_unregister_dsm_handler(); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { /* Skip inactive CRTCs */ if (!crtc->primary->fb) continue; @@ -11973,15 +12404,9 @@ intel_display_capture_error_state(struct drm_device *dev) if (!error->pipe[i].power_domain_on) continue; - if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) { - error->cursor[i].control = I915_READ(CURCNTR(i)); - error->cursor[i].position = I915_READ(CURPOS(i)); - error->cursor[i].base = I915_READ(CURBASE(i)); - } else { - error->cursor[i].control = I915_READ(CURCNTR_IVB(i)); - error->cursor[i].position = I915_READ(CURPOS_IVB(i)); - error->cursor[i].base = I915_READ(CURBASE_IVB(i)); - } + error->cursor[i].control = I915_READ(CURCNTR(i)); + error->cursor[i].position = I915_READ(CURPOS(i)); + error->cursor[i].base = I915_READ(CURBASE(i)); error->plane[i].control = I915_READ(DSPCNTR(i)); error->plane[i].stride = I915_READ(DSPSTRIDE(i)); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 34ed143ab479..7f7df2c8eed3 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -64,6 +64,24 @@ static const struct dp_link_dpll vlv_dpll[] = { { .p1 = 2, .p2 = 2, .n = 1, .m1 = 2, .m2 = 27 } } }; +/* + * CHV supports eDP 1.4 that have more link rates. + * Below only provides the fixed rate but exclude variable rate. + */ +static const struct dp_link_dpll chv_dpll[] = { + /* + * CHV requires to program fractional division for m2. + * m2 is stored in fixed point format using formula below + * (m2_int << 22) | m2_fraction + */ + { DP_LINK_BW_1_62, /* m2_int = 32, m2_fraction = 1677722 */ + { .p1 = 4, .p2 = 2, .n = 1, .m1 = 2, .m2 = 0x819999a } }, + { DP_LINK_BW_2_7, /* m2_int = 27, m2_fraction = 0 */ + { .p1 = 4, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } }, + { DP_LINK_BW_5_4, /* m2_int = 27, m2_fraction = 0 */ + { .p1 = 2, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } } +}; + /** * is_edp - is the given port attached to an eDP panel (either CPU or PCH) * @intel_dp: DP struct @@ -726,6 +744,9 @@ intel_dp_set_clock(struct intel_encoder *encoder, } else if (HAS_PCH_SPLIT(dev)) { divisor = pch_dpll; count = ARRAY_SIZE(pch_dpll); + } else if (IS_CHERRYVIEW(dev)) { + divisor = chv_dpll; + count = ARRAY_SIZE(chv_dpll); } else if (IS_VALLEYVIEW(dev)) { divisor = vlv_dpll; count = ARRAY_SIZE(vlv_dpll); @@ -779,6 +800,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, pipe_config->has_pch_encoder = true; pipe_config->has_dp_encoder = true; + pipe_config->has_audio = intel_dp->has_audio; if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) { intel_fixed_panel_mode(intel_connector->panel.fixed_mode, @@ -903,7 +925,7 @@ static void ironlake_set_pll_cpu_edp(struct intel_dp *intel_dp) udelay(500); } -static void intel_dp_mode_set(struct intel_encoder *encoder) +static void intel_dp_prepare(struct intel_encoder *encoder) { struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -938,7 +960,7 @@ static void intel_dp_mode_set(struct intel_encoder *encoder) intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0; intel_dp->DP |= DP_PORT_WIDTH(intel_dp->lane_count); - if (intel_dp->has_audio) { + if (crtc->config.has_audio) { DRM_DEBUG_DRIVER("Enabling DP audio on pipe %c\n", pipe_name(crtc->pipe)); intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE; @@ -971,14 +993,15 @@ static void intel_dp_mode_set(struct intel_encoder *encoder) if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) intel_dp->DP |= DP_ENHANCED_FRAMING; - if (crtc->pipe == 1) - intel_dp->DP |= DP_PIPEB_SELECT; + if (!IS_CHERRYVIEW(dev)) { + if (crtc->pipe == 1) + intel_dp->DP |= DP_PIPEB_SELECT; + } else { + intel_dp->DP |= DP_PIPE_SELECT_CHV(crtc->pipe); + } } else { intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT; } - - if (port == PORT_A && !IS_VALLEYVIEW(dev)) - ironlake_set_pll_cpu_edp(intel_dp); } #define IDLE_ON_MASK (PP_ON | PP_SEQUENCE_MASK | 0 | PP_SEQUENCE_STATE_MASK) @@ -1434,6 +1457,8 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, if (port == PORT_A && IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) { *pipe = PORT_TO_PIPE_CPT(tmp); + } else if (IS_CHERRYVIEW(dev)) { + *pipe = DP_PORT_TO_PIPE_CHV(tmp); } else if (!HAS_PCH_CPT(dev) || port == PORT_A) { *pipe = PORT_TO_PIPE(tmp); } else { @@ -1481,8 +1506,11 @@ static void intel_dp_get_config(struct intel_encoder *encoder, struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); int dotclock; + tmp = I915_READ(intel_dp->output_reg); + if (tmp & DP_AUDIO_OUTPUT_ENABLE) + pipe_config->has_audio = true; + if ((port == PORT_A) || !HAS_PCH_CPT(dev)) { - tmp = I915_READ(intel_dp->output_reg); if (tmp & DP_SYNC_HS_HIGH) flags |= DRM_MODE_FLAG_PHSYNC; else @@ -1837,6 +1865,42 @@ static void vlv_post_disable_dp(struct intel_encoder *encoder) intel_dp_link_down(intel_dp); } +static void chv_post_disable_dp(struct intel_encoder *encoder) +{ + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + struct intel_digital_port *dport = dp_to_dig_port(intel_dp); + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = + to_intel_crtc(encoder->base.crtc); + enum dpio_channel ch = vlv_dport_to_channel(dport); + enum pipe pipe = intel_crtc->pipe; + u32 val; + + intel_dp_link_down(intel_dp); + + mutex_lock(&dev_priv->dpio_lock); + + /* Propagate soft reset to data lane reset */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + + mutex_unlock(&dev_priv->dpio_lock); +} + static void intel_enable_dp(struct intel_encoder *encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); @@ -1876,8 +1940,13 @@ static void g4x_pre_enable_dp(struct intel_encoder *encoder) struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); struct intel_digital_port *dport = dp_to_dig_port(intel_dp); - if (dport->port == PORT_A) + intel_dp_prepare(encoder); + + /* Only ilk+ has port A */ + if (dport->port == PORT_A) { + ironlake_set_pll_cpu_edp(intel_dp); ironlake_edp_pll_on(intel_dp); + } } static void vlv_pre_enable_dp(struct intel_encoder *encoder) @@ -1929,6 +1998,8 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder) enum dpio_channel port = vlv_dport_to_channel(dport); int pipe = intel_crtc->pipe; + intel_dp_prepare(encoder); + /* Program Tx lane resets to default */ mutex_lock(&dev_priv->dpio_lock); vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port), @@ -1947,6 +2018,69 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder) mutex_unlock(&dev_priv->dpio_lock); } +static void chv_pre_enable_dp(struct intel_encoder *encoder) +{ + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + struct intel_digital_port *dport = dp_to_dig_port(intel_dp); + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct edp_power_seq power_seq; + struct intel_crtc *intel_crtc = + to_intel_crtc(encoder->base.crtc); + enum dpio_channel ch = vlv_dport_to_channel(dport); + int pipe = intel_crtc->pipe; + int data, i; + u32 val; + + mutex_lock(&dev_priv->dpio_lock); + + /* Deassert soft data lane reset*/ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + + /* Program Tx lane latency optimal setting*/ + for (i = 0; i < 4; i++) { + /* Set the latency optimal bit */ + data = (i == 1) ? 0x0 : 0x6; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW11(ch, i), + data << DPIO_FRC_LATENCY_SHFIT); + + /* Set the upar bit */ + data = (i == 1) ? 0x0 : 0x1; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i), + data << DPIO_UPAR_SHIFT); + } + + /* Data lane stagger programming */ + /* FIXME: Fix up value only after power analysis */ + + mutex_unlock(&dev_priv->dpio_lock); + + if (is_edp(intel_dp)) { + /* init power sequencer on this pipe and port */ + intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq); + intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, + &power_seq); + } + + intel_enable_dp(encoder); + + vlv_wait_port_ready(dev_priv, dport); +} + /* * Native read with retry for link status and receiver capability reads for * cases where the sink may still be asleep. @@ -2171,6 +2305,166 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp) return 0; } +static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp) +{ + struct drm_device *dev = intel_dp_to_dev(intel_dp); + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_digital_port *dport = dp_to_dig_port(intel_dp); + struct intel_crtc *intel_crtc = to_intel_crtc(dport->base.base.crtc); + u32 deemph_reg_value, margin_reg_value, val; + uint8_t train_set = intel_dp->train_set[0]; + enum dpio_channel ch = vlv_dport_to_channel(dport); + enum pipe pipe = intel_crtc->pipe; + int i; + + switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) { + case DP_TRAIN_PRE_EMPHASIS_0: + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + deemph_reg_value = 128; + margin_reg_value = 52; + break; + case DP_TRAIN_VOLTAGE_SWING_600: + deemph_reg_value = 128; + margin_reg_value = 77; + break; + case DP_TRAIN_VOLTAGE_SWING_800: + deemph_reg_value = 128; + margin_reg_value = 102; + break; + case DP_TRAIN_VOLTAGE_SWING_1200: + deemph_reg_value = 128; + margin_reg_value = 154; + /* FIXME extra to set for 1200 */ + break; + default: + return 0; + } + break; + case DP_TRAIN_PRE_EMPHASIS_3_5: + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + deemph_reg_value = 85; + margin_reg_value = 78; + break; + case DP_TRAIN_VOLTAGE_SWING_600: + deemph_reg_value = 85; + margin_reg_value = 116; + break; + case DP_TRAIN_VOLTAGE_SWING_800: + deemph_reg_value = 85; + margin_reg_value = 154; + break; + default: + return 0; + } + break; + case DP_TRAIN_PRE_EMPHASIS_6: + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + deemph_reg_value = 64; + margin_reg_value = 104; + break; + case DP_TRAIN_VOLTAGE_SWING_600: + deemph_reg_value = 64; + margin_reg_value = 154; + break; + default: + return 0; + } + break; + case DP_TRAIN_PRE_EMPHASIS_9_5: + switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) { + case DP_TRAIN_VOLTAGE_SWING_400: + deemph_reg_value = 43; + margin_reg_value = 154; + break; + default: + return 0; + } + break; + default: + return 0; + } + + mutex_lock(&dev_priv->dpio_lock); + + /* Clear calc init */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + + /* Program swing deemph */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i)); + val &= ~DPIO_SWING_DEEMPH9P5_MASK; + val |= deemph_reg_value << DPIO_SWING_DEEMPH9P5_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val); + } + + /* Program swing margin */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); + val &= ~DPIO_SWING_MARGIN_MASK; + val |= margin_reg_value << DPIO_SWING_MARGIN_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); + } + + /* Disable unique transition scale */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); + val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); + } + + if (((train_set & DP_TRAIN_PRE_EMPHASIS_MASK) + == DP_TRAIN_PRE_EMPHASIS_0) && + ((train_set & DP_TRAIN_VOLTAGE_SWING_MASK) + == DP_TRAIN_VOLTAGE_SWING_1200)) { + + /* + * The document said it needs to set bit 27 for ch0 and bit 26 + * for ch1. Might be a typo in the doc. + * For now, for this unique transition scale selection, set bit + * 27 for ch0 and ch1. + */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); + val |= DPIO_TX_UNIQ_TRANS_SCALE_EN; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); + } + + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); + val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT); + val |= (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT); + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); + } + } + + /* Start swing calculation */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + + /* LRC Bypass */ + val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30); + val |= DPIO_LRC_BYPASS; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val); + + mutex_unlock(&dev_priv->dpio_lock); + + return 0; +} + static void intel_get_adjust_train(struct intel_dp *intel_dp, const uint8_t link_status[DP_LINK_STATUS_SIZE]) @@ -2385,6 +2679,9 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp, uint32_t *DP) } else if (IS_HASWELL(dev)) { signal_levels = intel_hsw_signal_levels(train_set); mask = DDI_BUF_EMP_MASK; + } else if (IS_CHERRYVIEW(dev)) { + signal_levels = intel_chv_signal_levels(intel_dp); + mask = 0; } else if (IS_VALLEYVIEW(dev)) { signal_levels = intel_vlv_signal_levels(intel_dp); mask = 0; @@ -2751,22 +3048,7 @@ intel_dp_link_down(struct intel_dp *intel_dp) to_intel_crtc(intel_dig_port->base.base.crtc); uint32_t DP = intel_dp->DP; - /* - * DDI code has a strict mode set sequence and we should try to respect - * it, otherwise we might hang the machine in many different ways. So we - * really should be disabling the port only on a complete crtc_disable - * sequence. This function is just called under two conditions on DDI - * code: - * - Link train failed while doing crtc_enable, and on this case we - * really should respect the mode set sequence and wait for a - * crtc_disable. - * - Someone turned the monitor off and intel_dp_check_link_status - * called us. We don't need to disable the whole port on this case, so - * when someone turns the monitor on again, - * intel_ddi_prepare_link_retrain will take care of redoing the link - * train. - */ - if (HAS_DDI(dev)) + if (WARN_ON(HAS_DDI(dev))) return; if (WARN_ON((I915_READ(intel_dp->output_reg) & DP_PORT_EN) == 0)) @@ -4012,11 +4294,14 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) DRM_MODE_ENCODER_TMDS); intel_encoder->compute_config = intel_dp_compute_config; - intel_encoder->mode_set = intel_dp_mode_set; intel_encoder->disable = intel_disable_dp; intel_encoder->get_hw_state = intel_dp_get_hw_state; intel_encoder->get_config = intel_dp_get_config; - if (IS_VALLEYVIEW(dev)) { + if (IS_CHERRYVIEW(dev)) { + intel_encoder->pre_enable = chv_pre_enable_dp; + intel_encoder->enable = vlv_enable_dp; + intel_encoder->post_disable = chv_post_disable_dp; + } else if (IS_VALLEYVIEW(dev)) { intel_encoder->pre_pll_enable = vlv_dp_pre_pll_enable; intel_encoder->pre_enable = vlv_pre_enable_dp; intel_encoder->enable = vlv_enable_dp; @@ -4031,7 +4316,14 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port) intel_dig_port->dp.output_reg = output_reg; intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT; - intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); + if (IS_CHERRYVIEW(dev)) { + if (port == PORT_D) + intel_encoder->crtc_mask = 1 << 2; + else + intel_encoder->crtc_mask = (1 << 0) | (1 << 1); + } else { + intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); + } intel_encoder->cloneable = 0; intel_encoder->hot_plug = intel_dp_hot_plug; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index d8b540b891d1..f1d5897c96cd 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -106,8 +106,8 @@ #define INTEL_DVO_CHIP_TMDS 2 #define INTEL_DVO_CHIP_TVOUT 4 -#define INTEL_DSI_COMMAND_MODE 0 -#define INTEL_DSI_VIDEO_MODE 1 +#define INTEL_DSI_VIDEO_MODE 0 +#define INTEL_DSI_COMMAND_MODE 1 struct intel_framebuffer { struct drm_framebuffer base; @@ -273,6 +273,13 @@ struct intel_crtc_config { * accordingly. */ bool has_dp_encoder; + /* Whether we should send NULL infoframes. Required for audio. */ + bool has_hdmi_sink; + + /* Audio enabled on this pipe. Only valid if either has_hdmi_sink or + * has_dp_encoder is set. */ + bool has_audio; + /* * Enable dithering, used when the selected pipe bpp doesn't match the * plane bpp. @@ -363,7 +370,6 @@ struct intel_crtc { */ bool active; unsigned long enabled_power_domains; - bool eld_vld; bool primary_enabled; /* is the primary plane (partially) visible? */ bool lowfreq_avail; struct