OpenCloudOS-Kernel/drivers/gpu/drm/drm_crtc_helper.c

1032 lines
31 KiB
C
Raw Normal View History

/*
* Copyright (c) 2006-2008 Intel Corporation
* Copyright (c) 2007 Dave Airlie <airlied@linux.ie>
*
* DRM core CRTC related functions
*
* Permission to use, copy, modify, distribute, and sell this software and its
* documentation for any purpose is hereby granted without fee, provided that
* the above copyright notice appear in all copies and that both that copyright
* notice and this permission notice appear in supporting documentation, and
* that the name of the copyright holders not be used in advertising or
* publicity pertaining to distribution of the software without specific,
* written prior permission. The copyright holders make no representations
* about the suitability of this software for any purpose. It is provided "as
* is" without express or implied warranty.
*
* THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
* INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
* EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR
* CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
* DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
* TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
* OF THIS SOFTWARE.
*
* Authors:
* Keith Packard
* Eric Anholt <eric@anholt.net>
* Dave Airlie <airlied@linux.ie>
* Jesse Barnes <jesse.barnes@intel.com>
*/
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/moduleparam.h>
#include <drm/drmP.h>
drm/atomic: Refcounting for plane_state->fb So my original plan was that the drm core refcounts framebuffers like with the legacy ioctls. But that doesn't work for a bunch of reasons: - State objects might live longer than until the next fb change happens for a plane. For example delayed cleanup work only happens _after_ the pageflip ioctl has completed. So this definitely doesn't work without the plane state holding its own references. - The other issue is transition from legacy to atomic implementations, where the driver works under a mix of both worlds. Which means legacy paths might not properly update the ->fb pointer under plane->state->fb. Which is a bit a problem when then someone comes around and _does_ try to clean it up when it's long gone. The second issue is just a bit a transition bug, since drivers should update plane->state->fb in all the paths that aren't converted yet. But a bit more robustness for the transition can't hurt - we pull similar tricks with cleaning up the old fb in the transitional helpers already. The pattern for drivers that transition is if (plane->state) drm_atomic_set_fb_for_plane(plane->state, plane->fb); inserted after the fb update has logically completed at the end of ->set_config (or ->set_base/mode_set if using the crtc helpers), ->page_flip, ->update_plane or any other entry point which updates plane->fb. v2: Update kerneldoc - copypasta fail. v3: Fix spelling in the commit message (Sean). Reviewed-by: Sean Paul <seanpaul@chromium.org> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
2014-11-05 05:57:27 +08:00
#include <drm/drm_atomic.h>
#include <drm/drm_crtc.h>
#include <drm/drm_fourcc.h>
#include <drm/drm_crtc_helper.h>
#include <drm/drm_fb_helper.h>
#include <drm/drm_plane_helper.h>
drm/atomic: Refcounting for plane_state->fb So my original plan was that the drm core refcounts framebuffers like with the legacy ioctls. But that doesn't work for a bunch of reasons: - State objects might live longer than until the next fb change happens for a plane. For example delayed cleanup work only happens _after_ the pageflip ioctl has completed. So this definitely doesn't work without the plane state holding its own references. - The other issue is transition from legacy to atomic implementations, where the driver works under a mix of both worlds. Which means legacy paths might not properly update the ->fb pointer under plane->state->fb. Which is a bit a problem when then someone comes around and _does_ try to clean it up when it's long gone. The second issue is just a bit a transition bug, since drivers should update plane->state->fb in all the paths that aren't converted yet. But a bit more robustness for the transition can't hurt - we pull similar tricks with cleaning up the old fb in the transitional helpers already. The pattern for drivers that transition is if (plane->state) drm_atomic_set_fb_for_plane(plane->state, plane->fb); inserted after the fb update has logically completed at the end of ->set_config (or ->set_base/mode_set if using the crtc helpers), ->page_flip, ->update_plane or any other entry point which updates plane->fb. v2: Update kerneldoc - copypasta fail. v3: Fix spelling in the commit message (Sean). Reviewed-by: Sean Paul <seanpaul@chromium.org> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
2014-11-05 05:57:27 +08:00
#include <drm/drm_atomic_helper.h>
#include <drm/drm_edid.h>
/**
* DOC: overview
*
* The CRTC modeset helper library provides a default set_config implementation
* in drm_crtc_helper_set_config(). Plus a few other convenience functions using
* the same callbacks which drivers can use to e.g. restore the modeset
* configuration on resume with drm_helper_resume_force_mode().
*
* The driver callbacks are mostly compatible with the atomic modeset helpers,
* except for the handling of the primary plane: Atomic helpers require that the
* primary plane is implemented as a real standalone plane and not directly tied
* to the CRTC state. For easier transition this library provides functions to
* implement the old semantics required by the CRTC helpers using the new plane
* and atomic helper callbacks.
*
* Drivers are strongly urged to convert to the atomic helpers (by way of first
* converting to the plane helpers). New drivers must not use these functions
* but need to implement the atomic interface instead, potentially using the
* atomic helpers for that.
*/
MODULE_AUTHOR("David Airlie, Jesse Barnes");
MODULE_DESCRIPTION("DRM KMS helper");
MODULE_LICENSE("GPL and additional rights");
/**
* drm_helper_move_panel_connectors_to_head() - move panels to the front in the
* connector list
* @dev: drm device to operate on
*
* Some userspace presumes that the first connected connector is the main
* display, where it's supposed to display e.g. the login screen. For
* laptops, this should be the main panel. Use this function to sort all
* (eDP/LVDS) panels to the front of the connector list, instead of
* painstakingly trying to initialize them in the right order.
*/
void drm_helper_move_panel_connectors_to_head(struct drm_device *dev)
{
struct drm_connector *connector, *tmp;
struct list_head panel_list;
INIT_LIST_HEAD(&panel_list);
list_for_each_entry_safe(connector, tmp,
&dev->mode_config.connector_list, head) {
if (connector->connector_type == DRM_MODE_CONNECTOR_LVDS ||
connector->connector_type == DRM_MODE_CONNECTOR_eDP)
list_move_tail(&connector->head, &panel_list);
}
list_splice(&panel_list, &dev->mode_config.connector_list);
}
EXPORT_SYMBOL(drm_helper_move_panel_connectors_to_head);
/**
* drm_helper_encoder_in_use - check if a given encoder is in use
* @encoder: encoder to check
*
* Checks whether @encoder is with the current mode setting output configuration
* in use by any connector. This doesn't mean that it is actually enabled since
* the DPMS state is tracked separately.