intel_overlay *overlay; @@ -403,6 +409,8 @@ struct intel_crtc { } wm; wait_queue_head_t vbl_wait; + + int scanline_offset; }; struct intel_plane_wm_parameters { @@ -486,6 +494,7 @@ struct intel_hdmi { enum hdmi_infoframe_type type, const void *frame, ssize_t len); void (*set_infoframes)(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode); }; @@ -561,6 +570,7 @@ vlv_dport_to_channel(struct intel_digital_port *dport) { switch (dport->port) { case PORT_B: + case PORT_D: return DPIO_CH0; case PORT_C: return DPIO_CH1; @@ -569,6 +579,20 @@ vlv_dport_to_channel(struct intel_digital_port *dport) } } +static inline int +vlv_pipe_to_channel(enum pipe pipe) +{ + switch (pipe) { + case PIPE_A: + case PIPE_C: + return DPIO_CH0; + case PIPE_B: + return DPIO_CH1; + default: + BUG(); + } +} + static inline struct drm_crtc * intel_get_crtc_for_pipe(struct drm_device *dev, int pipe) { @@ -593,6 +617,8 @@ struct intel_unpin_work { #define INTEL_FLIP_INACTIVE 0 #define INTEL_FLIP_PENDING 1 #define INTEL_FLIP_COMPLETE 2 + u32 flip_count; + u32 gtt_offset; bool enable_stall_check; }; @@ -644,8 +670,6 @@ hdmi_to_dig_port(struct intel_hdmi *intel_hdmi) /* i915_irq.c */ bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, enum pipe pipe, bool enable); -bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, - enum pipe pipe, bool enable); bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev, enum transcoder pch_transcoder, bool enable); @@ -653,9 +677,12 @@ void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask); void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask); void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); +void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); +void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask); void intel_runtime_pm_disable_interrupts(struct drm_device *dev); void intel_runtime_pm_restore_interrupts(struct drm_device *dev); int intel_get_crtc_scanline(struct intel_crtc *crtc); +void i9xx_check_fifo_underruns(struct drm_device *dev); /* intel_crt.c */ @@ -694,7 +721,7 @@ int intel_pch_rawclk(struct drm_device *dev); int valleyview_cur_cdclk(struct drm_i915_private *dev_priv); void intel_mark_busy(struct drm_device *dev); void intel_mark_fb_busy(struct drm_i915_gem_object *obj, - struct intel_ring_buffer *ring); + struct intel_engine_cs *ring); void intel_mark_idle(struct drm_device *dev); void intel_crtc_restore_mode(struct drm_crtc *crtc); void intel_crtc_update_dpms(struct drm_crtc *crtc); @@ -726,7 +753,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector, struct intel_load_detect_pipe *old); int intel_pin_and_fence_fb_obj(struct drm_device *dev, struct drm_i915_gem_object *obj, - struct intel_ring_buffer *pipelined); + struct intel_engine_cs *pipelined); void intel_unpin_fb_obj(struct drm_i915_gem_object *obj); struct drm_framebuffer * __intel_framebuffer_create(struct drm_device *dev, @@ -777,6 +804,8 @@ int valleyview_get_vco(struct drm_i915_private *dev_priv); void intel_mode_from_pipe_config(struct drm_display_mode *mode, struct intel_crtc_config *pipe_config); int intel_format_to_fourcc(int format); +void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc); + /* intel_dp.c */ void intel_dp_init(struct drm_device *dev, int output_reg, enum port port); @@ -902,6 +931,7 @@ extern struct drm_display_mode *intel_find_panel_downclock( /* intel_pm.c */ void intel_init_clock_gating(struct drm_device *dev); void intel_suspend_hw(struct drm_device *dev); +int ilk_wm_max_level(const struct drm_device *dev); void intel_update_watermarks(struct drm_crtc *crtc); void intel_update_sprite_watermarks(struct drm_plane *plane, struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 4e271c768fd0..2525cdd52343 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -59,12 +59,12 @@ static struct intel_dsi *intel_attached_dsi(struct drm_connector *connector) static inline bool is_vid_mode(struct intel_dsi *intel_dsi) { - return intel_dsi->dev.type == INTEL_DSI_VIDEO_MODE; + return intel_dsi->operation_mode == INTEL_DSI_VIDEO_MODE; } static inline bool is_cmd_mode(struct intel_dsi *intel_dsi) { - return intel_dsi->dev.type == INTEL_DSI_COMMAND_MODE; + return intel_dsi->operation_mode == INTEL_DSI_COMMAND_MODE; } static void intel_dsi_hot_plug(struct intel_encoder *encoder) @@ -94,13 +94,6 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder, return true; } -static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder) -{ - DRM_DEBUG_KMS("\n"); - - vlv_enable_dsi_pll(encoder); -} - static void intel_dsi_device_ready(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = encoder->base.dev->dev_private; @@ -185,6 +178,8 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder) /* put device in ready state */ intel_dsi_device_ready(encoder); + msleep(intel_dsi->panel_on_delay); + if (intel_dsi->dev.dev_ops->panel_reset) intel_dsi->dev.dev_ops->panel_reset(&intel_dsi->dev); @@ -301,6 +296,9 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder) if (intel_dsi->dev.dev_ops->disable_panel_power) intel_dsi->dev.dev_ops->disable_panel_power(&intel_dsi->dev); + + msleep(intel_dsi->panel_off_delay); + msleep(intel_dsi->panel_pwr_cycle_delay); } static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, @@ -428,7 +426,7 @@ static void set_dsi_timings(struct drm_encoder *encoder, I915_WRITE(MIPI_VBP_COUNT(pipe), vbp); } -static void intel_dsi_mode_set(struct intel_encoder *intel_encoder) +static void intel_dsi_prepare(struct intel_encoder *intel_encoder) { struct drm_encoder *encoder = &intel_encoder->base; struct drm_device *dev = encoder->dev; @@ -525,6 +523,9 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder) /* recovery disables */ I915_WRITE(MIPI_EOT_DISABLE(pipe), val); + /* in terms of low power clock */ + I915_WRITE(MIPI_INIT_COUNT(pipe), intel_dsi->init_count); + /* in terms of txbyteclkhs. actual high to low switch + * MIPI_STOP_STATE_STALL * MIPI_LP_BYTECLK. * @@ -562,6 +563,15 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder) RANDOM_DPI_DISPLAY_RESOLUTION); } +static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder) +{ + DRM_DEBUG_KMS("\n"); + + intel_dsi_prepare(encoder); + + vlv_enable_dsi_pll(encoder); +} + static enum drm_connector_status intel_dsi_detect(struct drm_connector *connector, bool force) { @@ -639,6 +649,7 @@ bool intel_dsi_init(struct drm_device *dev) struct intel_connector *intel_connector; struct drm_connector *connector; struct drm_display_mode *fixed_mode = NULL; + struct drm_i915_private *dev_priv = dev->dev_private; const struct intel_dsi_device *dsi; unsigned int i; @@ -658,6 +669,13 @@ bool intel_dsi_init(struct drm_device *dev) encoder = &intel_encoder->base; intel_dsi->attached_connector = intel_connector; + if (IS_VALLEYVIEW(dev)) { + dev_priv->mipi_mmio_base = VLV_MIPI_BASE; + } else { + DRM_ERROR("Unsupported Mipi device to reg base"); + return false; + } + connector = &intel_connector->base; drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI); @@ -668,7 +686,6 @@ bool intel_dsi_init(struct drm_device *dev) intel_encoder->pre_pll_enable = intel_dsi_pre_pll_enable; intel_encoder->pre_enable = intel_dsi_pre_enable; intel_encoder->enable = intel_dsi_enable_nop; - intel_encoder->mode_set = intel_dsi_mode_set; intel_encoder->disable = intel_dsi_disable; intel_encoder->post_disable = intel_dsi_post_disable; intel_encoder->get_hw_state = intel_dsi_get_hw_state; diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h index 550714c7860e..e3f4e91c526f 100644 --- a/drivers/gpu/drm/i915/intel_dsi.h +++ b/drivers/gpu/drm/i915/intel_dsi.h @@ -31,7 +31,6 @@ struct intel_dsi_device { unsigned int panel_id; const char *name; - int type; const struct intel_dsi_dev_ops *dev_ops; void *dev_priv; }; @@ -85,6 +84,9 @@ struct intel_dsi { /* virtual channel */ int channel; + /* Video mode or command mode */ + u16 operation_mode; + /* number of DSI lanes */ unsigned int lane_count; @@ -112,6 +114,15 @@ struct intel_dsi { u16 hs_to_lp_count; u16 clk_lp_to_hs_count; u16 clk_hs_to_lp_count; + + u16 init_count; + + /* all delays in ms */ + u16 backlight_off_delay; + u16 backlight_on_delay; + u16 panel_on_delay; + u16 panel_off_delay; + u16 panel_pwr_cycle_delay; }; static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder) diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index fce4a0d93c0b..2b36ce2a999e 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -343,15 +343,15 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, num_connectors_detected++; if (!enabled[i]) { - DRM_DEBUG_KMS("connector %d not enabled, skipping\n", - connector->base.id); + DRM_DEBUG_KMS("connector %s not enabled, skipping\n", + drm_get_connector_name(connector)); continue; } encoder = connector->encoder; if (!encoder || WARN_ON(!encoder->crtc)) { - DRM_DEBUG_KMS("connector %d has no encoder or crtc, skipping\n", - connector->base.id); + DRM_DEBUG_KMS("connector %s has no encoder or crtc, skipping\n", + drm_get_connector_name(connector)); enabled[i] = false; continue; } @@ -373,16 +373,16 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, } } - DRM_DEBUG_KMS("looking for cmdline mode on connector %d\n", - fb_conn->connector->base.id); + DRM_DEBUG_KMS("looking for cmdline mode on connector %s\n", + drm_get_connector_name(connector)); /* go for command line mode first */ modes[i] = drm_pick_cmdline_mode(fb_conn, width, height); /* try for preferred next */ if (!modes[i]) { - DRM_DEBUG_KMS("looking for preferred mode on connector %d\n", - fb_conn->connector->base.id); + DRM_DEBUG_KMS("looking for preferred mode on connector %s\n", + drm_get_connector_name(connector)); modes[i] = drm_has_preferred_mode(fb_conn, width, height); } @@ -400,16 +400,20 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, * since the fb helper layer wants a pointer to * something we own. */ + DRM_DEBUG_KMS("looking for current mode on connector %s\n", + drm_get_connector_name(connector)); intel_mode_from_pipe_config(&encoder->crtc->hwmode, &to_intel_crtc(encoder->crtc)->config); modes[i] = &encoder->crtc->hwmode; } crtcs[i] = new_crtc; - DRM_DEBUG_KMS("connector %s on crtc %d: %s\n", + DRM_DEBUG_KMS("connector %s on pipe %d [CRTC:%d]: %dx%d%s\n", drm_get_connector_name(connector), + pipe_name(to_intel_crtc(encoder->crtc)->pipe), encoder->crtc->base.id, - modes[i]->name); + modes[i]->hdisplay, modes[i]->vdisplay, + modes[i]->flags & DRM_MODE_FLAG_INTERLACE ? "i" :""); fallback = false; } @@ -488,7 +492,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, return false; /* Find the largest fb */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { intel_crtc = to_intel_crtc(crtc); if (!intel_crtc->active || !crtc->primary->fb) { @@ -512,7 +516,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, } /* Now make sure all the pipes will fit into it */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { unsigned int cur_size; intel_crtc = to_intel_crtc(crtc); @@ -577,7 +581,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev, drm_framebuffer_reference(&ifbdev->fb->base); /* Final pass to check if any active pipes don't have fbs */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { intel_crtc = to_intel_crtc(crtc); if (!intel_crtc->active) diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index b606162cc17c..171d0dd0239a 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -418,6 +418,7 @@ intel_hdmi_set_hdmi_infoframe(struct drm_encoder *encoder, } static void g4x_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -440,7 +441,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder, * either. */ val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC; - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { if (!(val & VIDEO_DIP_ENABLE)) return; val &= ~VIDEO_DIP_ENABLE; @@ -471,6 +472,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder, } static void ibx_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -486,7 +488,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder, /* See the big comment in g4x_set_infoframes() */ val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC; - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { if (!(val & VIDEO_DIP_ENABLE)) return; val &= ~VIDEO_DIP_ENABLE; @@ -518,6 +520,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder, } static void cpt_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -531,7 +534,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder, /* See the big comment in g4x_set_infoframes() */ val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC; - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { if (!(val & VIDEO_DIP_ENABLE)) return; val &= ~(VIDEO_DIP_ENABLE | VIDEO_DIP_ENABLE_AVI); @@ -554,6 +557,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder, } static void vlv_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -569,7 +573,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder, /* See the big comment in g4x_set_infoframes() */ val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC; - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { if (!(val & VIDEO_DIP_ENABLE)) return; val &= ~VIDEO_DIP_ENABLE; @@ -601,6 +605,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder, } static void hsw_set_infoframes(struct drm_encoder *encoder, + bool enable, struct drm_display_mode *adjusted_mode) { struct drm_i915_private *dev_priv = encoder->dev->dev_private; @@ -611,7 +616,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder, assert_hdmi_port_disabled(intel_hdmi); - if (!intel_hdmi->has_hdmi_sink) { + if (!enable) { I915_WRITE(reg, 0); POSTING_READ(reg); return; @@ -628,7 +633,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder, intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode); } -static void intel_hdmi_mode_set(struct intel_encoder *encoder) +static void intel_hdmi_prepare(struct intel_encoder *encoder) { struct drm_device *dev = encoder->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -650,20 +655,21 @@ static void intel_hdmi_mode_set(struct intel_encoder *encoder) else hdmi_val |= SDVO_COLOR_FORMAT_8bpc; - if (intel_hdmi->has_hdmi_sink && - (HAS_PCH_CPT(dev) || IS_VALLEYVIEW(dev))) + if (crtc->config.has_hdmi_sink) hdmi_val |= HDMI_MODE_SELECT_HDMI; - if (intel_hdmi->has_audio) { + if (crtc->config.has_audio) { + WARN_ON(!crtc->config.has_hdmi_sink); DRM_DEBUG_DRIVER("Enabling HDMI audio on pipe %c\n", pipe_name(crtc->pipe)); hdmi_val |= SDVO_AUDIO_ENABLE; - hdmi_val |= HDMI_MODE_SELECT_HDMI; intel_write_eld(&encoder->base, adjusted_mode); } if (HAS_PCH_CPT(dev)) hdmi_val |= SDVO_PIPE_SEL_CPT(crtc->pipe); + else if (IS_CHERRYVIEW(dev)) + hdmi_val |= SDVO_PIPE_SEL_CHV(crtc->pipe); else hdmi_val |= SDVO_PIPE_SEL(crtc->pipe); @@ -691,6 +697,8 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); + else if (IS_CHERRYVIEW(dev)) + *pipe = SDVO_PORT_TO_PIPE_CHV(tmp); else *pipe = PORT_TO_PIPE(tmp); @@ -717,6 +725,12 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder, else flags |= DRM_MODE_FLAG_NVSYNC; + if (tmp & HDMI_MODE_SELECT_HDMI) + pipe_config->has_hdmi_sink = true; + + if (tmp & HDMI_MODE_SELECT_HDMI) + pipe_config->has_audio = true; + pipe_config->adjusted_mode.flags |= flags; if ((tmp & SDVO_COLOR_FORMAT_MASK) == HDMI_COLOR_FORMAT_12bpc) @@ -739,7 +753,7 @@ static void intel_enable_hdmi(struct intel_encoder *encoder) u32 temp; u32 enable_bits = SDVO_ENABLE; - if (intel_hdmi->has_audio) + if (intel_crtc->config.has_audio) enable_bits |= SDVO_AUDIO_ENABLE; temp = I915_READ(intel_hdmi->hdmi_reg); @@ -893,9 +907,11 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, int portclock_limit = hdmi_portclock_limit(intel_hdmi, false); int desired_bpp; + pipe_config->has_hdmi_sink = intel_hdmi->has_hdmi_sink; + if (intel_hdmi->color_range_auto) { /* See CEA-861-E - 5.1 Default Encoding Parameters */ - if (intel_hdmi->has_hdmi_sink && + if (pipe_config->has_hdmi_sink && drm_match_cea_mode(adjusted_mode) > 1) intel_hdmi->color_range = HDMI_COLOR_RANGE_16_235; else @@ -908,13 +924,16 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder, if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev)) pipe_config->has_pch_encoder = true; + if (pipe_config->has_hdmi_sink && intel_hdmi->has_audio) + pipe_config->has_audio = true; + /* * HDMI is either 12 or 8, so if the display lets 10bpc sneak * through, clamp it down. Note that g4x/vlv don't support 12bpc hdmi * outputs. We also need to check that the higher clock still fits * within limits. */ - if (pipe_config->pipe_bpp > 8*3 && intel_hdmi->has_hdmi_sink && + if (pipe_config->pipe_bpp > 8*3 && pipe_config->has_hdmi_sink && clock_12bpc <= portclock_limit && hdmi_12bpc_possible(encoder->new_crtc)) { DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n"); @@ -1121,7 +1140,11 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder) struct drm_display_mode *adjusted_mode = &intel_crtc->config.adjusted_mode; - intel_hdmi->set_infoframes(&encoder->base, adjusted_mode); + intel_hdmi_prepare(encoder); + + intel_hdmi->set_infoframes(&encoder->base, + intel_crtc->config.has_hdmi_sink, + adjusted_mode); } static void vlv_hdmi_pre_enable(struct intel_encoder *encoder) @@ -1138,9 +1161,6 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder) int pipe = intel_crtc->pipe; u32 val; - if (!IS_VALLEYVIEW(dev)) - return; - /* Enable clock channels for this port */ mutex_lock(&dev_priv->dpio_lock); val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(port)); @@ -1167,7 +1187,9 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder) vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW23(port), 0x00400888); mutex_unlock(&dev_priv->dpio_lock); - intel_hdmi->set_infoframes(&encoder->base, adjusted_mode); + intel_hdmi->set_infoframes(&encoder->base, + intel_crtc->config.has_hdmi_sink, + adjusted_mode); intel_enable_hdmi(encoder); @@ -1184,8 +1206,7 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder) enum dpio_channel port = vlv_dport_to_channel(dport); int pipe = intel_crtc->pipe; - if (!IS_VALLEYVIEW(dev)) - return; + intel_hdmi_prepare(encoder); /* Program Tx lane resets to default */ mutex_lock(&dev_priv->dpio_lock); @@ -1224,6 +1245,152 @@ static void vlv_hdmi_post_disable(struct intel_encoder *encoder) mutex_unlock(&dev_priv->dpio_lock); } +static void chv_hdmi_post_disable(struct intel_encoder *encoder) +{ + struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = + to_intel_crtc(encoder->base.crtc); + enum dpio_channel ch = vlv_dport_to_channel(dport); + enum pipe pipe = intel_crtc->pipe; + u32 val; + + mutex_lock(&dev_priv->dpio_lock); + + /* Propagate soft reset to data lane reset */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + + mutex_unlock(&dev_priv->dpio_lock); +} + +static void chv_hdmi_pre_enable(struct intel_encoder *encoder) +{ + struct intel_digital_port *dport = enc_to_dig_port(&encoder->base); + struct drm_device *dev = encoder->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = + to_intel_crtc(encoder->base.crtc); + enum dpio_channel ch = vlv_dport_to_channel(dport); + int pipe = intel_crtc->pipe; + int data, i; + u32 val; + + mutex_lock(&dev_priv->dpio_lock); + + /* Deassert soft data lane reset*/ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch)); + val |= CHV_PCS_REQ_SOFTRESET_EN; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch)); + val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch)); + val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val); + + /* Program Tx latency optimal setting */ + for (i = 0; i < 4; i++) { + /* Set the latency optimal bit */ + data = (i == 1) ? 0x0 : 0x6; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW11(ch, i), + data << DPIO_FRC_LATENCY_SHFIT); + + /* Set the upar bit */ + data = (i == 1) ? 0x0 : 0x1; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i), + data << DPIO_UPAR_SHIFT); + } + + /* Data lane stagger programming */ + /* FIXME: Fix up value only after power analysis */ + + /* Clear calc init */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3); + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + + /* FIXME: Program the support xxx V-dB */ + /* Use 800mV-0dB */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i)); + val &= ~DPIO_SWING_DEEMPH9P5_MASK; + val |= 128 << DPIO_SWING_DEEMPH9P5_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val); + } + + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i)); + val &= ~DPIO_SWING_MARGIN_MASK; + val |= 102 << DPIO_SWING_MARGIN_SHIFT; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val); + } + + /* Disable unique transition scale */ + for (i = 0; i < 4; i++) { + val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i)); + val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN; + vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val); + } + + /* Additional steps for 1200mV-0dB */ +#if 0 + val = vlv_dpio_read(dev_priv, pipe, VLV_TX_DW3(ch)); + if (ch) + val |= DPIO_TX_UNIQ_TRANS_SCALE_CH1; + else + val |= DPIO_TX_UNIQ_TRANS_SCALE_CH0; + vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(ch), val); + + vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(ch), + vlv_dpio_read(dev_priv, pipe, VLV_TX_DW2(ch)) | + (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT)); +#endif + /* Start swing calculation */ + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val); + + val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch)); + val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3; + vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val); + + /* LRC Bypass */ + val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30); + val |= DPIO_LRC_BYPASS; + vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val); + + mutex_unlock(&dev_priv->dpio_lock); + + intel_enable_hdmi(encoder); + + vlv_wait_port_ready(dev_priv, dport); +} + static void intel_hdmi_destroy(struct drm_connector *connector) { drm_connector_cleanup(connector); @@ -1284,7 +1451,10 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port, intel_encoder->hpd_pin = HPD_PORT_C; break; case PORT_D: - intel_hdmi->ddc_bus = GMBUS_PORT_DPD; + if (IS_CHERRYVIEW(dev)) + intel_hdmi->ddc_bus = GMBUS_PORT_DPD_CHV; + else + intel_hdmi->ddc_bus = GMBUS_PORT_DPD; intel_encoder->hpd_pin = HPD_PORT_D; break; case PORT_A: @@ -1354,11 +1524,14 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port) DRM_MODE_ENCODER_TMDS); intel_encoder->compute_config = intel_hdmi_compute_config; - intel_encoder->mode_set = intel_hdmi_mode_set; intel_encoder->disable = intel_disable_hdmi; intel_encoder->get_hw_state = intel_hdmi_get_hw_state; intel_encoder->get_config = intel_hdmi_get_config; - if (IS_VALLEYVIEW(dev)) { + if (IS_CHERRYVIEW(dev)) { + intel_encoder->pre_enable = chv_hdmi_pre_enable; + intel_encoder->enable = vlv_enable_hdmi; + intel_encoder->post_disable = chv_hdmi_post_disable; + } else if (IS_VALLEYVIEW(dev)) { intel_encoder->pre_pll_enable = vlv_hdmi_pre_pll_enable; intel_encoder->pre_enable = vlv_hdmi_pre_enable; intel_encoder->enable = vlv_enable_hdmi; @@ -1369,7 +1542,14 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port) } intel_encoder->type = INTEL_OUTPUT_HDMI; - intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); + if (IS_CHERRYVIEW(dev)) { + if (port == PORT_D) + intel_encoder->crtc_mask = 1 << 2; + else + intel_encoder->crtc_mask = (1 << 0) | (1 << 1); + } else { + intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); + } intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG; /* * BSpec is unclear about HDMI+HDMI cloning on g4x, but it seems diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 1b1541dfb440..d1539f3efe44 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -119,10 +119,6 @@ static void intel_lvds_get_config(struct intel_encoder *encoder, pipe_config->adjusted_mode.crtc_clock = dotclock; } -/* The LVDS pin pair needs to be on before the DPLLs are enabled. - * This is an exception to the general rule that mode_set doesn't turn - * things on. - */ static void intel_pre_enable_lvds(struct intel_encoder *encoder) { struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); @@ -324,15 +320,6 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder, return true; } -static void intel_lvds_mode_set(struct intel_encoder *encoder) -{ - /* - * We don't do anything here, the LVDS port is fully set up in the pre - * enable hook - the ordering constraints for enabling the lvds port vs. - * enabling the display pll are too strict. - */ -} - /** * Detect the LVDS connection. * @@ -946,7 +933,6 @@ void intel_lvds_init(struct drm_device *dev) intel_encoder->enable = intel_enable_lvds; intel_encoder->pre_enable = intel_pre_enable_lvds; intel_encoder->compute_config = intel_lvds_compute_config; - intel_encoder->mode_set = intel_lvds_mode_set; intel_encoder->disable = intel_disable_lvds; intel_encoder->get_hw_state = intel_lvds_get_hw_state; intel_encoder->get_config = intel_lvds_get_config; diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index d8adc9104dca..27eb820d1b19 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -213,7 +213,7 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay, { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; int ret; BUG_ON(overlay->last_flip_req); @@ -236,7 +236,7 @@ static int intel_overlay_on(struct intel_overlay *overlay) { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; int ret; BUG_ON(overlay->active); @@ -263,7 +263,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay, { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; u32 flip_addr = overlay->flip_addr; u32 tmp; int ret; @@ -320,7 +320,7 @@ static int intel_overlay_off(struct intel_overlay *overlay) { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; u32 flip_addr = overlay->flip_addr; int ret; @@ -363,7 +363,7 @@ static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay) { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; int ret; if (overlay->last_flip_req == 0) @@ -389,7 +389,7 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay) { struct drm_device *dev = overlay->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; int ret; /* Only wait if there is actually an old frame to release to diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index 44ad415e3706..776249bab488 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -42,6 +42,59 @@ intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode, drm_mode_set_crtcinfo(adjusted_mode, 0); } +/** + * intel_find_panel_downclock - find the reduced downclock for LVDS in EDID + * @dev: drm device + * @fixed_mode : panel native mode + * @connector: LVDS/eDP connector + * + * Return downclock_avail + * Find the reduced downclock for LVDS/eDP in EDID. + */ +struct drm_display_mode * +intel_find_panel_downclock(struct drm_device *dev, + struct drm_display_mode *fixed_mode, + struct drm_connector *connector) +{ + struct drm_display_mode *scan, *tmp_mode; + int temp_downclock; + + temp_downclock = fixed_mode->clock; + tmp_mode = NULL; + + list_for_each_entry(scan, &connector->probed_modes, head) { + /* + * If one mode has the same resolution with the fixed_panel + * mode while they have the different refresh rate, it means + * that the reduced downclock is found. In such + * case we can set the different FPx0/1 to dynamically select + * between low and high frequency. + */ + if (scan->hdisplay == fixed_mode->hdisplay && + scan->hsync_start == fixed_mode->hsync_start && + scan->hsync_end == fixed_mode->hsync_end && + scan->htotal == fixed_mode->htotal && + scan->vdisplay == fixed_mode->vdisplay && + scan->vsync_start == fixed_mode->vsync_start && + scan->vsync_end == fixed_mode->vsync_end && + scan->vtotal == fixed_mode->vtotal) { + if (scan->clock < temp_downclock) { + /* + * The downclock is already found. But we + * expect to find the lower downclock. + */ + temp_downclock = scan->clock; + tmp_mode = scan; + } + } + } + + if (temp_downclock < fixed_mode->clock) + return drm_mode_duplicate(dev, tmp_mode); + else + return NULL; +} + /* adjusted_mode has been preset to be the panel's fixed mode */ void intel_pch_panel_fitting(struct intel_crtc *intel_crtc, @@ -323,6 +376,28 @@ out: pipe_config->gmch_pfit.lvds_border_bits = border; } +enum drm_connector_status +intel_panel_detect(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + /* Assume that the BIOS does not lie through the OpRegion... */ + if (!i915.panel_ignore_lid && dev_priv->opregion.lid_state) { + return ioread32(dev_priv->opregion.lid_state) & 0x1 ? + connector_status_connected : + connector_status_disconnected; + } + + switch (i915.panel_ignore_lid) { + case -2: + return connector_status_connected; + case -1: + return connector_status_disconnected; + default: + return connector_status_unknown; + } +} + static u32 intel_panel_compute_brightness(struct intel_connector *connector, u32 val) { @@ -795,28 +870,6 @@ void intel_panel_enable_backlight(struct intel_connector *connector) spin_unlock_irqrestore(&dev_priv->backlight_lock, flags); } -enum drm_connector_status -intel_panel_detect(struct drm_device *dev) -{ - struct drm_i915_private *dev_priv = dev->dev_private; - - /* Assume that the BIOS does not lie through the OpRegion... */ - if (!i915.panel_ignore_lid && dev_priv->opregion.lid_state) { - return ioread32(dev_priv->opregion.lid_state) & 0x1 ? - connector_status_connected : - connector_status_disconnected; - } - - switch (i915.panel_ignore_lid) { - case -2: - return connector_status_connected; - case -1: - return connector_status_disconnected; - default: - return connector_status_unknown; - } -} - #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE) static int intel_backlight_device_update_status(struct backlight_device *bd) { @@ -1103,59 +1156,6 @@ void intel_panel_destroy_backlight(struct drm_connector *connector) intel_backlight_device_unregister(intel_connector); } -/** - * intel_find_panel_downclock - find the reduced downclock for LVDS in EDID - * @dev: drm device - * @fixed_mode : panel native mode - * @connector: LVDS/eDP connector - * - * Return downclock_avail - * Find the reduced downclock for LVDS/eDP in EDID. - */ -struct drm_display_mode * -intel_find_panel_downclock(struct drm_device *dev, - struct drm_display_mode *fixed_mode, - struct drm_connector *connector) -{ - struct drm_display_mode *scan, *tmp_mode; - int temp_downclock; - - temp_downclock = fixed_mode->clock; - tmp_mode = NULL; - - list_for_each_entry(scan, &connector->probed_modes, head) { - /* - * If one mode has the same resolution with the fixed_panel - * mode while they have the different refresh rate, it means - * that the reduced downclock is found. In such - * case we can set the different FPx0/1 to dynamically select - * between low and high frequency. - */ - if (scan->hdisplay == fixed_mode->hdisplay && - scan->hsync_start == fixed_mode->hsync_start && - scan->hsync_end == fixed_mode->hsync_end && - scan->htotal == fixed_mode->htotal && - scan->vdisplay == fixed_mode->vdisplay && - scan->vsync_start == fixed_mode->vsync_start && - scan->vsync_end == fixed_mode->vsync_end && - scan->vtotal == fixed_mode->vtotal) { - if (scan->clock < temp_downclock) { - /* - * The