*
* Returns:
* True if @encoder is used, false otherwise.
*/
bool drm_helper_encoder_in_use(struct drm_encoder *encoder)
{
struct drm_connector *connector;
struct drm_device *dev = encoder->dev;
/*
* We can expect this mutex to be locked if we are not panicking.
* Locking is currently fubar in the panic handler.
*/
if (!oops_in_progress) {
WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
}
list_for_each_entry(connector, &dev->mode_config.connector_list, head)
if (connector->encoder == encoder)
return true;
return false;
}
EXPORT_SYMBOL(drm_helper_encoder_in_use);
/**
* drm_helper_crtc_in_use - check if a given CRTC is in a mode_config
* @crtc: CRTC to check
*
* Checks whether @crtc is with the current mode setting output configuration
* in use by any connector. This doesn't mean that it is actually enabled since
* the DPMS state is tracked separately.
*
* Returns:
* True if @crtc is used, false otherwise.
*/
bool drm_helper_crtc_in_use(struct drm_crtc *crtc)
{
struct drm_encoder *encoder;
struct drm_device *dev = crtc->dev;
/*
* We can expect this mutex to be locked if we are not panicking.
* Locking is currently fubar in the panic handler.
*/
if (!oops_in_progress)
WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head)
if (encoder->crtc == crtc && drm_helper_encoder_in_use(encoder))
return true;
return false;
}
EXPORT_SYMBOL(drm_helper_crtc_in_use);
static void
drm_encoder_disable(struct drm_encoder *encoder)
{
const struct drm_encoder_helper_funcs *encoder_funcs = encoder->helper_private;
if (encoder->bridge)
encoder->bridge->funcs->disable(encoder->bridge);
if (encoder_funcs->disable)
(*encoder_funcs->disable)(encoder);
else
(*encoder_funcs->dpms)(encoder, DRM_MODE_DPMS_OFF);
if (encoder->bridge)
encoder->bridge->funcs->post_disable(encoder->bridge);
}
drm/crtc-helper: fix locking for drm_helper_disable_unused_functions We have two calling contexts for thise function: - In the crtc helper code itself as part of the ->set_config implementation. In this calling context all modeset locks are already held, as they should. - In drivers not implementing fastboot before the fbdev/fbcon setup and initialization. This has been added for all drivers in commit 76a39dbfb2d1bc45219839e5a95d4ceaf6ca114f Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Sun Jan 20 23:12:54 2013 +0100 drm/fb-helper: don't disable everything in initial_config In this calling context we do not hold any modeset locks since the immediately following call to initialize the fbev emulation grabs all these locks themselves. - There are two exceptions to the above rule: shmob doesn't have fbdev emulation support. I've manually checked the callchain up to the driver load function and no kms locks are held. The right fix therefore is to split this helper into an internal and external version and add the required locking to the function exported to drivers. This remedies locking inconsistencies exposed by me adding locking WARNs as part of the recent kerneldoc abi polishing done in commit 62ff94a5492175759546f8bc61383189d6b49122 Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 22:18:47 2014 +0100 drm/crtc-helper: remove LOCKING from kerneldoc and commit 63951385052f7974155fa38f962f0f4e9847f90a Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 15:14:15 2014 +0100 drm/doc: Repleace LOCKING kerneldoc sections in drm_modes.c v2: It helps when I actually git add the entire thing. Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Tested-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2014-03-20 21:26:34 +08:00
static void __drm_helper_disable_unused_functions(struct drm_device *dev)
{
struct drm_encoder *encoder;
struct drm_crtc *crtc;
drm_warn_on_modeset_not_all_locked(dev);
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
if (!drm_helper_encoder_in_use(encoder)) {
drm_encoder_disable(encoder);
/* disconnect encoder from any connector */
encoder->crtc = NULL;
}
}
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
crtc->enabled = drm_helper_crtc_in_use(crtc);
if (!crtc->enabled) {
if (crtc_funcs->disable)
(*crtc_funcs->disable)(crtc);
else
(*crtc_funcs->dpms)(crtc, DRM_MODE_DPMS_OFF);
crtc->primary->fb = NULL;
}
}
}
drm/crtc-helper: fix locking for drm_helper_disable_unused_functions We have two calling contexts for thise function: - In the crtc helper code itself as part of the ->set_config implementation. In this calling context all modeset locks are already held, as they should. - In drivers not implementing fastboot before the fbdev/fbcon setup and initialization. This has been added for all drivers in commit 76a39dbfb2d1bc45219839e5a95d4ceaf6ca114f Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Sun Jan 20 23:12:54 2013 +0100 drm/fb-helper: don't disable everything in initial_config In this calling context we do not hold any modeset locks since the immediately following call to initialize the fbev emulation grabs all these locks themselves. - There are two exceptions to the above rule: shmob doesn't have fbdev emulation support. I've manually checked the callchain up to the driver load function and no kms locks are held. The right fix therefore is to split this helper into an internal and external version and add the required locking to the function exported to drivers. This remedies locking inconsistencies exposed by me adding locking WARNs as part of the recent kerneldoc abi polishing done in commit 62ff94a5492175759546f8bc61383189d6b49122 Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 22:18:47 2014 +0100 drm/crtc-helper: remove LOCKING from kerneldoc and commit 63951385052f7974155fa38f962f0f4e9847f90a Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 15:14:15 2014 +0100 drm/doc: Repleace LOCKING kerneldoc sections in drm_modes.c v2: It helps when I actually git add the entire thing. Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Tested-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2014-03-20 21:26:34 +08:00
/**
* drm_helper_disable_unused_functions - disable unused objects
* @dev: DRM device
*
* This function walks through the entire mode setting configuration of @dev. It
* will remove any crtc links of unused encoders and encoder links of
* disconnected connectors. Then it will disable all unused encoders and crtcs
* either by calling their disable callback if available or by calling their
* dpms callback with DRM_MODE_DPMS_OFF.
*/
void drm_helper_disable_unused_functions(struct drm_device *dev)
{
drm_modeset_lock_all(dev);
__drm_helper_disable_unused_functions(dev);
drm_modeset_unlock_all(dev);
}
EXPORT_SYMBOL(drm_helper_disable_unused_functions);
/*
* Check the CRTC we're going to map each output to vs. its current
* CRTC. If they don't match, we have to disable the output and the CRTC
* since the driver will have to re-route things.
*/
static void
drm_crtc_prepare_encoders(struct drm_device *dev)
{
const struct drm_encoder_helper_funcs *encoder_funcs;
struct drm_encoder *encoder;
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
encoder_funcs = encoder->helper_private;
/* Disable unused encoders */
if (encoder->crtc == NULL)
drm_encoder_disable(encoder);
/* Disable encoders whose CRTC is about to change */
if (encoder_funcs->get_crtc &&
encoder->crtc != (*encoder_funcs->get_crtc)(encoder))
drm_encoder_disable(encoder);
}
}
/**
* drm_crtc_helper_set_mode - internal helper to set a mode
* @crtc: CRTC to program
* @mode: mode to use
* @x: horizontal offset into the surface
* @y: vertical offset into the surface
* @old_fb: old framebuffer, for cleanup
*
* Try to set @mode on @crtc. Give @crtc and its associated connectors a chance
* to fixup or reject the mode prior to trying to set it. This is an internal
* helper that drivers could e.g. use to update properties that require the
* entire output pipe to be disabled and re-enabled in a new configuration. For
* example for changing whether audio is enabled on a hdmi link or for changing
* panel fitter or dither attributes. It is also called by the
* drm_crtc_helper_set_config() helper function to drive the mode setting
* sequence.
*
* Returns:
* True if the mode was set successfully, false otherwise.
*/
bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
struct drm_display_mode *mode,
int x, int y,
struct drm_framebuffer *old_fb)
{
struct drm_device *dev = crtc->dev;
struct drm_display_mode *adjusted_mode, saved_mode, saved_hwmode;
const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
const struct drm_encoder_helper_funcs *encoder_funcs;
int saved_x, saved_y;
bool saved_enabled;
struct drm_encoder *encoder;
bool ret = true;
drm_warn_on_modeset_not_all_locked(dev);
saved_enabled = crtc->enabled;
crtc->enabled = drm_helper_crtc_in_use(crtc);
if (!crtc->enabled)
return true;
adjusted_mode = drm_mode_duplicate(dev, mode);
if (!adjusted_mode) {
crtc->enabled = saved_enabled;
return false;
}
saved_mode = crtc->mode;
saved_hwmode = crtc->hwmode;
saved_x = crtc->x;
saved_y = crtc->y;
/* Update crtc values up front so the driver can rely on them for mode
* setting.
*/
crtc->mode = *mode;
crtc->x = x;
crtc->y = y;
/* Pass our mode to the connectors and the CRTC to give them a chance to
* adjust it according to limitations or connector properties, and also
* a chance to reject the mode entirely.
*/
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
if (encoder->crtc != crtc)
continue;
if (encoder->bridge && encoder->bridge->funcs->mode_fixup) {
ret = encoder->bridge->funcs->mode_fixup(
encoder->bridge, mode, adjusted_mode);
if (!ret) {
DRM_DEBUG_KMS("Bridge fixup failed\n");
goto done;
}
}
encoder_funcs = encoder->helper_private;
if (!(ret = encoder_funcs->mode_fixup(encoder, mode,
adjusted_mode))) {
DRM_DEBUG_KMS("Encoder fixup failed\n");
goto done;
}
}
if (!(ret = crtc_funcs->mode_fixup(crtc, mode, adjusted_mode))) {
DRM_DEBUG_KMS("CRTC fixup failed\n");
goto done;
}
DRM_DEBUG_KMS("[CRTC:%d]\n", crtc->base.id);
crtc->hwmode = *adjusted_mode;
/* Prepare the encoders and CRTCs before setting the mode. */
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
if (encoder->crtc != crtc)
continue;
if (encoder->bridge)
encoder->bridge->funcs->disable(encoder->bridge);
encoder_funcs = encoder->helper_private;
/* Disable the encoders as the first thing we do. */
encoder_funcs->prepare(encoder);
if (encoder->bridge)
encoder->bridge->funcs->post_disable(encoder->bridge);
}
drm_crtc_prepare_encoders(dev);
crtc_funcs->prepare(crtc);
/* Set up the DPLL and any encoders state that needs to adjust or depend
* on the DPLL.
*/
ret = !crtc_funcs->mode_set(crtc, mode, adjusted_mode, x, y, old_fb);
if (!ret)
goto done;
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
if (encoder->crtc != crtc)
continue;
DRM_DEBUG_KMS("[ENCODER:%d:%s] set [MODE:%d:%s]\n",
encoder->base.id, encoder->name,
mode->base.id, mode->name);
encoder_funcs = encoder->helper_private;
encoder_funcs->mode_set(encoder, mode, adjusted_mode);
if (encoder->bridge && encoder->bridge->funcs->mode_set)
encoder->bridge->funcs->mode_set(encoder->bridge, mode,
adjusted_mode);
}
/* Now enable the clocks, plane, pipe, and connectors that we set up. */
crtc_funcs->commit(crtc);
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
if (encoder->crtc != crtc)
continue;
if (encoder->bridge)
encoder->bridge->funcs->pre_enable(encoder->bridge);
encoder_funcs = encoder->helper_private;
encoder_funcs->commit(encoder);
if (encoder->bridge)
encoder->bridge->funcs->enable(encoder->bridge);
}
drm/vblank: Add support for precise vblank timestamping. The DRI2 swap & sync implementation needs precise vblank counts and precise timestamps corresponding to those vblank counts. For conformance to the OpenML OML_sync_control extension specification the DRM timestamp associated with a vblank count should correspond to the start of video scanout of the first scanline of the video frame following the vblank interval for that vblank count. Therefore we need to carry around precise timestamps for vblanks. Currently the DRM and KMS drivers generate timestamps ad-hoc via do_gettimeofday() in some places. The resulting timestamps are sometimes not very precise due to interrupt handling delays, they don't conform to OML_sync_control and some are wrong, as they aren't taken synchronized to the vblank. This patch implements support inside the drm core for precise and robust timestamping. It consists of the following interrelated pieces. 