downclock is already found. But we - * expect to find the lower downclock. - */ - temp_downclock = scan->clock; - tmp_mode = scan; - } - } - } - - if (temp_downclock < fixed_mode->clock) - return drm_mode_duplicate(dev, tmp_mode); - else - return NULL; -} - /* Set up chip specific backlight functions */ void intel_panel_init_backlight_funcs(struct drm_device *dev) { diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 834c49c2beb7..b86b58c44228 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -487,7 +487,7 @@ void intel_update_fbc(struct drm_device *dev) * - new fb is too large to fit in compressed buffer * - going to an unsupported config (interlace, pixel multiply, etc.) */ - list_for_each_entry(tmp_crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, tmp_crtc) { if (intel_crtc_active(tmp_crtc) && to_intel_crtc(tmp_crtc)->primary_enabled) { if (crtc) { @@ -1010,7 +1010,7 @@ static struct drm_crtc *single_enabled_crtc(struct drm_device *dev) { struct drm_crtc *crtc, *enabled = NULL; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + for_each_crtc(dev, crtc) { if (intel_crtc_active(crtc)) { if (enabled) return NULL; @@ -2077,7 +2077,7 @@ static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5]) wm[3] *= 2; } -static int ilk_wm_max_level(const struct drm_device *dev) +int ilk_wm_max_level(const struct drm_device *dev) { /* how many WM levels are we expecting */ if (IS_HASWELL(dev) || IS_BROADWELL(dev)) @@ -2170,7 +2170,7 @@ static void ilk_compute_wm_config(struct drm_device *dev, struct intel_crtc *intel_crtc; /* Compute the currently _active_ config */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, intel_crtc) { const struct intel_pipe_wm *wm = &intel_crtc->wm.active; if (!wm->pipe_enabled) @@ -2254,7 +2254,7 @@ static void ilk_merge_wm_level(struct drm_device *dev, ret_wm->enable = true; - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, intel_crtc) { const struct intel_pipe_wm *active = &intel_crtc->wm.active; const struct intel_wm_level *wm = &active->wm[level]; @@ -2400,7 +2400,7 @@ static void ilk_compute_wm_results(struct drm_device *dev, } /* LP0 register values */ - list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) { + for_each_intel_crtc(dev, intel_crtc) { enum pipe pipe = intel_crtc->pipe; const struct intel_wm_level *r = &intel_crtc->wm.active.wm[0]; @@ -2747,7 +2747,7 @@ void ilk_wm_get_hw_state(struct drm_device *dev) struct ilk_wm_values *hw = &dev_priv->wm.hw; struct drm_crtc *crtc; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) + for_each_crtc(dev, crtc) ilk_pipe_wm_get_hw_state(crtc); hw->wm_lp[0] = I915_READ(WM1_LP_ILK); @@ -3114,6 +3114,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val) if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev)) mask |= GEN6_PM_RP_UP_EI_EXPIRED; + if (IS_GEN8(dev_priv->dev)) + mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP; + return ~mask; } @@ -3246,6 +3249,26 @@ void valleyview_set_rps(struct drm_device *dev, u8 val) trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val)); } +static void gen8_disable_rps_interrupts(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP); + I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) & + ~dev_priv->pm_rps_events); + /* Complete PM interrupt masking here doesn't race with the rps work + * item again unmasking PM interrupts because that is using a different + * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in + * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which + * gen8_enable_rps will clean up. */ + + spin_lock_irq(&dev_priv->irq_lock); + dev_priv->rps.pm_iir = 0; + spin_unlock_irq(&dev_priv->irq_lock); + + I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events); +} + static void gen6_disable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3272,7 +3295,10 @@ static void gen6_disable_rps(struct drm_device *dev) I915_WRITE(GEN6_RC_CONTROL, 0); I915_WRITE(GEN6_RPNSWREQ, 1 << 31); - gen6_disable_rps_interrupts(dev); + if (IS_BROADWELL(dev)) + gen8_disable_rps_interrupts(dev); + else + gen6_disable_rps_interrupts(dev); } static void valleyview_disable_rps(struct drm_device *dev) @@ -3308,10 +3334,6 @@ static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6) if (INTEL_INFO(dev)->gen == 5 && !IS_IRONLAKE_M(dev)) return 0; - /* Disable RC6 on Broadwell for now */ - if (IS_BROADWELL(dev)) - return 0; - /* Respect the kernel parameter if it is set */ if (enable_rc6 >= 0) { int mask; @@ -3324,7 +3346,7 @@ static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6) if ((enable_rc6 & mask) != enable_rc6) DRM_INFO("Adjusting RC6 mask to %d (requested %d, valid %d)\n", - enable_rc6, enable_rc6 & mask, mask); + enable_rc6 & mask, enable_rc6, mask); return enable_rc6 & mask; } @@ -3344,6 +3366,17 @@ int intel_enable_rc6(const struct drm_device *dev) return i915.enable_rc6; } +static void gen8_enable_rps_interrupts(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + spin_lock_irq(&dev_priv->irq_lock); + WARN_ON(dev_priv->rps.pm_iir); + bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events); + I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events); + spin_unlock_irq(&dev_priv->irq_lock); +} + static void gen6_enable_rps_interrupts(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -3379,7 +3412,7 @@ static void parse_rp_state_cap(struct drm_i915_private *dev_priv, u32 rp_state_c static void gen8_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; uint32_t rc6_mask = 0, rp_state_cap; int unused; @@ -3433,11 +3466,15 @@ static void gen8_enable_rps(struct drm_device *dev) I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10); + /* WaDisablePwrmtrEvent:chv (pre-production hw) */ + I915_WRITE(0xA80C, I915_READ(0xA80C) & 0x00ffffff); + I915_WRITE(0xA810, I915_READ(0xA810) & 0xffffff00); + /* 5: Enable RPS */ I915_WRITE(GEN6_RP_CONTROL, GEN6_RP_MEDIA_TURBO | GEN6_RP_MEDIA_HW_NORMAL_MODE | - GEN6_RP_MEDIA_IS_GFX | + GEN6_RP_MEDIA_IS_GFX | /* WaSetMaskForGfxBusyness:chv (pre-production hw ?) */ GEN6_RP_ENABLE | GEN6_RP_UP_BUSY_AVG | GEN6_RP_DOWN_IDLE_AVG); @@ -3446,7 +3483,7 @@ static void gen8_enable_rps(struct drm_device *dev) gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8); - gen6_enable_rps_interrupts(dev); + gen8_enable_rps_interrupts(dev); gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL); } @@ -3454,7 +3491,7 @@ static void gen8_enable_rps(struct drm_device *dev) static void gen6_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; u32 rp_state_cap; u32 gt_perf_status; u32 rc6vids, pcu_mbox = 0, rc6_mask = 0; @@ -3783,7 +3820,7 @@ static void valleyview_cleanup_gt_powersave(struct drm_device *dev) static void valleyview_enable_rps(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; u32 gtfifodbg, val, rc6_mode = 0; int i; @@ -3914,7 +3951,7 @@ static int ironlake_setup_rc6(struct drm_device *dev) static void ironlake_enable_rc6(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; bool was_interruptible; int ret; @@ -4426,7 +4463,7 @@ EXPORT_SYMBOL_GPL(i915_gpu_lower); bool i915_gpu_busy(void) { struct drm_i915_private *dev_priv; - struct intel_ring_buffer *ring; + struct intel_engine_cs *ring; bool ret = false; int i; @@ -4608,8 +4645,10 @@ void intel_disable_gt_powersave(struct drm_device *dev) if (IS_IRONLAKE_M(dev)) { ironlake_disable_drps(dev); ironlake_disable_rc6(dev); - } else if (IS_GEN6(dev) || IS_GEN7(dev)) { - cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work); + } else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) { + if (cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work)) + intel_runtime_pm_put(dev_priv); + cancel_work_sync(&dev_priv->rps.work); mutex_lock(&dev_priv->rps.hw_lock); if (IS_VALLEYVIEW(dev)) @@ -4655,7 +4694,7 @@ void intel_enable_gt_powersave(struct drm_device *dev) ironlake_enable_rc6(dev); intel_init_emon(dev); mutex_unlock(&dev->struct_mutex); - } else if (IS_GEN6(dev) || IS_GEN7(dev)) { + } else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) { /* * PCU communication is slow and this doesn't need to be * done at any specific time, so do this out of our fast path @@ -5335,6 +5374,59 @@ static void valleyview_init_clock_gating(struct drm_device *dev) I915_WRITE(VLV_GUNIT_CLOCK_GATE, GCFG_DIS); } +static void cherryview_init_clock_gating(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + + I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE); + + I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE); + + /* WaDisablePartialInstShootdown:chv */ + I915_WRITE(GEN8_ROW_CHICKEN, + _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE)); + + /* WaDisableThreadStallDopClockGating:chv */ + I915_WRITE(GEN8_ROW_CHICKEN, + _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE)); + + /* WaVSRefCountFullforceMissDisable:chv */ + /* WaDSRefCountFullforceMissDisable:chv */ + I915_WRITE(GEN7_FF_THREAD_MODE, + I915_READ(GEN7_FF_THREAD_MODE) & + ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME)); + + /* WaDisableSemaphoreAndSyncFlipWait:chv */ + I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL, + _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE)); + + /* WaDisableCSUnitClockGating:chv */ + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_CSUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSDEUnitClockGating:chv */ + I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) | + GEN8_SDEUNIT_CLOCK_GATE_DISABLE); + + /* WaDisableSamplerPowerBypass:chv (pre-production hw) */ + I915_WRITE(HALF_SLICE_CHICKEN3, + _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS)); + + /* WaDisableGunitClockGating:chv (pre-production hw) */ + I915_WRITE(VLV_GUNIT_CLOCK_GATE, I915_READ(VLV_GUNIT_CLOCK_GATE) | + GINT_DIS); + + /* WaDisableFfDopClockGating:chv (pre-production hw) */ + I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL, + _MASKED_BIT_ENABLE(GEN8_FF_DOP_CLOCK_GATE_DISABLE)); + + /* WaDisableDopClockGating:chv (pre-production hw) */ + I915_WRITE(GEN7_ROW_CHICKEN2, + _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE)); + I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) | + GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE); +} + static void g4x_init_clock_gating(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -5545,33 +5637,6 @@ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv) } } -static void reset_vblank_counter(struct drm_device *dev, enum pipe pipe) -{ - assert_spin_locked(&dev->vbl_lock); - - dev->vblank[pipe].last = 0; -} - -static void hsw_power_well_post_disable(struct drm_i915_private *dev_priv) -{ - struct drm_device *dev = dev_priv->dev; - enum pipe pipe; - unsigned long irqflags; - - /* - * After this, the registers on the pipes that are part of the power - * well will become zero, so we have to adjust our counters according to - * that. - * - * FIXME: Should we do this in general in drm_vblank_post_modeset? - */ - spin_lock_irqsave(&dev->vbl_lock, irqflags); - for_each_pipe(pipe) - if (pipe != PIPE_A) - reset_vblank_counter(dev, pipe); - spin_unlock_irqrestore(&dev->vbl_lock, irqflags); -} - static void hsw_set_power_well(struct drm_i915_private *dev_priv, struct i915_power_well *power_well, bool enable) { @@ -5600,8 +5665,6 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv, I915_WRITE(HSW_PWR_WELL_DRIVER, 0); POSTING_READ(HSW_PWR_WELL_DRIVER); DRM_DEBUG_KMS("Requesting to disable the power well\n"); - - hsw_power_well_post_disable(dev_priv); } } } @@ -5758,23 +5821,12 @@ static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv, static void vlv_display_power_well_disable(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { - struct drm_device *dev = dev_priv->dev; - enum pipe pipe; - WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DISP2D); spin_lock_irq(&dev_priv->irq_lock); - for_each_pipe(pipe) - __intel_set_cpu_fifo_underrun_reporting(dev, pipe, false); - valleyview_disable_display_irqs(dev_priv); spin_unlock_irq(&dev_priv->irq_lock); - spin_lock_irq(&dev->vbl_lock); - for_each_pipe(pipe) - reset_vblank_counter(dev, pipe); - spin_unlock_irq(&dev->vbl_lock); - vlv_set_power_well(dev_priv, power_well, false); } @@ -6270,6 +6322,10 @@ void intel_init_pm(struct drm_device *dev) dev_priv->display.init_clock_gating = haswell_init_clock_gating; else if (INTEL_INFO(dev)->gen == 8) dev_priv->display.init_clock_gating = gen8_init_clock_gating; + } else if (IS_CHERRYVIEW(dev)) { + dev_priv->display.update_wm = valleyview_update_wm; + dev_priv->display.init_clock_gating = + cherryview_init_clock_gating; } else if (IS_VALLEYVIEW(dev)) { dev_priv->display.update_wm = valleyview_update_wm; dev_priv->display.init_clock_gating = diff --git a/drivers/gpu/drm/i915/intel_renderstate.h b/drivers/gpu/drm/i915/intel_renderstate.h new file mode 100644 index 000000000000..a5e783a9928a --- /dev/null +++ b/drivers/gpu/drm/i915/intel_renderstate.h @@ -0,0 +1,48 @@ +/* + * Copyright © 2014 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_RENDERSTATE_H +#define _INTEL_RENDERSTATE_H + +#include <linux/types.h> + +struct intel_renderstate_rodata { + const u32 *reloc; + const u32 reloc_items; + const u32 *batch; + const u32 batch_items; +}; + +extern const struct intel_renderstate_rodata gen6_null_state; +extern const struct intel_renderstate_rodata gen7_null_state; +extern const struct intel_renderstate_rodata gen8_null_state; + +#define RO_RENDERSTATE(_g) \ + const struct intel_renderstate_rodata gen ## _g ## _null_state = { \ + .reloc = gen ## _g ## _null_state_relocs, \ + .reloc_items = sizeof(gen ## _g ## _null_state_relocs)/4, \ + .batch = gen ## _g ## _null_state_batch, \ + .batch_items = sizeof(gen ## _g ## _null_state_batch)/4, \ + } + +#endif /* INTEL_RENDERSTATE_H */ diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen6.c b/drivers/gpu/drm/i915/intel_renderstate_gen6.c new file mode 100644 index 000000000000..740538ad0977 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_renderstate_gen6.c @@ -0,0 +1,289 @@ +#include "intel_renderstate.h" + +static const u32 gen6_null_state_relocs[] = { + 0x00000020, + 0x00000024, + 0x0000002c, + 0x000001e0, + 0x000001e4, +}; + +static const u32 gen6_null_state_batch[] = { + 0x69040000, + 0x790d0001, + 0x00000000, + 0x00000000, + 0x78180000, + 0x00000001, + 0x61010008, + 0x00000000, + 0x00000001, /* reloc */ + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, + 0x00000000, + 0x00000001, + 0x61020000, + 0x00000000, + 0x78050001, + 0x00000018, + 0x00000000, + 0x780d1002, + 0x00000000, + 0x00000000, + 0x00000420, + 0x78150003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78100004, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78160003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78110005, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78120002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78170003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x79050005, + 0xe0040000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x79100000, + 0x00000000, + 0x79000002, + 0xffffffff, + 0x00000000, + 0x00000000, + 0x780e0002, + 0x00000441, + 0x00000401, + 0x00000401, + 0x78021002, + 0x00000000, + 0x00000000, + 0x00000400, + 0x78130012, + 0x00400810, + 0x00000000, + 0x20000000, + 0x04000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78140007, + 0x00000280, + 0x08080000, + 0x00000000, + 0x00060000, + 0x4e080002, + 0x00100400, + 0x00000000, + 0x00000000, + 0x78090005, + 0x02000000, + 0x22220000, + 0x02f60000, + 0x11330000, + 0x02850004, + 0x11220000, + 0x78011002, + 0x00000000, + 0x00000000, + 0x00000200, + 0x78080003, + 