1. Vblank timestamp caching: A per-crtc ringbuffer stores the most recent vblank timestamps corresponding to vblank counts. The ringbuffer can be read out lock-free via the accessor function: struct timeval timestamp; vblankcount = drm_vblank_count_and_time(dev, crtcid, &timestamp). The function returns the current vblank count and the corresponding timestamp for start of video scanout following the vblank interval. It can be used anywhere between enclosing drm_vblank_get(dev, crtcid) and drm_vblank_put(dev,crtcid) statements. It is used inside the drmWaitVblank ioctl and in the vblank event queueing and handling. It should be used by kms drivers for timestamping of bufferswap completion. The timestamp ringbuffer is reinitialized each time vblank irq's get reenabled in drm_vblank_get()/ drm_update_vblank_count(). It is invalidated when vblank irq's get disabled. The ringbuffer is updated inside drm_handle_vblank() at each vblank irq. 2. Calculation of precise vblank timestamps: drm_get_last_vbltimestamp() is used to compute the timestamp for the end of the most recent vblank (if inside active scanout), or the expected end of the current vblank interval (if called inside a vblank interval). The function calls into a new optional kms driver entry point dev->driver->get_vblank_timestamp() which is supposed to provide the precise timestamp. If a kms driver doesn't implement the entry point or if the call fails, a simple do_gettimeofday() timestamp is returned as crude approximation of the true vblank time. A new drm module parameter drm.timestamp_precision_usec allows to disable high precision timestamps (if set to zero) or to specify the maximum acceptable error in the timestamps in microseconds. Kms drivers could implement their get_vblank_timestamp() function in a gpu specific way, as long as returned timestamps conform to OML_sync_control, e.g., by use of gpu specific hardware timestamps. Optionally, kms drivers can simply wrap and use the new utility function drm_calc_vbltimestamp_from_scanoutpos(). This function calls a new optional kms driver function dev->driver->get_scanout_position() which returns the current horizontal and vertical video scanout position of the crtc. The scanout position together with the drm_display_timing of the current video mode is used to calculate elapsed time relative to start of active scanout for the current video frame. This elapsed time is subtracted from the current do_gettimeofday() time to get the timestamp corresponding to start of video scanout. Currently non-interlaced, non-doublescan video modes, with or without panel scaling are handled correctly. Interlaced/ doublescan modes are tbd in a future patch. 3. Filtering of redundant vblank irq's and removal of some race-conditions in the vblank irq enable/disable path: Some gpu's (e.g., Radeon R500/R600) send spurious vblank irq's outside the vblank if vblank irq's get reenabled. These get detected by use of the vblank timestamps and filtered out to avoid miscounting of vblanks. Some race-conditions between the vblank irq enable/disable functions, the vblank irq handler and the gpu itself (updating its hardware vblank counter in the "wrong" moment) are fixed inside vblank_disable_and_save() and drm_update_vblank_count() by use of the vblank timestamps and a new spinlock dev->vblank_time_lock. The time until vblank irq disable is now configurable via a new drm module parameter drm.vblankoffdelay to allow experimentation with timeouts that are much shorter than the current 5 seconds and should allow longer vblank off periods for better power savings. Followup patches will use these new functions to implement precise timestamping for the intel and radeon kms drivers. Signed-off-by: Mario Kleiner <mario.kleiner@tuebingen.mpg.de> Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-10-23 10:20:23 +08:00
/* Calculate and store various constants which
* are later needed by vblank and swap-completion
* timestamping. They are derived from true hwmode.
*/
drm_calc_timestamping_constants(crtc, &crtc->hwmode);
drm/vblank: Add support for precise vblank timestamping. The DRI2 swap & sync implementation needs precise vblank counts and precise timestamps corresponding to those vblank counts. For conformance to the OpenML OML_sync_control extension specification the DRM timestamp associated with a vblank count should correspond to the start of video scanout of the first scanline of the video frame following the vblank interval for that vblank count. Therefore we need to carry around precise timestamps for vblanks. Currently the DRM and KMS drivers generate timestamps ad-hoc via do_gettimeofday() in some places. The resulting timestamps are sometimes not very precise due to interrupt handling delays, they don't conform to OML_sync_control and some are wrong, as they aren't taken synchronized to the vblank. This patch implements support inside the drm core for precise and robust timestamping. It consists of the following interrelated pieces. 1. Vblank timestamp caching: A per-crtc ringbuffer stores the most recent vblank timestamps corresponding to vblank counts. The ringbuffer can be read out lock-free via the accessor function: struct timeval timestamp; vblankcount = drm_vblank_count_and_time(dev, crtcid, &timestamp). The function returns the current vblank count and the corresponding timestamp for start of video scanout following the vblank interval. It can be used anywhere between enclosing drm_vblank_get(dev, crtcid) and drm_vblank_put(dev,crtcid) statements. It is used inside the drmWaitVblank ioctl and in the vblank event queueing and handling. It should be used by kms drivers for timestamping of bufferswap completion. The timestamp ringbuffer is reinitialized each time vblank irq's get reenabled in drm_vblank_get()/ drm_update_vblank_count(). It is invalidated when vblank irq's get disabled. The ringbuffer is updated inside drm_handle_vblank() at each vblank irq. 2. Calculation of precise vblank timestamps: drm_get_last_vbltimestamp() is used to compute the timestamp for the end of the most recent vblank (if inside active scanout), or the expected end of the current vblank interval (if called inside a vblank interval). The function calls into a new optional kms driver entry point dev->driver->get_vblank_timestamp() which is supposed to provide the precise timestamp. If a kms driver doesn't implement the entry point or if the call fails, a simple do_gettimeofday() timestamp is returned as crude approximation of the true vblank time. A new drm module parameter drm.timestamp_precision_usec allows to disable high precision timestamps (if set to zero) or to specify the maximum acceptable error in the timestamps in microseconds. Kms drivers could implement their get_vblank_timestamp() function in a gpu specific way, as long as returned timestamps conform to OML_sync_control, e.g., by use of gpu specific hardware timestamps. Optionally, kms drivers can simply wrap and use the new utility function drm_calc_vbltimestamp_from_scanoutpos(). This function calls a new optional kms driver function dev->driver->get_scanout_position() which returns the current horizontal and vertical video scanout position of the crtc. The scanout position together with the drm_display_timing of the current video mode is used to calculate elapsed time relative to start of active scanout for the current video frame. This elapsed time is subtracted from the current do_gettimeofday() time to get the timestamp corresponding to start of video scanout. Currently non-interlaced, non-doublescan video modes, with or without panel scaling are handled correctly. Interlaced/ doublescan modes are tbd in a future patch. 3. Filtering of redundant vblank irq's and removal of some race-conditions in the vblank irq enable/disable path: Some gpu's (e.g., Radeon R500/R600) send spurious vblank irq's outside the vblank if vblank irq's get reenabled. These get detected by use of the vblank timestamps and filtered out to avoid miscounting of vblanks. Some race-conditions between the vblank irq enable/disable functions, the vblank irq handler and the gpu itself (updating its hardware vblank counter in the "wrong" moment) are fixed inside vblank_disable_and_save() and drm_update_vblank_count() by use of the vblank timestamps and a new spinlock dev->vblank_time_lock. The time until vblank irq disable is now configurable via a new drm module parameter drm.vblankoffdelay to allow experimentation with timeouts that are much shorter than the current 5 seconds and should allow longer vblank off periods for better power savings. Followup patches will use these new functions to implement precise timestamping for the intel and radeon kms drivers. Signed-off-by: Mario Kleiner <mario.kleiner@tuebingen.mpg.de> Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-10-23 10:20:23 +08:00
/* FIXME: add subpixel order */
done:
drm_mode_destroy(dev, adjusted_mode);
if (!ret) {
crtc->enabled = saved_enabled;
crtc->mode = saved_mode;
crtc->hwmode = saved_hwmode;
crtc->x = saved_x;
crtc->y = saved_y;
}
return ret;
}
EXPORT_SYMBOL(drm_crtc_helper_set_mode);
static void
drm_crtc_helper_disable(struct drm_crtc *crtc)
{
struct drm_device *dev = crtc->dev;
struct drm_connector *connector;
struct drm_encoder *encoder;
/* Decouple all encoders and their attached connectors from this crtc */
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
if (encoder->crtc != crtc)
continue;
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
if (connector->encoder != encoder)
continue;
connector->encoder = NULL;
/*
* drm_helper_disable_unused_functions() ought to be
* doing this, but since we've decoupled the encoder
* from the connector above, the required connection
* between them is henceforth no longer available.
*/
connector->dpms = DRM_MODE_DPMS_OFF;
}
}
drm/crtc-helper: fix locking for drm_helper_disable_unused_functions We have two calling contexts for thise function: - In the crtc helper code itself as part of the ->set_config implementation. In this calling context all modeset locks are already held, as they should. - In drivers not implementing fastboot before the fbdev/fbcon setup and initialization. This has been added for all drivers in commit 76a39dbfb2d1bc45219839e5a95d4ceaf6ca114f Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Sun Jan 20 23:12:54 2013 +0100 drm/fb-helper: don't disable everything in initial_config In this calling context we do not hold any modeset locks since the immediately following call to initialize the fbev emulation grabs all these locks themselves. - There are two exceptions to the above rule: shmob doesn't have fbdev emulation support. I've manually checked the callchain up to the driver load function and no kms locks are held. The right fix therefore is to split this helper into an internal and external version and add the required locking to the function exported to drivers. This remedies locking inconsistencies exposed by me adding locking WARNs as part of the recent kerneldoc abi polishing done in commit 62ff94a5492175759546f8bc61383189d6b49122 Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 22:18:47 2014 +0100 drm/crtc-helper: remove LOCKING from kerneldoc and commit 63951385052f7974155fa38f962f0f4e9847f90a Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 15:14:15 2014 +0100 drm/doc: Repleace LOCKING kerneldoc sections in drm_modes.c v2: It helps when I actually git add the entire thing. Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Tested-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2014-03-20 21:26:34 +08:00
__drm_helper_disable_unused_functions(dev);
}
/**
* drm_crtc_helper_set_config - set a new config from userspace
* @set: mode set configuration
*
* Setup a new configuration, provided by the upper layers (either an ioctl call
* from userspace or internally e.g. from the fbdev support code) in @set, and
* enable it. This is the main helper functions for drivers that implement
* kernel mode setting with the crtc helper functions and the assorted
* ->prepare(), ->modeset() and ->commit() helper callbacks.
*
* Returns:
* Returns 0 on success, negative errno numbers on failure.
*/
int drm_crtc_helper_set_config(struct drm_mode_set *set)
{
struct drm_device *dev;
struct drm_crtc *new_crtc;
struct drm_encoder *save_encoders, *new_encoder, *encoder;
bool mode_changed = false; /* if true do a full mode set */
bool fb_changed = false; /* if true and !mode_changed just do a flip */
struct drm_connector *save_connectors, *connector;
int count = 0, ro, fail = 0;
const struct drm_crtc_helper_funcs *crtc_funcs;
struct drm_mode_set save_set;
int ret;
int i;
DRM_DEBUG_KMS("\n");
BUG_ON(!set);
BUG_ON(!set->crtc);
BUG_ON(!set->crtc->helper_private);
/* Enforce sane interface api - has been abused by the fb helper. */
BUG_ON(!set->mode && set->fb);
BUG_ON(set->fb && set->num_connectors == 0);
crtc_funcs = set->crtc->helper_private;
if (!set->mode)
set->fb = NULL;
if (set->fb) {
DRM_DEBUG_KMS("[CRTC:%d] [FB:%d] #connectors=%d (x y) (%i %i)\n",
set->crtc->base.id, set->fb->base.id,
(int)set->num_connectors, set->x, set->y);
} else {
DRM_DEBUG_KMS("[CRTC:%d] [NOFB]\n", set->crtc->base.id);
drm_crtc_helper_disable(set->crtc);
return 0;
}
dev = set->crtc->dev;
drm_warn_on_modeset_not_all_locked(dev);
/*
* Allocate space for the backup of all (non-pointer) encoder and
* connector data.
*/
save_encoders = kzalloc(dev->mode_config.num_encoder *
sizeof(struct drm_encoder), GFP_KERNEL);
if (!save_encoders)
return -ENOMEM;
save_connectors = kzalloc(dev->mode_config.num_connector *
sizeof(struct drm_connector), GFP_KERNEL);
if (!save_connectors) {
kfree(save_encoders);
return -ENOMEM;
}
/*
* Copy data. Note that driver private data is not affected.
* Should anything bad happen only the expected state is
* restored, not the drivers personal bookkeeping.