0x00002000, + 0x00000448, /* reloc */ + 0x00000448, /* reloc */ + 0x00000000, + 0x05000000, /* cmds end */ + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000220, /* state start */ + 0x00000240, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0060005a, + 0x204077be, + 0x000000c0, + 0x008d0040, + 0x0060005a, + 0x206077be, + 0x000000c0, + 0x008d0080, + 0x0060005a, + 0x208077be, + 0x000000d0, + 0x008d0040, + 0x0060005a, + 0x20a077be, + 0x000000d0, + 0x008d0080, + 0x00000201, + 0x20080061, + 0x00000000, + 0x00000000, + 0x00600001, + 0x20200022, + 0x008d0000, + 0x00000000, + 0x02800031, + 0x21c01cc9, + 0x00000020, + 0x0a8a0001, + 0x00600001, + 0x204003be, + 0x008d01c0, + 0x00000000, + 0x00600001, + 0x206003be, + 0x008d01e0, + 0x00000000, + 0x00600001, + 0x208003be, + 0x008d0200, + 0x00000000, + 0x00600001, + 0x20a003be, + 0x008d0220, + 0x00000000, + 0x00600001, + 0x20c003be, + 0x008d0240, + 0x00000000, + 0x00600001, + 0x20e003be, + 0x008d0260, + 0x00000000, + 0x00600001, + 0x210003be, + 0x008d0280, + 0x00000000, + 0x00600001, + 0x212003be, + 0x008d02a0, + 0x00000000, + 0x05800031, + 0x24001cc8, + 0x00000040, + 0x90019000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0000007e, + 0x00000000, + 0x00000000, + 0x00000000, + 0x30000000, + 0x00000124, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0xf99a130c, + 0x799a130c, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x80000031, + 0x00000003, + 0x00000000, /* state end */ +}; + +RO_RENDERSTATE(6); diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen7.c b/drivers/gpu/drm/i915/intel_renderstate_gen7.c new file mode 100644 index 000000000000..6fa7ff2a1298 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_renderstate_gen7.c @@ -0,0 +1,253 @@ +#include "intel_renderstate.h" + +static const u32 gen7_null_state_relocs[] = { + 0x0000000c, + 0x00000010, + 0x00000018, + 0x000001ec, +}; + +static const u32 gen7_null_state_batch[] = { + 0x69040000, + 0x61010008, + 0x00000000, + 0x00000001, /* reloc */ + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, + 0x00000000, + 0x00000001, + 0x790d0002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78180000, + 0x00000001, + 0x79160000, + 0x00000008, + 0x78300000, + 0x02010040, + 0x78310000, + 0x04000000, + 0x78320000, + 0x04000000, + 0x78330000, + 0x02000000, + 0x78100004, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781b0005, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781c0002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781d0004, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78110005, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78120002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78210000, + 0x00000000, + 0x78130005, + 0x00000000, + 0x20000000, + 0x04000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78140001, + 0x20000800, + 0x00000000, + 0x781e0001, + 0x00000000, + 0x00000000, + 0x78050005, + 0xe0040000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78040001, + 0x00000000, + 0x00000000, + 0x78240000, + 0x00000240, + 0x78230000, + 0x00000260, + 0x782f0000, + 0x00000280, + 0x781f000c, + 0x00400810, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78200006, + 0x000002c0, + 0x08080000, + 0x00000000, + 0x28000402, + 0x00060000, + 0x00000000, + 0x00000000, + 0x78090005, + 0x02000000, + 0x22220000, + 0x02f60000, + 0x11230000, + 0x02f60004, + 0x11230000, + 0x78080003, + 0x00006008, + 0x00000340, /* reloc */ + 0xffffffff, + 0x00000000, + 0x782a0000, + 0x00000360, + 0x79000002, + 0xffffffff, + 0x00000000, + 0x00000000, + 0x7b000005, + 0x0000000f, + 0x00000003, + 0x00000000, + 0x00000001, + 0x00000000, + 0x00000000, + 0x05000000, /* cmds end */ + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000031, /* state start */ + 0x00000003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0xf99a130c, + 0x799a130c, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000492, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0080005a, + 0x2e2077bd, + 0x000000c0, + 0x008d0040, + 0x0080005a, + 0x2e6077bd, + 0x000000d0, + 0x008d0040, + 0x02800031, + 0x21801fa9, + 0x008d0e20, + 0x08840001, + 0x00800001, + 0x2e2003bd, + 0x008d0180, + 0x00000000, + 0x00800001, + 0x2e6003bd, + 0x008d01c0, + 0x00000000, + 0x00800001, + 0x2ea003bd, + 0x008d0200, + 0x00000000, + 0x00800001, + 0x2ee003bd, + 0x008d0240, + 0x00000000, + 0x05800031, + 0x20001fa8, + 0x008d0e20, + 0x90031000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000380, + 0x000003a0, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, /* state end */ +}; + +RO_RENDERSTATE(7); diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen8.c b/drivers/gpu/drm/i915/intel_renderstate_gen8.c new file mode 100644 index 000000000000..5c875615d42a --- /dev/null +++ b/drivers/gpu/drm/i915/intel_renderstate_gen8.c @@ -0,0 +1,479 @@ +#include "intel_renderstate.h" + +static const u32 gen8_null_state_relocs[] = { + 0x00000048, + 0x00000050, + 0x00000060, + 0x000003ec, +}; + +static const u32 gen8_null_state_batch[] = { + 0x69040000, + 0x61020001, + 0x00000000, + 0x00000000, + 0x79120000, + 0x00000000, + 0x79130000, + 0x00000000, + 0x79140000, + 0x00000000, + 0x79150000, + 0x00000000, + 0x79160000, + 0x00000000, + 0x6101000e, + 0x00000001, + 0x00000000, + 0x00000001, + 0x00000001, /* reloc */ + 0x00000000, + 0x00000001, /* reloc */ + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000001, /* reloc */ + 0x00000000, + 0xfffff001, + 0x00001001, + 0xfffff001, + 0x00001001, + 0x78230000, + 0x000006e0, + 0x78210000, + 0x00000700, + 0x78300000, + 0x08010040, + 0x78330000, + 0x08000000, + 0x78310000, + 0x08000000, + 0x78320000, + 0x08000000, + 0x78240000, + 0x00000641, + 0x780e0000, + 0x00000601, + 0x780d0000, + 0x00000000, + 0x78180000, + 0x00000001, + 0x78520003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78190009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781b0007, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78270000, + 0x00000000, + 0x782c0000, + 0x00000000, + 0x781c0002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78160009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78110008, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78290000, + 0x00000000, + 0x782e0000, + 0x00000000, + 0x781a0009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781d0007, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78280000, + 0x00000000, + 0x782d0000, + 0x00000000, + 0x78260000, + 0x00000000, + 0x782b0000, + 0x00000000, + 0x78150009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78100007, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781e0003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78120002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x781f0002, + 0x30400820, + 0x00000000, + 0x00000000, + 0x78510009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78500003, + 0x00210000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78130002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x782a0000, + 0x00000480, + 0x782f0000, + 0x00000540, + 0x78140000, + 0x00000800, + 0x78170009, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x7820000a, + 0x00000580, + 0x00000000, + 0x08080000, + 0x00000000, + 0x00000000, + 0x1f000002, + 0x00060000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x784d0000, + 0x40000000, + 0x784f0000, + 0x80000100, + 0x780f0000, + 0x00000740, + 0x78050006, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78070003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78060003, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x78040001, + 0x00000000, + 0x00000001, + 0x79000002, + 0xffffffff, + 0x00000000, + 0x00000000, + 0x78080003, + 0x00006000, + 0x000005e0, /* reloc */ + 0x00000000, + 0x00000000, + 0x78090005, + 0x02000000, + 0x22220000, + 0x02f60000, + 0x11230000, + 0x02850004, + 0x11230000, + 0x784b0000, + 0x0000000f, + 0x78490001, + 0x00000000, + 0x00000000, + 0x7b000005, + 0x00000000, + 0x00000003, + 0x00000000, + 0x00000001, + 0x00000000, + 0x00000000, + 0x05000000, /* cmds end */ + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x000004c0, /* state start */ + 0x00000500, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000092, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x0060005a, + 0x21403ae8, + 0x3a0000c0, + 0x008d0040, + 0x0060005a, + 0x21603ae8, + 0x3a0000c0, + 0x008d0080, + 0x0060005a, + 0x21803ae8, + 0x3a0000d0, + 0x008d0040, + 0x0060005a, + 0x21a03ae8, + 0x3a0000d0, + 0x008d0080, + 0x02800031, + 0x2e0022e8, + 0x0e000140, + 0x08840001, + 0x05800031, + 0x200022e0, + 0x0e000e00, + 0x90031000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x06200000, + 0x00000002, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0xf99a130c, + 0x799a130c, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x3f800000, + 0x00000000, + 0x3f800000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, + 0x00000000, /* state end */ +}; + +RO_RENDERSTATE(8); diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 40a7aa4db589..3379722d0e6d 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -40,30 +40,37 @@ */ #define CACHELINE_BYTES 64 -static inline int ring_space(struct intel_ring_buffer *ring) +static inline int __ring_space(int head, int tail, int size) { - int space = (ring->head & HEAD_ADDR) - (ring->tail + I915_RING_FREE_SPACE); + int space = head - (tail + I915_RING_FREE_SPACE); if (space < 0) - space += ring->size; + space += size; return space; } -static bool intel_ring_stopped(struct intel_ring_buffer *ring) +static inline int ring_space(struct intel_engine_cs *ring) +{ + struct intel_ringbuffer *ringbuf = ring->buffer; + return __ring_space(ringbuf->head & HEAD_ADDR, ringbuf->tail, ringbuf->size); +} + +static bool intel_ring_stopped(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring); } -void __intel_ring_advance(struct intel_ring_buffer *ring) +void __intel_ring_advance(struct intel_engine_cs *ring) { - ring->tail &= ring->size - 1; + struct intel_ringbuffer *ringbuf = ring->buffer; + ringbuf->tail &= ringbuf->size - 1; if (intel_ring_stopped(ring)) return; - ring->write_tail(ring, ring->tail); + ring->write_tail(ring, ringbuf->tail); } static int -gen2_render_ring_flush(struct intel_ring_buffer *ring, +gen2_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { @@ -89,7 +96,7 @@ gen2_render_ring_flush(struct intel_ring_buffer *ring, } static int -gen4_render_ring_flush(struct intel_ring_buffer *ring, +gen4_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { @@ -184,7 +191,7 @@ gen4_render_ring_flush(struct intel_ring_buffer *ring, * really our business. That leaves only stall at scoreboard. */ static int -intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring) +intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring) { u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES; int ret; @@ -219,7 +226,7 @@ intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring) } static int -gen6_render_ring_flush(struct intel_ring_buffer *ring, +gen6_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { u32 flags = 0; @@ -271,7 +278,7 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring, } static int -gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring) +gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring) { int ret; @@ -289,7 +296,7 @@ gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring) return 0; } -static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value) +static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value) { int ret; @@ -313,7 +320,7 @@ static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value) } static int -gen7_render_ring_flush(struct intel_ring_buffer *ring, +gen7_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { u32 flags = 0; @@ -374,7 +381,7 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring, } static int -gen8_render_ring_flush(struct intel_ring_buffer *ring, +gen8_render_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { u32 flags = 0; @@ -414,14 +421,14 @@ gen8_render_ring_flush(struct intel_ring_buffer *ring, } -static void ring_write_tail(struct intel_ring_buffer *ring, +static void ring_write_tail(struct intel_engine_cs *ring, u32 value) { struct drm_i915_private *dev_priv = ring->dev->dev_private; I915_WRITE_TAIL(ring, value); } -u64 intel_ring_get_active_head(struct intel_ring_buffer *ring) +u64 intel_ring_get_active_head(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; u64 acthd; @@ -437,7 +444,7 @@ u64 intel_ring_get_active_head(struct intel_ring_buffer *ring) return acthd; } -static void ring_setup_phys_status_page(struct intel_ring_buffer *ring) +static void ring_setup_phys_status_page(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; u32 addr; @@ -448,7 +455,7 @@ static void ring_setup_phys_status_page(struct intel_ring_buffer *ring) I915_WRITE(HWS_PGA, addr); } -static bool stop_ring(struct intel_ring_buffer *ring) +static bool stop_ring(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = to_i915(ring->dev); @@ -472,11 +479,12 @@ static bool stop_ring(struct intel_ring_buffer *ring) return (I915_READ_HEAD(ring) & HEAD_ADDR) == 0; } -static int init_ring_common(struct intel_ring_buffer *ring) +static int init_ring_common(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct drm_i915_gem_object *obj = ring->obj; + struct intel_ringbuffer *ringbuf = ring->buffer; + struct drm_i915_gem_object *obj = ringbuf->obj; int ret = 0; gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL); @@ -515,7 +523,7 @@ static int init_ring_common(struct intel_ring_buffer *ring) * register values. */ I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj)); I915_WRITE_CTL(ring, - ((ring->size - PAGE_SIZE) & RING_NR_PAGES) + ((ringbuf->size - PAGE_SIZE) & RING_NR_PAGES) | RING_VALID); /* If the head is still not zero, the ring is dead */ @@ -535,10 +543,10 @@ static int init_ring_common(struct intel_ring_buffer *ring) if (!drm_core_check_feature(ring->dev, DRIVER_MODESET)) i915_kernel_lost_context(ring->dev); else { - ring->head = I915_READ_HEAD(ring); - ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR; - ring->space = ring_space(ring); - ring->last_retired_head = -1; + ringbuf->head = I915_READ_HEAD(ring); + ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR; + ringbuf->space = ring_space(ring); + ringbuf->last_retired_head = -1; } memset(&ring->hangcheck, 0, sizeof(ring->hangcheck)); @@ -550,7 +558,7 @@ out: } static int -init_pipe_control(struct intel_ring_buffer *ring) +init_pipe_control(struct intel_engine_cs *ring) { int ret; @@ -591,7 +599,7 @@ err: return ret; } -static int init_render_ring(struct intel_ring_buffer *ring) +static int init_render_ring(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -605,7 +613,7 @@ static int init_render_ring(struct intel_ring_buffer *ring) * to use MI_WAIT_FOR_EVENT within the CS. It should already be * programmed to '1' on all products. * - * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw + * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv */ if (INTEL_INFO(dev)->gen >= 6) I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE)); @@ -647,7 +655,7 @@ static int init_render_ring(struct intel_ring_buffer *ring) return ret; } -static void render_ring_cleanup(struct intel_ring_buffer *ring) +static void render_ring_cleanup(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; @@ -663,12 +671,12 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring) ring->scratch.obj = NULL; } -static int gen6_signal(struct intel_ring_buffer *signaller, +static int gen6_signal(struct intel_engine_cs *signaller, unsigned int num_dwords) { struct drm_device *dev = signaller->dev; struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *useless; + struct intel_engine_cs *useless; int i, ret; /* NB: In order to be able to do semaphore MBOX updates for varying @@ -679,6 +687,8 @@ static int gen6_signal(struct intel_ring_buffer *signaller, #define MBOX_UPDATE_DWORDS 4 if (i915_semaphore_is_enabled(dev)) num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS); + else + return intel_ring_begin(signaller, num_dwords); ret = intel_ring_begin(signaller, num_dwords); if (ret) @@ -713,7 +723,7 @@ static int gen6_signal(struct intel_ring_buffer *signaller, * This acts like a signal in the canonical semaphore. */ static int -gen6_add_request(struct intel_ring_buffer *ring) +gen6_add_request(struct intel_engine_cs *ring) { int ret; @@ -745,8 +755,8 @@ static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev, * @seqno - seqno which the waiter will block on */ static int -gen6_ring_sync(struct intel_ring_buffer *waiter, - struct intel_ring_buffer *signaller, +gen6_ring_sync(struct intel_engine_cs *waiter, + struct intel_engine_cs *signaller, u32 seqno) { u32 dw1 = MI_SEMAPHORE_MBOX | @@ -794,7 +804,7 @@ do { \ } while (0) static int -pc_render_add_request(struct intel_ring_buffer *ring) +pc_render_add_request(struct intel_engine_cs *ring) { u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES; int ret; @@ -842,7 +852,7 @@ pc_render_add_request(struct intel_ring_buffer *ring) } static u32 -gen6_ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) +gen6_ring_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency) { /* Workaround to force correct ordering between irq and seqno writes on * ivb (and maybe also on snb) by reading from a CS register (like @@ -856,31 +866,31 @@ gen6_ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) } static u32 -ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) +ring_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency) { return intel_read_status_page(ring, I915_GEM_HWS_INDEX); } static void -ring_set_seqno(struct intel_ring_buffer *ring, u32 seqno) +ring_set_seqno(struct intel_engine_cs *ring, u32 seqno) { intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno); } static u32 -pc_render_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency) +pc_render_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency) { return ring->scratch.cpu_page[0]; } static void -pc_render_set_seqno(struct intel_ring_buffer *ring, u32 seqno) +pc_render_set_seqno(struct intel_engine_cs *ring, u32 seqno) { ring->scratch.cpu_page[0] = seqno; } static bool -gen5_ring_get_irq(struct intel_ring_buffer *ring) +gen5_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -898,7 +908,7 @@ gen5_ring_get_irq(struct intel_ring_buffer *ring) } static void -gen5_ring_put_irq(struct intel_ring_buffer *ring) +gen5_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -911,7 +921,7 @@ gen5_ring_put_irq(struct intel_ring_buffer *ring) } static bool -i9xx_ring_get_irq(struct intel_ring_buffer *ring) +i9xx_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -932,7 +942,7 @@ i9xx_ring_get_irq(struct intel_ring_buffer *ring) } static void -i9xx_ring_put_irq(struct intel_ring_buffer *ring) +i9xx_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -948,7 +958,7 @@ i9xx_ring_put_irq(struct intel_ring_buffer *ring) } static bool -i8xx_ring_get_irq(struct intel_ring_buffer *ring) +i8xx_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -969,7 +979,7 @@ i8xx_ring_get_irq(struct intel_ring_buffer *ring) } static void -i8xx_ring_put_irq(struct intel_ring_buffer *ring) +i8xx_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -984,7 +994,7 @@ i8xx_ring_put_irq(struct intel_ring_buffer *ring) spin_unlock_irqrestore(&dev_priv->irq_lock, flags); } -void intel_ring_setup_status_page(struct intel_ring_buffer *ring) +void intel_ring_setup_status_page(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1047,7 +1057,7 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring) } static int -bsd_ring_flush(struct intel_ring_buffer *ring, +bsd_ring_flush(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains) { @@ -1064,7 +1074,7 @@ bsd_ring_flush(struct intel_ring_buffer *ring, } static int -i9xx_add_request(struct intel_ring_buffer *ring) +i9xx_add_request(struct intel_engine_cs *ring) { int ret; @@ -1082,7 +1092,7 @@ i9xx_add_request(struct intel_ring_buffer *ring) } static bool -gen6_ring_get_irq(struct intel_ring_buffer *ring) +gen6_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1107,7 +1117,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring) } static void -gen6_ring_put_irq(struct intel_ring_buffer *ring) +gen6_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1125,7 +1135,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring) } static bool -hsw_vebox_get_irq(struct intel_ring_buffer *ring) +hsw_vebox_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1145,7 +1155,7 @@ hsw_vebox_get_irq(struct intel_ring_buffer *ring) } static void -hsw_vebox_put_irq(struct intel_ring_buffer *ring) +hsw_vebox_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1163,7 +1173,7 @@ hsw_vebox_put_irq(struct intel_ring_buffer *ring) } static bool -gen8_ring_get_irq(struct intel_ring_buffer *ring) +gen8_ring_get_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1189,7 +1199,7 @@ gen8_ring_get_irq(struct intel_ring_buffer *ring) } static void -gen8_ring_put_irq(struct intel_ring_buffer *ring) +gen8_ring_put_irq(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; @@ -1209,7 +1219,7 @@ gen8_ring_put_irq(struct intel_ring_buffer *ring) } static int -i965_dispatch_execbuffer(struct intel_ring_buffer *ring, +i965_dispatch_execbuffer(struct intel_engine_cs *ring, u64 offset, u32 length, unsigned flags) { @@ -1232,7 +1242,7 @@ i965_dispatch_execbuffer(struct intel_ring_buffer *ring, /* Just userspace ABI convention to limit the wa batch bo to a resonable size */ #define I830_BATCH_LIMIT (256*1024) static int -i830_dispatch_execbuffer(struct intel_ring_buffer *ring, +i830_dispatch_execbuffer(struct intel_engine_cs *ring, u64 offset, u32 len, unsigned flags) { @@ -1283,7 +1293,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring, } static int -i915_dispatch_execbuffer(struct intel_ring_buffer *ring, +i915_dispatch_execbuffer(struct intel_engine_cs *ring, u64 offset, u32 len, unsigned flags) { @@ -1300,7 +1310,7 @@ i915_dispatch_execbuffer(struct intel_ring_buffer *ring, return 0; } -static void cleanup_status_page(struct intel_ring_buffer *ring) +static void cleanup_status_page(struct intel_engine_cs *ring) { struct drm_i915_gem_object *obj; @@ -1314,7 +1324,7 @@ static void cleanup_status_page(struct intel_ring_buffer *ring) ring->status_page.obj = NULL; } -static int init_status_page(struct intel_ring_buffer *ring) +static int init_status_page(struct intel_engine_cs *ring) { struct drm_i915_gem_object *obj; @@ -1351,7 +1361,7 @@ err_unref: return 0; } -static int init_phys_status_page(struct intel_ring_buffer *ring) +static int init_phys_status_page(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1368,21 +1378,22 @@ static int init_phys_status_page(struct intel_ring_buffer *ring) return 0; } -static int allocate_ring_buffer(struct intel_ring_buffer *ring) +static int allocate_ring_buffer(struct intel_engine_cs *ring) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_ringbuffer *ringbuf = ring->buffer; struct drm_i915_gem_object *obj; int ret; - if (ring->obj) + if (intel_ring_initialized(ring)) return 0; obj = NULL; if (!HAS_LLC(dev)) - obj = i915_gem_object_create_stolen(dev, ring->size); + obj = i915_gem_object_create_stolen(dev, ringbuf->size); if (obj == NULL) - obj = i915_gem_alloc_object(dev, ring->size); + obj = i915_gem_alloc_object(dev, ringbuf->size); if (obj == NULL) return -ENOMEM; @@ -1394,15 +1405,15 @@ static int allocate_ring_buffer(struct intel_ring_buffer *ring) if (ret) goto err_unpin; - ring->virtual_start = + ringbuf->virtual_start = ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj), - ring->size); - if (ring->virtual_start == NULL) { + ringbuf->size); + if (ringbuf->virtual_start == NULL) { ret = -EINVAL; goto err_unpin; } - ring->obj = obj; + ringbuf->obj = obj; return 0; err_unpin: @@ -1413,14 +1424,22 @@ err_unref: } static int intel_init_ring_buffer(struct drm_device *dev, - struct intel_ring_buffer *ring) + struct intel_engine_cs *ring) { + struct intel_ringbuffer *ringbuf = ring->buffer; int ret; + if (ringbuf == NULL) { + ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL); + if (!ringbuf) + return -ENOMEM; + ring->buffer = ringbuf; + } + ring->dev = dev; INIT_LIST_HEAD(&ring->active_list); INIT_LIST_HEAD(&ring->request_list); - ring->size = 32 * PAGE_SIZE; + ringbuf->size = 32 * PAGE_SIZE; memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno)); init_waitqueue_head(&ring->irq_queue); @@ -1428,48 +1447,60 @@ static int intel_init_ring_buffer(struct drm_device *dev, if (I915_NEED_GFX_HWS(dev)) { ret = init_status_page(ring); if (ret) - return ret; + goto error; } else { BUG_ON(ring->id != RCS); ret = init_phys_status_page(ring); if (ret) - return ret; + goto error; } ret = allocate_ring_buffer(ring); if (ret) { DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", ring->name, ret); - return ret; + goto error; } /* Workaround an erratum on the i830 which causes a hang if * the TAIL pointer points to within the last 2 cachelines * of the buffer. */ - ring->effective_size = ring->size; + ringbuf->effective_size = ringbuf->size; if (IS_I830(dev) || IS_845G(dev)) - ring->effective_size -= 2 * CACHELINE_BYTES; + ringbuf->effective_size -= 2 * CACHELINE_BYTES; - i915_cmd_parser_init_ring(ring); + ret = i915_cmd_parser_init_ring(ring); + if (ret) + goto error; - return ring->init(ring); + ret = ring->init(ring); + if (ret) + goto error; + + return 0; + +error: + kfree(ringbuf); + ring->buffer = NULL; + return ret; } -void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring) +void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) { struct drm_i915_private *dev_priv = to_i915(ring->dev); + struct intel_ringbuffer *ringbuf = ring->buffer; - if (ring->obj == NULL) + if (!intel_ring_initialized(ring)) return; intel_stop_ring_buffer(ring); WARN_ON((I915_READ_MODE(ring) & MODE_IDLE) == 0); - iounmap(ring->virtual_start); + iounmap(ringbuf->virtual_start); - i915_gem_object_ggtt_unpin(ring->obj); - drm_gem_object_unreference(&ring->obj->base); - ring->obj = NULL; + i915_gem_object_ggtt_unpin(ringbuf->obj); + drm_gem_object_unreference(&ringbuf->obj->base); + ringbuf->obj = NULL; ring->preallocated_lazy_request = NULL; ring->outstanding_lazy_seqno = 0; @@ -1477,44 +1508,34 @@ void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring) ring->cleanup(ring); cleanup_status_page(ring); + + i915_cmd_parser_fini_ring(ring); + + kfree(ringbuf); + ring->buffer = NULL; } -static int intel_ring_wait_request(struct intel_ring_buffer *ring, int n) +static int intel_ring_wait_request(struct intel_engine_cs *ring, int n) { + struct intel_ringbuffer *ringbuf = ring->buffer; struct drm_i915_gem_request *request; - u32 seqno = 0, tail; + u32 seqno = 0; int ret; - if (ring->last_retired_head != -1) { - ring->head = ring->last_retired_head; - ring->last_retired_head = -1; + if (ringbuf->last_retired_head != -1) { + ringbuf->head = ringbuf->last_retired_head; + ringbuf->last_retired_head = -1; - ring->space = ring_space(ring); - if (ring->space >= n) + ringbuf->space = ring_space(ring); + if (ringbuf->space >= n) return 0; } list_for_each_entry(request, &ring->request_list, list) { - int space; - - if (request->tail == -1) - continue; - - space = request->tail - (ring->tail + I915_RING_FREE_SPACE); - if (space < 0) - space += ring->size; - if (space >= n) { + if (__ring_space(request->tail, ringbuf->tail, ringbuf->size) >= n) { seqno = request->seqno; - tail = request->tail; break; } - - /* Consume this request in case we need more space than - * is available and so need to prevent a race between - * updating last_retired_head and direct reads of - * I915_RING_HEAD. It also provides a nice sanity check. - */ - request->tail = -1; } if (seqno == 0) @@ -1524,18 +1545,19 @@ static int intel_ring_wait_request(struct intel_ring_buffer *ring, int n) if (ret) return ret; - ring->head = tail; - ring->space = ring_space(ring); - if (WARN_ON(ring->space < n)) - return -ENOSPC; + i915_gem_retire_requests_ring(ring); + ringbuf->head = ringbuf->last_retired_head; + ringbuf->last_retired_head = -1; + ringbuf->space = ring_space(ring); return 0; } -static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) +static int ring_wait_for_space(struct intel_engine_cs *ring, int n) { struct drm_device *dev = ring->dev; struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_ringbuffer *ringbuf = ring->buffer; unsigned long end; int ret; @@ -1546,7 +1568,6 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) /* force the tail write in case we have been skipping them */ __intel_ring_advance(ring); - trace_i915_ring_wait_begin(ring); /* With GEM the hangcheck timer should kick us out of the loop, * leaving it early runs the risk of corrupting GEM state (due * to running on almost untested codepaths). But on resume @@ -1554,12 +1575,13 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) * case by choosing an insanely large timeout. */ end = jiffies + 60 * HZ; + trace_i915_ring_wait_begin(ring); do { - ring->head = I915_READ_HEAD(ring); - ring->space = ring_space(ring); - if (ring->space >= n) { - trace_i915_ring_wait_end(ring); - return 0; + ringbuf->head = I915_READ_HEAD(ring); + ringbuf->space = ring_space(ring); + if (ringbuf->space >= n) { + ret = 0; + break; } if (!drm_core_check_feature(dev, DRIVER_MODESET) && @@ -1571,38 +1593,49 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n) msleep(1); + if (dev_priv->mm.interruptible && signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + ret = i915_gem_check_wedge(&dev_priv->gpu_error, dev_priv->mm.interruptible); if (ret) - return ret; - } while (!time_after(jiffies, end)); + break; + + if (time_after(jiffies, end)) { + ret = -EBUSY; + break; + } + } while (1); trace_i915_ring_wait_end(ring); - return -EBUSY; + return ret; } -static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring) +static int intel_wrap_ring_buffer(struct intel_engine_cs *ring) { uint32_t __iomem *virt; - int rem = ring->size - ring->tail; + struct intel_ringbuffer *ringbuf = ring->buffer; + int rem = ringbuf->size - ringbuf->tail; - if (ring->space < rem) { + if (ringbuf->space < rem) { int ret = ring_wait_for_space(ring, rem); if (ret) return ret; } - virt = ring->virtual_start + ring->tail; + virt = ringbuf->virtual_start + ringbuf->tail; rem /= 4; while (rem--) iowrite32(MI_NOOP, virt++); - ring->tail = 0; - ring->space = ring_space(ring); + ringbuf->tail = 0; + ringbuf->space = ring_space(ring); return 0; } -int intel_ring_idle(struct intel_ring_buffer *ring) +int intel_ring_idle(struct intel_engine_cs *ring) { u32 seqno; int ret; @@ -1626,7 +1659,7 @@ int intel_ring_idle(struct intel_ring_buffer *ring) } static int -intel_ring_alloc_seqno(struct intel_ring_buffer *ring) +intel_ring_alloc_seqno(struct intel_engine_cs *ring) { if (ring->outstanding_lazy_seqno) return 0; @@ -1644,18 +1677,19 @@ intel_ring_alloc_seqno(struct intel_ring_buffer *ring) return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno); } -static int __intel_ring_prepare(struct intel_ring_buffer *ring, +static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes) { + struct intel_ringbuffer *ringbuf = ring->buffer; int ret; - if (unlikely(ring->tail + bytes > ring->effective_size)) { + if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) { ret = intel_wrap_ring_buffer(ring); if (unlikely(ret)) return ret; } - if (unlikely(ring->space < bytes)) { + if (unlikely(ringbuf->space < bytes)) { ret = ring_wait_for_space(ring, bytes); if (unlikely(ret)) return ret; @@ -1664,7 +1698,7 @@ static int __intel_ring_prepare(struct intel_ring_buffer *ring, return 0; } -int intel_ring_begin(struct intel_ring_buffer *ring, +int intel_ring_begin(struct intel_engine_cs *ring, int num_dwords) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1684,14 +1718,14 @@ int intel_ring_begin(struct intel_ring_buffer *ring, if (ret) return ret; - ring->space -= num_dwords * sizeof(uint32_t); + ring->buffer->space -= num_dwords * sizeof(uint32_t); return 0; } /* Align the ring tail to a cacheline boundary */ -int intel_ring_cacheline_align(struct intel_ring_buffer *ring) +int intel_ring_cacheline_align(struct intel_engine_cs *ring) { - int num_dwords = (ring->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t); + int num_dwords = (ring->buffer->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t); int ret; if (num_dwords == 0) @@ -1710,7 +1744,7 @@ int intel_ring_cacheline_align(struct intel_ring_buffer *ring) return 0; } -void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno) +void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1727,7 +1761,7 @@ void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno) ring->hangcheck.seqno = seqno; } -static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring, +static void gen6_bsd_ring_write_tail(struct intel_engine_cs *ring, u32 value) { struct drm_i915_private *dev_priv = ring->dev->dev_private; @@ -1760,7 +1794,7 @@ static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring, _MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE)); } -static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring, +static int gen6_bsd_ring_flush(struct intel_engine_cs *ring, u32 invalidate, u32 flush) { uint32_t cmd; @@ -1796,7 +1830,7 @@ static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring, } static int -gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, +gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring, u64 offset, u32 len, unsigned flags) { @@ -1820,7 +1854,7 @@ gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, } static int -hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, +hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring, u64 offset, u32 len, unsigned flags) { @@ -1841,7 +1875,7 @@ hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, } static int -gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, +gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring, u64 offset, u32 len, unsigned flags) { @@ -1863,7 +1897,7 @@ gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring, /* Blitter support (SandyBridge+) */ -static int gen6_ring_flush(struct intel_ring_buffer *ring, +static int gen6_ring_flush(struct intel_engine_cs *ring, u32 invalidate, u32 flush) { struct drm_device *dev = ring->dev; @@ -1906,7 +1940,7 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring, int intel_init_render_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; ring->name = "render ring"; ring->id = RCS; @@ -2016,16 +2050,25 @@ int intel_init_render_ring_buffer(struct drm_device *dev) int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[RCS]; + struct intel_engine_cs *ring = &dev_priv->ring[RCS]; + struct intel_ringbuffer *ringbuf = ring->buffer; int ret; + if (ringbuf == NULL) { + ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL); + if (!ringbuf) + return -ENOMEM; + ring->buffer = ringbuf; + } + ring->name = "render ring"; ring->id = RCS; ring->mmio_base = RENDER_RING_BASE; if (INTEL_INFO(dev)->gen >= 6) { /* non-kms not supported on gen6+ */ - return -ENODEV; + ret = -ENODEV; + goto err_ringbuf; } /* Note: gem is not supported on gen5/ilk without kms (the corresponding @@ -2060,31 +2103,39 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size) INIT_LIST_HEAD(&ring->active_list); INIT_LIST_HEAD(&ring->request_list); - ring->size = size; - ring->effective_size = ring->size; + ringbuf->size = size; + ringbuf->effective_size = ringbuf->size; if (IS_I830(ring->dev) || IS_845G(ring->dev)) - ring->effective_size -= 2 * CACHELINE_BYTES; + ringbuf->effective_size -= 2 * CACHELINE_BYTES; - ring->virtual_start = ioremap_wc(start, size); - if (ring->virtual_start == NULL) { + ringbuf->virtual_start = ioremap_wc(start, size); + if (ringbuf->virtual_start == NULL) { DRM_ERROR("can not ioremap virtual address for" " ring buffer\n"); - return -ENOMEM; + ret = -ENOMEM; + goto err_ringbuf; } if (!I915_NEED_GFX_HWS(dev)) { ret = init_phys_status_page(ring); if (ret) - return ret; + goto err_vstart; } return 0; + +err_vstart: + iounmap(ringbuf->virtual_start); +err_ringbuf: + kfree(ringbuf); + ring->buffer = NULL; + return ret; } int intel_init_bsd_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[VCS]; + struct intel_engine_cs *ring = &dev_priv->ring[VCS]; ring->name = "bsd ring"; ring->id = VCS; @@ -2160,7 +2211,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev) int intel_init_bsd2_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[VCS2]; + struct intel_engine_cs *ring = &dev_priv->ring[VCS2]; if ((INTEL_INFO(dev)->gen != 8)) { DRM_ERROR("No dual-BSD ring on non-BDW machine\n"); @@ -2183,6 +2234,7 @@ int intel_init_bsd2_ring_buffer(struct drm_device *dev) ring->dispatch_execbuffer = gen8_ring_dispatch_execbuffer; ring->semaphore.sync_to = gen6_ring_sync; + ring->semaphore.signal = gen6_signal; /* * The current semaphore is only applied on the pre-gen8. And there * is no bsd2 ring on the pre-gen8. So now the semaphore_register @@ -2208,7 +2260,7 @@ int intel_init_bsd2_ring_buffer(struct drm_device *dev) int intel_init_blt_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[BCS]; + struct intel_engine_cs *ring = &dev_priv->ring[BCS]; ring->name = "blitter ring"; ring->id = BCS; @@ -2257,7 +2309,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev) int intel_init_vebox_ring_buffer(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_ring_buffer *ring = &dev_priv->ring[VECS]; + struct intel_engine_cs *ring = &dev_priv->ring[VECS]; ring->name = "video enhancement ring"; ring->id = VECS; @@ -2299,7 +2351,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev) } int -intel_ring_flush_all_caches(struct intel_ring_buffer *ring) +intel_ring_flush_all_caches(struct intel_engine_cs *ring) { int ret; @@ -2317,7 +2369,7 @@ intel_ring_flush_all_caches(struct intel_ring_buffer *ring) } int -intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring) +intel_ring_invalidate_all_caches(struct intel_engine_cs *ring) { uint32_t flush_domains; int ret; @@ -2337,7 +2389,7 @@ intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring) } void -intel_stop_ring_buffer(struct intel_ring_buffer *ring) +intel_stop_ring_buffer(struct intel_engine_cs *ring) { int ret; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 72c3c15f6240..910c83cf7d44 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -1,6 +1,10 @@ #ifndef _INTEL_RINGBUFFER_H_ #define _INTEL_RINGBUFFER_H_ +#include <linux/hashtable.h> + +#define I915_CMD_HASH_ORDER 9 + /* * Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use" * Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use" @@ -54,7 +58,28 @@ struct intel_ring_hangcheck { bool deadlock; }; -struct intel_ring_buffer { +struct intel_ringbuffer { + struct drm_i915_gem_object *obj; + void __iomem *virtual_start; + + u32 head; + u32 tail; + int space; + int size; + int effective_size; + + /** We track the position of the requests in the ring buffer, and + * when each is retired we increment last_retired_head as the GPU + * must have finished processing the request and so we know we + * can advance the ringbuffer up to that position. + * + * last_retired_head is set to -1 after the value is consumed so + * we can detect new retirements. + */ + u32 last_retired_head; +}; + +struct intel_engine_cs { const char *name; enum intel_ring_id { RCS = 0x0, @@ -66,57 +91,41 @@ struct intel_ring_buffer { #define I915_NUM_RINGS 5 #define LAST_USER_RING (VECS + 1) u32 mmio_base; - void __iomem *virtual_start; struct drm_device *dev; - struct drm_i915_gem_object *obj; + struct intel_ringbuffer *buffer; - u32 head; - u32 tail; - int space; - int size; - int effective_size; struct intel_hw_status_page status_page; - /** We track the position of the requests in the ring buffer, and - * when each is retired we increment last_retired_head as the GPU - * must have finished processing the request and so we know we - * can advance the ringbuffer up to that position. - * - * last_retired_head is set to -1 after the value is consumed so - * we can detect new retirements. - */ - u32 last_retired_head; - unsigned irq_refcount; /* protected by dev_priv->irq_lock */ u32 irq_enable_mask; /* bitmask to enable ring interrupt */ u32 trace_irq_seqno; - bool __must_check (*irq_get)(struct intel_ring_buffer *ring); - void (*irq_put)(struct intel_ring_buffer *ring); + bool __must_check (*irq_get)(struct intel_engine_cs *ring); + void (*irq_put)(struct intel_engine_cs *ring); - int (*init)(struct intel_ring_buffer *ring); + int (*init)(struct intel_engine_cs *ring); - void (*write_tail)(struct intel_ring_buffer *ring, + void (*write_tail)(struct intel_engine_cs *ring, u32 value); - int __must_check (*flush)(struct intel_ring_buffer *ring, + int __must_check (*flush)(struct intel_engine_cs *ring, u32 invalidate_domains, u32 flush_domains); - int (*add_request)(struct intel_ring_buffer *ring); + int (*add_request)(struct intel_engine_cs *ring); /* Some chipsets are not quite as coherent as advertised and need * an expensive kick to force a true read of the up-to-date seqno. * However, the up-to-date seqno is not always required and the last * seen value is good enough. Note that the seqno will always be * monotonic, even if not coherent. */ - u32 (*get_seqno)(struct intel_ring_buffer *ring, + u32 (*get_seqno)(struct intel_engine_cs *ring, bool lazy_coherency); - void (*set_seqno)(struct intel_ring_buffer *ring, + void (*set_seqno)(struct intel_engine_cs *ring, u32 seqno); - int (*dispatch_execbuffer)(struct intel_ring_buffer *ring, + int (*dispatch_execbuffer)(struct intel_engine_cs *ring, u64 offset, u32 length, unsigned flags); #define I915_DISPATCH_SECURE 0x1 #define I915_DISPATCH_PINNED 0x2 - void (*cleanup)(struct intel_ring_buffer *ring); + void (*cleanup)(struct intel_engine_cs *ring); struct { u32 sync_seqno[I915_NUM_RINGS-1]; @@ -129,10 +138,10 @@ struct intel_ring_buffer { } mbox; /* AKA wait() */ - int (*sync_to)(struct intel_ring_buffer *ring, - struct intel_ring_buffer *to, + int (*sync_to)(struct intel_engine_cs *ring, + struct intel_engine_cs *to, u32 seqno); - int (*signal)(struct intel_ring_buffer *signaller, + int (*signal)(struct intel_engine_cs *signaller, /* num_dwords needed by caller */ unsigned int num_dwords); } semaphore; @@ -165,8 +174,8 @@ struct intel_ring_buffer { wait_queue_head_t irq_queue; - struct i915_hw_context *default_context; - struct i915_hw_context *last_context; + struct intel_context *default_context; + struct intel_context *last_context; struct intel_ring_hangcheck hangcheck; @@ -176,12 +185,13 @@ struct intel_ring_buffer { volatile u32 *cpu_page; } scratch; + bool needs_cmd_parser; + /* - * Tables of commands the command parser needs to know about + * Table of commands the command parser needs to know about * for this ring. */ - const struct drm_i915_cmd_table *cmd_tables; - int cmd_table_count; + DECLARE_HASHTABLE(cmd_hash, I915_CMD_HASH_ORDER); /* * Table of registers allowed in commands that read/write registers. @@ -210,20 +220,20 @@ struct intel_ring_buffer { }; static inline bool -intel_ring_initialized(struct intel_ring_buffer *ring) +intel_ring_initialized(struct intel_engine_cs *ring) { - return ring->obj != NULL; + return ring->buffer && ring->buffer->obj; } static inline unsigned -intel_ring_flag(struct intel_ring_buffer *ring) +intel_ring_flag(struct intel_engine_cs *ring) { return 1 << ring->id; } static inline u32 -intel_ring_sync_index(struct intel_ring_buffer *ring, - struct intel_ring_buffer *other) +intel_ring_sync_index(struct intel_engine_cs *ring, + struct intel_engine_cs *other) { int idx; @@ -241,7 +251,7 @@ intel_ring_sync_index(struct intel_ring_buffer *ring, } static inline u32 -intel_read_status_page(struct intel_ring_buffer *ring, +intel_read_status_page(struct intel_engine_cs *ring, int reg) { /* Ensure that the compiler doesn't optimize away the load. */ @@ -250,7 +260,7 @@ intel_read_status_page(struct intel_ring_buffer *ring, } static inline void -intel_write_status_page(struct intel_ring_buffer *ring, +intel_write_status_page(struct intel_engine_cs *ring, int reg, u32 value) { ring->status_page.page_addr[reg] = value; @@ -275,27 +285,29 @@ intel_write_status_page(struct intel_ring_buffer *ring, #define I915_GEM_HWS_SCRATCH_INDEX 0x30 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT) -void intel_stop_ring_buffer(struct intel_ring_buffer *ring); -void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring); +void intel_stop_ring_buffer(struct intel_engine_cs *ring); +void intel_cleanup_ring_buffer(struct intel_engine_cs *ring); -int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n); -int __must_check intel_ring_cacheline_align(struct intel_ring_buffer *ring); -static inline void intel_ring_emit(struct intel_ring_buffer *ring, +int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n); +int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring); +static inline void intel_ring_emit(struct intel_engine_cs *ring, u32 data) { - iowrite32(data, ring->virtual_start + ring->tail); - ring->tail += 4; + struct intel_ringbuffer *ringbuf = ring->buffer; + iowrite32(data, ringbuf->virtual_start + ringbuf->tail); + ringbuf->tail += 4; } -static inline void intel_ring_advance(struct intel_ring_buffer *ring) +static inline void intel_ring_advance(struct intel_engine_cs *ring) { - ring->tail &= ring->size - 1; + struct intel_ringbuffer *ringbuf = ring->buffer; + ringbuf->tail &= ringbuf->size - 1; } -void __intel_ring_advance(struct intel_ring_buffer *ring); +void __intel_ring_advance(struct intel_engine_cs *ring); -int __must_check intel_ring_idle(struct intel_ring_buffer *ring); -void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno); -int intel_ring_flush_all_caches(struct intel_ring_buffer *ring); -int intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring); +int __must_check intel_ring_idle(struct intel_engine_cs *ring); +void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno); +int intel_ring_flush_all_caches(struct intel_engine_cs *ring); +int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring); int intel_init_render_ring_buffer(struct drm_device *dev); int intel_init_bsd_ring_buffer(struct drm_device *dev); @@ -303,21 +315,21 @@ int intel_init_bsd2_ring_buffer(struct drm_device *dev); int intel_init_blt_ring_buffer(struct drm_device *dev); int intel_init_vebox_ring_buffer(struct drm_device *dev); -u64 intel_ring_get_active_head(struct intel_ring_buffer *ring); -void intel_ring_setup_status_page(struct intel_ring_buffer *ring); +u64 intel_ring_get_active_head(struct intel_engine_cs *ring); +void intel_ring_setup_status_page(struct