*/
count = 0;
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
save_encoders[count++] = *encoder;
}
count = 0;
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
save_connectors[count++] = *connector;
}
save_set.crtc = set->crtc;
save_set.mode = &set->crtc->mode;
save_set.x = set->crtc->x;
save_set.y = set->crtc->y;
save_set.fb = set->crtc->primary->fb;
/* We should be able to check here if the fb has the same properties
* and then just flip_or_move it */
if (set->crtc->primary->fb != set->fb) {
/* If we have no fb then treat it as a full mode set */
if (set->crtc->primary->fb == NULL) {
DRM_DEBUG_KMS("crtc has no fb, full mode set\n");
mode_changed = true;
} else if (set->fb == NULL) {
mode_changed = true;
} else if (set->fb->pixel_format !=
set->crtc->primary->fb->pixel_format) {
mode_changed = true;
} else
fb_changed = true;
}
if (set->x != set->crtc->x || set->y != set->crtc->y)
fb_changed = true;
if (set->mode && !drm_mode_equal(set->mode, &set->crtc->mode)) {
DRM_DEBUG_KMS("modes are different, full mode set\n");
drm_mode_debug_printmodeline(&set->crtc->mode);
drm_mode_debug_printmodeline(set->mode);
mode_changed = true;
}
/* a) traverse passed in connector list and get encoders for them */
count = 0;
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
const struct drm_connector_helper_funcs *connector_funcs =
connector->helper_private;
new_encoder = connector->encoder;
for (ro = 0; ro < set->num_connectors; ro++) {
if (set->connectors[ro] == connector) {
new_encoder = connector_funcs->best_encoder(connector);
/* if we can't get an encoder for a connector
we are setting now - then fail */
if (new_encoder == NULL)
/* don't break so fail path works correct */
fail = 1;
drm/crtc-helper: explicit DPMS on after modeset Atm the crtc helper implementation of set_config has really inconsisten semantics: If just an fb update is good enough, dpms state will be left as-is, but if we do a full modeset we force everything to dpms on. This change has already been applied to the i915 modeset code in commit e3de42b68478a8c95dd27520e9adead2af9477a5 Author: Imre Deak <imre.deak@intel.com> Date: Fri May 3 19:44:07 2013 +0200 drm/i915: force full modeset if the connector is in DPMS OFF mode which according to Greg KH seems to aim for a new record in most Bugzilla: links in a commit message. The history of this dpms forcing is pretty interesting. This patch here is an almost-revert of commit 811aaa55ba21ab37407018cfc01770d6b037d3fb Author: Keith Packard <keithp@keithp.com> Date: Thu Feb 3 16:57:28 2011 -0800 drm: Only set DPMS ON when actually configuring a mode which fixed the bug of trying to dpms on disabled outputs, but introduced the new discrepancy between an fb update only and full modesets. The actual introduction of this goes back to commit bf9dc102e284a5aa78c73fc9d72e11d5ccd8669f Author: Keith Packard <keithp@keithp.com> Date: Fri Nov 26 10:45:58 2010 -0800 drm: Set connector DPMS status to ON in drm_crtc_helper_set_config And if you'd dig around in the i915 driver code there's even more fun around forcing dpms on and losing our heads and temper of the resulting inconsistencies. Especially the DP re-training code had tons of funny stuff in it. v2: So v1 totally blew up on resume on my radeon system here. After much head-scraching I've figured out that the radeon resume functions resumes the console system _before_ it actually restores all the modeset state. And resuming the console systems means that fbdev doeas an immediate ->set_par call. Now up to this patch that ->set_par did absolutely nothing: All the old sw state from pre-suspend was still around (since the modeset reset wasn't done yet), which means that the set_config calls done as a result of the ->set_par where all treated as no-ops (despite that the real hw state was obviously something completely different). Since v1 of this patch just added a bunch of ->dpms calls if the crtc was enabled, those set_config calls suddenly stopped being no-ops. But because the hw state wasn't restored the ->dpms callbacks resulted in decent amounts of hilarity and eventual full hangs. Since I can't review all kms drivers for such tricky ordering constraints v2 opts for a different approach and forces a full modeset if the connector dpms state isnt' DPMS_ON. Since the ->dpms callbacks implemented by the modeset helpers update the connector->dpms property we have the same effect of ensuring that the pipe is ultimately turned on, even if we just end up updating the fb. This is the same approac we ended up using in the intel driver. Note that besides i915.ko only all other drivers eventually call drm_helper_connector_dpms with the exception of vmwgfx, which does not support dmps at all. v3: Dave Airlie merged the broken first version of this patch, so squash in the revert of commit 372835a8527f85b3eff20a18c2c339e827dfd4e4 Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Sat Jun 15 00:13:13 2013 +0200 drm/crtc-helper: explicit DPMS on after modeset Also fix up the spelling fail a bit in the commit message while at it. Cc: Dave Airlie <airlied@redhat.com> Reviewed-by: Alex Deucher <alexdeucher@gmail.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=67043 Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Dave Airlie <airlied@redhat.com>
2013-07-20 00:57:11 +08:00
if (connector->dpms != DRM_MODE_DPMS_ON) {
DRM_DEBUG_KMS("connector dpms not on, full mode switch\n");
mode_changed = true;
}
break;
}
}
if (new_encoder != connector->encoder) {
DRM_DEBUG_KMS("encoder changed, full mode switch\n");
mode_changed = true;
/* If the encoder is reused for another connector, then
* the appropriate crtc will be set later.