intel_engine_cs *ring); -static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring) +static inline u32 intel_ring_get_tail(struct intel_engine_cs *ring) { - return ring->tail; + return ring->buffer->tail; } -static inline u32 intel_ring_get_seqno(struct intel_ring_buffer *ring) +static inline u32 intel_ring_get_seqno(struct intel_engine_cs *ring) { BUG_ON(ring->outstanding_lazy_seqno == 0); return ring->outstanding_lazy_seqno; } -static inline void i915_trace_irq_get(struct intel_ring_buffer *ring, u32 seqno) +static inline void i915_trace_irq_get(struct intel_engine_cs *ring, u32 seqno) { if (ring->trace_irq_seqno == 0 && ring->irq_get(ring)) ring->trace_irq_seqno = seqno; diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 2bf09e8eb5ed..aa2c609fccf1 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -1153,20 +1153,21 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder, pipe_config->pixel_multiplier = intel_sdvo_get_pixel_multiplier(adjusted_mode); + pipe_config->has_hdmi_sink = intel_sdvo->has_hdmi_monitor; + if (intel_sdvo->color_range_auto) { /* See CEA-861-E - 5.1 Default Encoding Parameters */ /* FIXME: This bit is only valid when using TMDS encoding and 8 * bit per color mode. */ - if (intel_sdvo->has_hdmi_monitor && + if (pipe_config->has_hdmi_sink && drm_match_cea_mode(adjusted_mode) > 1) - intel_sdvo->color_range = HDMI_COLOR_RANGE_16_235; - else - intel_sdvo->color_range = 0; + pipe_config->limited_color_range = true; + } else { + if (pipe_config->has_hdmi_sink && + intel_sdvo->color_range == HDMI_COLOR_RANGE_16_235) + pipe_config->limited_color_range = true; } - if (intel_sdvo->color_range) - pipe_config->limited_color_range = true; - /* Clock computation needs to happen after pixel multiplier. */ if (intel_sdvo->is_tv) i9xx_adjust_sdvo_tv_clock(pipe_config); @@ -1223,7 +1224,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder) if (!intel_sdvo_set_target_input(intel_sdvo)) return; - if (intel_sdvo->has_hdmi_monitor) { + if (crtc->config.has_hdmi_sink) { intel_sdvo_set_encode(intel_sdvo, SDVO_ENCODE_HDMI); intel_sdvo_set_colorimetry(intel_sdvo, SDVO_COLORIMETRY_RGB256); @@ -1258,8 +1259,8 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder) /* The real mode polarity is set by the SDVO commands, using * struct intel_sdvo_dtd. */ sdvox = SDVO_VSYNC_ACTIVE_HIGH | SDVO_HSYNC_ACTIVE_HIGH; - if (!HAS_PCH_SPLIT(dev) && intel_sdvo->is_hdmi) - sdvox |= intel_sdvo->color_range; + if (!HAS_PCH_SPLIT(dev) && crtc->config.limited_color_range) + sdvox |= HDMI_COLOR_RANGE_16_235; if (INTEL_INFO(dev)->gen < 5) sdvox |= SDVO_BORDER_ENABLE; } else { @@ -1349,6 +1350,8 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, u8 val; bool ret; + sdvox = I915_READ(intel_sdvo->sdvo_reg); + ret = intel_sdvo_get_input_timing(intel_sdvo, &dtd); if (!ret) { /* Some sdvo encoders are not spec compliant and don't @@ -1377,7 +1380,6 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, * other platfroms. */ if (IS_I915G(dev) || IS_I915GM(dev)) { - sdvox = I915_READ(intel_sdvo->sdvo_reg); pipe_config->pixel_multiplier = ((sdvox & SDVO_PORT_MULTIPLY_MASK) >> SDVO_PORT_MULTIPLY_SHIFT) + 1; @@ -1406,6 +1408,15 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder, } } + if (sdvox & HDMI_COLOR_RANGE_16_235) + pipe_config->limited_color_range = true; + + if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ENCODE, + &val, 1)) { + if (val == SDVO_ENCODE_HDMI) + pipe_config->has_hdmi_sink = true; + } + WARN(encoder_pixel_multiplier != pipe_config->pixel_multiplier, "SDVO pixel multiplier mismatch, port: %i, encoder: %i\n", pipe_config->pixel_multiplier, encoder_pixel_multiplier); diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index b1a5514e695a..01d841ea3140 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -29,12 +29,21 @@ * IOSF sideband, see VLV2_SidebandMsg_HAS.docx and * VLV_VLV2_PUNIT_HAS_0.8.docx */ + +/* Standard MMIO read, non-posted */ +#define SB_MRD_NP 0x00 +/* Standard MMIO write, non-posted */ +#define SB_MWR_NP 0x01 +/* Private register read, double-word addressing, non-posted */ +#define SB_CRRDDA_NP 0x06 +/* Private register write, double-word addressing, non-posted */ +#define SB_CRWRDA_NP 0x07 + static int vlv_sideband_rw(struct drm_i915_private *dev_priv, u32 devfn, u32 port, u32 opcode, u32 addr, u32 *val) { u32 cmd, be = 0xf, bar = 0; - bool is_read = (opcode == PUNIT_OPCODE_REG_READ || - opcode == DPIO_OPCODE_REG_READ); + bool is_read = (opcode == SB_MRD_NP || opcode == SB_CRRDDA_NP); cmd = (devfn << IOSF_DEVFN_SHIFT) | (opcode << IOSF_OPCODE_SHIFT) | (port << IOSF_PORT_SHIFT) | (be << IOSF_BYTE_ENABLES_SHIFT) | @@ -74,7 +83,7 @@ u32 vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr) mutex_lock(&dev_priv->dpio_lock); vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT, - PUNIT_OPCODE_REG_READ, addr, &val); + SB_CRRDDA_NP, addr, &val); mutex_unlock(&dev_priv->dpio_lock); return val; @@ -86,7 +95,7 @@ void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val) mutex_lock(&dev_priv->dpio_lock); vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT, - PUNIT_OPCODE_REG_WRITE, addr, &val); + SB_CRWRDA_NP, addr, &val); mutex_unlock(&dev_priv->dpio_lock); } @@ -95,7 +104,7 @@ u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg) u32 val = 0; vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT, - PUNIT_OPCODE_REG_READ, reg, &val); + SB_CRRDDA_NP, reg, &val); return val; } @@ -103,7 +112,7 @@ u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg) void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) { vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT, - PUNIT_OPCODE_REG_WRITE, reg, &val); + SB_CRWRDA_NP, reg, &val); } u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr) @@ -114,7 +123,7 @@ u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr) mutex_lock(&dev_priv->dpio_lock); vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_NC, - PUNIT_OPCODE_REG_READ, addr, &val); + SB_CRRDDA_NP, addr, &val); mutex_unlock(&dev_priv->dpio_lock); return val; @@ -124,56 +133,56 @@ 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); + SB_CRRDDA_NP, 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); + SB_CRWRDA_NP, 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); + SB_CRRDDA_NP, 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); + SB_CRWRDA_NP, 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); + SB_CRRDDA_NP, 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); + SB_CRWRDA_NP, 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); + SB_CRRDDA_NP, 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); + SB_CRWRDA_NP, reg, &val); } u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg) @@ -181,7 +190,7 @@ u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg) u32 val = 0; vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)), - DPIO_OPCODE_REG_READ, reg, &val); + SB_MRD_NP, reg, &val); /* * FIXME: There might be some registers where all 1's is a valid value, @@ -196,7 +205,7 @@ u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg) void vlv_dpio_write(struct drm_i915_private *dev_priv, enum pipe pipe, int reg, u32 val) { vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)), - DPIO_OPCODE_REG_WRITE, reg, &val); + SB_MWR_NP, reg, &val); } /* SBI access */ @@ -261,13 +270,13 @@ void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value, u32 vlv_flisdsi_read(struct drm_i915_private *dev_priv, u32 reg) { u32 val = 0; - vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, - DPIO_OPCODE_REG_READ, reg, &val); + vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRRDDA_NP, + reg, &val); return val; } void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val) { - vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, - DPIO_OPCODE_REG_WRITE, reg, &val); + vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRWRDA_NP, + reg, &val); } diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index 213cd58f0412..d6acd6bd0bf0 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -696,10 +696,7 @@ intel_post_enable_primary(struct drm_crtc *crtc) * when going from primary only to sprite only and vice * versa. */ - if (intel_crtc->config.ips_enabled) { - intel_wait_for_vblank(dev, intel_crtc->pipe); - hsw_enable_ips(intel_crtc); - } + hsw_enable_ips(intel_crtc); mutex_lock(&dev->struct_mutex); intel_update_fbc(dev); @@ -1021,6 +1018,9 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, intel_crtc->primary_enabled = primary_enabled; + if (primary_was_enabled != primary_enabled) + intel_crtc_wait_for_pending_flips(crtc); + if (primary_was_enabled && !primary_enabled) intel_pre_disable_primary(crtc); diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 76dc185793ce..9cd99d9676fd 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -921,7 +921,7 @@ int i915_get_reset_stats_ioctl(struct drm_device *dev, struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_reset_stats *args = data; struct i915_ctx_hang_stats *hs; - struct i915_hw_context *ctx; + struct intel_context *ctx; int ret; if (args->flags || args->pad) @@ -976,7 +976,6 @@ static int i965_do_reset(struct drm_device *dev) if (ret) return ret; - /* We can't reset render&media without also resetting display ... */ pci_write_config_byte(dev->pdev, I965_GDRST, GRDOM_MEDIA | GRDOM_RESET_ENABLE); @@ -989,26 +988,58 @@ static int i965_do_reset(struct drm_device *dev) return 0; } +static int g4x_do_reset(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + int ret; + + pci_write_config_byte(dev->pdev, I965_GDRST, + GRDOM_RENDER | GRDOM_RESET_ENABLE); + ret = wait_for(i965_reset_complete(dev), 500); + if (ret) + return ret; + + /* WaVcpClkGateDisableForMediaReset:ctg,elk */ + I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) | VCP_UNIT_CLOCK_GATE_DISABLE); + POSTING_READ(VDECCLK_GATE_D); + + pci_write_config_byte(dev->pdev, I965_GDRST, + GRDOM_MEDIA | GRDOM_RESET_ENABLE); + ret = wait_for(i965_reset_complete(dev), 500); + if (ret) + return ret; + + /* WaVcpClkGateDisableForMediaReset:ctg,elk */ + I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) & ~VCP_UNIT_CLOCK_GATE_DISABLE); + POSTING_READ(VDECCLK_GATE_D); + + pci_write_config_byte(dev->pdev, I965_GDRST, 0); + + return 0; +} + static int ironlake_do_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - u32 gdrst; int ret; - gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR); - gdrst &= ~GRDOM_MASK; I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, - gdrst | GRDOM_RENDER | GRDOM_RESET_ENABLE); - ret = wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500); + ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE); + ret = wait_for((I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & + ILK_GRDOM_RESET_ENABLE) == 0, 500); if (ret) return ret; - /* We can't reset render&media without also resetting display ... */ - gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR); - gdrst &= ~GRDOM_MASK; I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, - gdrst | GRDOM_MEDIA | GRDOM_RESET_ENABLE); - return wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500); + ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE); + ret = wait_for((I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & + ILK_GRDOM_RESET_ENABLE) == 0, 500); + if (ret) + return ret; + + I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, 0); + + return 0; } static int gen6_do_reset(struct drm_device *dev) @@ -1039,7 +1070,11 @@ int intel_gpu_reset(struct drm_device *dev) case 7: case 6: return gen6_do_reset(dev); case 5: return ironlake_do_reset(dev); - case 4: return i965_do_reset(dev); + case 4: + if (IS_G4X(dev)) + return g4x_do_reset(dev); + else + return i965_do_reset(dev); default: return -ENODEV; } } diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 12f10bc2395f..76ccaabd0418 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -1024,14 +1024,17 @@ struct drm_pending_vblank_event { }; struct drm_vblank_crtc { + struct drm_device *dev; /* pointer to the drm_device */ wait_queue_head_t queue; /**< VBLANK wait queue */ struct timeval time[DRM_VBLANKTIME_RBSIZE]; /**< timestamp of current count */ + struct timer_list disable_timer; /* delayed disable timer */ atomic_t count; /**< number of VBLANK interrupts */ atomic_t refcount; /* number of users of vblank interruptsper crtc */ u32 last; /* protected by dev->vbl_lock, used */ /* for wraparound handling */ u32 last_wait; /* Last vblank seqno waited per CRTC */ unsigned int inmodeset; /* Display driver is setting mode */ + int crtc; /* crtc index */ bool enabled; /* so we don't call enable more than once per disable */ }; @@ -1119,7 +1122,6 @@ struct drm_device { spinlock_t vblank_time_lock; /**< Protects vblank count and time updates during vblank enable/disable */ spinlock_t vbl_lock; - struct timer_list vblank_disable_timer; u32 max_vblank_count; /**< size of vblank counter register */ @@ -1357,8 +1359,14 @@ extern void drm_send_vblank_event(struct drm_device *dev, int crtc, extern bool drm_handle_vblank(struct drm_device *dev, int crtc); extern int drm_vblank_get(struct drm_device *dev, int crtc); extern void drm_vblank_put(struct drm_device *dev, int crtc); +extern int drm_crtc_vblank_get(struct drm_crtc *crtc); +extern void drm_crtc_vblank_put(struct drm_crtc *crtc); extern void drm_vblank_off(struct drm_device *dev, int crtc); +extern void drm_vblank_on(struct drm_device *dev, int crtc); +extern void drm_crtc_vblank_off(struct drm_crtc *crtc); +extern void drm_crtc_vblank_on(struct drm_crtc *crtc); extern void drm_vblank_cleanup(struct drm_device *dev); + extern u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc, struct timeval *tvblank, unsigned flags); extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev, diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h index 24f3cad045db..d18f31a77987 100644 --- a/include/drm/i915_pciids.h +++ b/include/drm/i915_pciids.h @@ -245,4 +245,10 @@ INTEL_BDW_GT12D_IDS(info), \ INTEL_BDW_GT3D_IDS(info) +#define INTEL_CHV_IDS(info) \ + INTEL_VGA_DEVICE(0x22b0, info), \ + INTEL_VGA_DEVICE(0x22b1, info), \ + INTEL_VGA_DEVICE(0x22b2, info), \ + INTEL_VGA_DEVICE(0x22b3, info) + #endif /* _I915_PCIIDS_H */ diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 8a3e4ef00c3d..ff57f07c3249 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -223,6 +223,7 @@ typedef struct _drm_i915_sarea { #define DRM_I915_GEM_GET_CACHING 0x30 #define DRM_I915_REG_READ 0x31 #define DRM_I915_GET_RESET_STATS 0x32 +#define DRM_I915_GEM_USERPTR 0x33 #define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t) #define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH) @@ -273,6 +274,7 @@ typedef struct _drm_i915_sarea { #define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy) #define DRM_IOCTL_I915_REG_READ DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read) #define DRM_IOCTL_I915_GET_RESET_STATS DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats) +#define DRM_IOCTL_I915_GEM_USERPTR DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr) /* Allow drivers to submit batchbuffers directly to hardware, relying * on the security mechanisms provided by hardware. @@ -1050,4 +1052,18 @@ struct drm_i915_reset_stats { __u32 pad; }; +struct drm_i915_gem_userptr { + __u64 user_ptr; + __u64 user_size; + __u32 flags; +#define I915_USERPTR_READ_ONLY 0x1 +#define I915_USERPTR_UNSYNCHRONIZED 0x80000000 + /** + * Returned handle for the object. + * + * Object handles are nonzero. + */ + __u32 handle; +}; + #endif /* _UAPI_I915_DRM_H_ */ |