*/
if (connector->encoder)
connector->encoder->crtc = NULL;
connector->encoder = new_encoder;
}
}
if (fail) {
ret = -EINVAL;
goto fail;
}
count = 0;
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
if (!connector->encoder)
continue;
if (connector->encoder->crtc == set->crtc)
new_crtc = NULL;
else
new_crtc = connector->encoder->crtc;
for (ro = 0; ro < set->num_connectors; ro++) {
if (set->connectors[ro] == connector)
new_crtc = set->crtc;
}
/* Make sure the new CRTC will work with the encoder */
if (new_crtc &&
!drm_encoder_crtc_ok(connector->encoder, new_crtc)) {
ret = -EINVAL;
goto fail;
}
if (new_crtc != connector->encoder->crtc) {
DRM_DEBUG_KMS("crtc changed, full mode switch\n");
mode_changed = true;
connector->encoder->crtc = new_crtc;
}
if (new_crtc) {
DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [CRTC:%d]\n",
connector->base.id, connector->name,
new_crtc->base.id);
} else {
DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [NOCRTC]\n",
connector->base.id, connector->name);
}
}
/* mode_set_base is not a required function */
if (fb_changed && !crtc_funcs->mode_set_base)
mode_changed = true;
if (mode_changed) {
if (drm_helper_crtc_in_use(set->crtc)) {
DRM_DEBUG_KMS("attempting to set mode from"
" userspace\n");
drm_mode_debug_printmodeline(set->mode);
set->crtc->primary->fb = set->fb;
if (!drm_crtc_helper_set_mode(set->crtc, set->mode,
set->x, set->y,
save_set.fb)) {
DRM_ERROR("failed to set mode on [CRTC:%d]\n",
set->crtc->base.id);
set->crtc->primary->fb = save_set.fb;
ret = -EINVAL;
goto fail;
}
drm/crtc-helper: explicit DPMS on after modeset Atm the crtc helper implementation of set_config has really inconsisten semantics: If just an fb update is good enough, dpms state will be left as-is, but if we do a full modeset we force everything to dpms on. This change has already been applied to the i915 modeset code in commit e3de42b68478a8c95dd27520e9adead2af9477a5 Author: Imre Deak <imre.deak@intel.com> Date: Fri May 3 19:44:07 2013 +0200 drm/i915: force full modeset if the connector is in DPMS OFF mode which according to Greg KH seems to aim for a new record in most Bugzilla: links in a commit message. The history of this dpms forcing is pretty interesting. This patch here is an almost-revert of commit 811aaa55ba21ab37407018cfc01770d6b037d3fb Author: Keith Packard <keithp@keithp.com> Date: Thu Feb 3 16:57:28 2011 -0800 drm: Only set DPMS ON when actually configuring a mode which fixed the bug of trying to dpms on disabled outputs, but introduced the new discrepancy between an fb update only and full modesets. The actual introduction of this goes back to commit bf9dc102e284a5aa78c73fc9d72e11d5ccd8669f Author: Keith Packard <keithp@keithp.com> Date: Fri Nov 26 10:45:58 2010 -0800 drm: Set connector DPMS status to ON in drm_crtc_helper_set_config And if you'd dig around in the i915 driver code there's even more fun around forcing dpms on and losing our heads and temper of the resulting inconsistencies. Especially the DP re-training code had tons of funny stuff in it. v2: So v1 totally blew up on resume on my radeon system here. After much head-scraching I've figured out that the radeon resume functions resumes the console system _before_ it actually restores all the modeset state. And resuming the console systems means that fbdev doeas an immediate ->set_par call. Now up to this patch that ->set_par did absolutely nothing: All the old sw state from pre-suspend was still around (since the modeset reset wasn't done yet), which means that the set_config calls done as a result of the ->set_par where all treated as no-ops (despite that the real hw state was obviously something completely different). Since v1 of this patch just added a bunch of ->dpms calls if the crtc was enabled, those set_config calls suddenly stopped being no-ops. But because the hw state wasn't restored the ->dpms callbacks resulted in decent amounts of hilarity and eventual full hangs. Since I can't review all kms drivers for such tricky ordering constraints v2 opts for a different approach and forces a full modeset if the connector dpms state isnt' DPMS_ON. Since the ->dpms callbacks implemented by the modeset helpers update the connector->dpms property we have the same effect of ensuring that the pipe is ultimately turned on, even if we just end up updating the fb. This is the same approac we ended up using in the intel driver. Note that besides i915.ko only all other drivers eventually call drm_helper_connector_dpms with the exception of vmwgfx, which does not support dmps at all. v3: Dave Airlie merged the broken first version of this patch, so squash in the revert of commit 372835a8527f85b3eff20a18c2c339e827dfd4e4 Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Sat Jun 15 00:13:13 2013 +0200 drm/crtc-helper: explicit DPMS on after modeset Also fix up the spelling fail a bit in the commit message while at it. Cc: Dave Airlie <airlied@redhat.com> Reviewed-by: Alex Deucher <alexdeucher@gmail.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=67043 Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Dave Airlie <airlied@redhat.com>
2013-07-20 00:57:11 +08:00
DRM_DEBUG_KMS("Setting connector DPMS state to on\n");
for (i = 0; i < set->num_connectors; i++) {
DRM_DEBUG_KMS("\t[CONNECTOR:%d:%s] set DPMS on\n", set->connectors[i]->base.id,
set->connectors[i]->name);
drm/crtc-helper: explicit DPMS on after modeset Atm the crtc helper implementation of set_config has really inconsisten semantics: If just an fb update is good enough, dpms state will be left as-is, but if we do a full modeset we force everything to dpms on. This change has already been applied to the i915 modeset code in commit e3de42b68478a8c95dd27520e9adead2af9477a5 Author: Imre Deak <imre.deak@intel.com> Date: Fri May 3 19:44:07 2013 +0200 drm/i915: force full modeset if the connector is in DPMS OFF mode which according to Greg KH seems to aim for a new record in most Bugzilla: links in a commit message. The history of this dpms forcing is pretty interesting. This patch here is an almost-revert of commit 811aaa55ba21ab37407018cfc01770d6b037d3fb Author: Keith Packard <keithp@keithp.com> Date: Thu Feb 3 16:57:28 2011 -0800 drm: Only set DPMS ON when actually configuring a mode which fixed the bug of trying to dpms on disabled outputs, but introduced the new discrepancy between an fb update only and full modesets. The actual introduction of this goes back to commit bf9dc102e284a5aa78c73fc9d72e11d5ccd8669f Author: Keith Packard <keithp@keithp.com> Date: Fri Nov 26 10:45:58 2010 -0800 drm: Set connector DPMS status to ON in drm_crtc_helper_set_config And if you'd dig around in the i915 driver code there's even more fun around forcing dpms on and losing our heads and temper of the resulting inconsistencies. Especially the DP re-training code had tons of funny stuff in it. v2: So v1 totally blew up on resume on my radeon system here. After much head-scraching I've figured out that the radeon resume functions resumes the console system _before_ it actually restores all the modeset state. And resuming the console systems means that fbdev doeas an immediate ->set_par call. Now up to this patch that ->set_par did absolutely nothing: All the old sw state from pre-suspend was still around (since the modeset reset wasn't done yet), which means that the set_config calls done as a result of the ->set_par where all treated as no-ops (despite that the real hw state was obviously something completely different). Since v1 of this patch just added a bunch of ->dpms calls if the crtc was enabled, those set_config calls suddenly stopped being no-ops. But because the hw state wasn't restored the ->dpms callbacks resulted in decent amounts of hilarity and eventual full hangs. Since I can't review all kms drivers for such tricky ordering constraints v2 opts for a different approach and forces a full modeset if the connector dpms state isnt' DPMS_ON. Since the ->dpms callbacks implemented by the modeset helpers update the connector->dpms property we have the same effect of ensuring that the pipe is ultimately turned on, even if we just end up updating the fb. This is the same approac we ended up using in the intel driver. Note that besides i915.ko only all other drivers eventually call drm_helper_connector_dpms with the exception of vmwgfx, which does not support dmps at all. v3: Dave Airlie merged the broken first version of this patch, so squash in the revert of commit 372835a8527f85b3eff20a18c2c339e827dfd4e4 Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Sat Jun 15 00:13:13 2013 +0200 drm/crtc-helper: explicit DPMS on after modeset Also fix up the spelling fail a bit in the commit message while at it. Cc: Dave Airlie <airlied@redhat.com> Reviewed-by: Alex Deucher <alexdeucher@gmail.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=67043 Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Dave Airlie <airlied@redhat.com>
2013-07-20 00:57:11 +08:00
set->connectors[i]->funcs->dpms(set->connectors[i], DRM_MODE_DPMS_ON);
}
}
drm/crtc-helper: fix locking for drm_helper_disable_unused_functions We have two calling contexts for thise function: - In the crtc helper code itself as part of the ->set_config implementation. In this calling context all modeset locks are already held, as they should. - In drivers not implementing fastboot before the fbdev/fbcon setup and initialization. This has been added for all drivers in commit 76a39dbfb2d1bc45219839e5a95d4ceaf6ca114f Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Sun Jan 20 23:12:54 2013 +0100 drm/fb-helper: don't disable everything in initial_config In this calling context we do not hold any modeset locks since the immediately following call to initialize the fbev emulation grabs all these locks themselves. - There are two exceptions to the above rule: shmob doesn't have fbdev emulation support. I've manually checked the callchain up to the driver load function and no kms locks are held. The right fix therefore is to split this helper into an internal and external version and add the required locking to the function exported to drivers. This remedies locking inconsistencies exposed by me adding locking WARNs as part of the recent kerneldoc abi polishing done in commit 62ff94a5492175759546f8bc61383189d6b49122 Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 22:18:47 2014 +0100 drm/crtc-helper: remove LOCKING from kerneldoc and commit 63951385052f7974155fa38f962f0f4e9847f90a Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 15:14:15 2014 +0100 drm/doc: Repleace LOCKING kerneldoc sections in drm_modes.c v2: It helps when I actually git add the entire thing. Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Tested-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2014-03-20 21:26:34 +08:00
__drm_helper_disable_unused_functions(dev);
} else if (fb_changed) {
set->crtc->x = set->x;
set->crtc->y = set->y;
set->crtc->primary->fb = set->fb;
ret = crtc_funcs->mode_set_base(set->crtc,
set->x, set->y, save_set.fb);
drm: Restore the old_fb upon modeset failure ... or else we may end up disabling the wrong framebuffer, leading to an OOPS, e.g: [ 6033.229012] kernel BUG at drivers/gpu/drm/i915/i915_gem.c:3271! [ 6033.229012] invalid opcode: 0000 [#1] SMP [ 6033.229012] last sysfs file: /sys/devices/virtual/backlight/acpi_video0/uevent [ 6033.229012] Modules linked in: sunrpc cpufreq_ondemand acpi_cpufreq mperf snd_hda_codec_analog snd_hda_intel snd_hda_codec snd_hwdep snd_seq snd_seq_device snd_pcm snd_timer thinkpad_acpi ppdev snd r852 sm_common iTCO_wdt uvcvideo i2c_i801 iTCO_vendor_support microcode wmi nand videodev nand_ids nand_ecc snd_page_alloc parport_pc parport mtd soundcore joydev v4l1_compat pcspkr uinput ipv6 sdhci_pci sdhci mmc_core yenta_socket i915 drm_kms_helper drm i2c_algo_bit i2c_core video output [last unloaded: scsi_wait_scan] [ 6033.229012] [ 6033.229012] Pid: 4834, comm: Xorg Not tainted 2.6.37-rc8+ #25 7661BL5/7661BL5 [ 6033.229012] EIP: 0060:[<f86fda5e>] EFLAGS: 00013246 CPU: 0 [ 6033.229012] EIP is at i915_gem_object_unpin+0x23/0x76 [i915] [ 6033.229012] EAX: f68a4000 EBX: f6831f00 ECX: 000600fa EDX: f68a8000 [ 6033.229012] ESI: f68a4014 EDI: f68a42b8 EBP: f2169c44 ESP: f2169c3c [ 6033.229012] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 [ 6033.229012] Process Xorg (pid: 4834, ti=f2168000 task=f21c8000 task.ti=f2168000) [ 6033.229012] Stack: [ 6033.229012] f3a84800 f68a4014 f2169c54 f87045d8 f3a84800 f872d9a8 f2169c68 f7fd8091 [ 6033.229012] f3b952a4 00000000 f68a414c f2169cf0 f7fd9377 00000000 00000000 f7fd98b0 [ 6033.229012] f7fd9f4e 0000000f f7f328a0 00000000 00000000 00000000 f2169ca4 f68a414c [ 6033.229012] Call Trace: [ 6033.229012] [<f87045d8>] ? intel_crtc_disable+0x36/0x41 [i915] [ 6033.229012] [<f7fd8091>] ? drm_helper_disable_unused_functions+0xcd/0xf9 [drm_kms_helper] [ 6033.229012] [<f7fd9377>] ? drm_crtc_helper_set_config+0x62a/0x7f7 [drm_kms_helper] [ 6033.229012] [<c04daa10>] ? __slab_free+0x1b/0xa4 [ 6033.229012] [<f7fd7e62>] ? drm_fb_helper_initial_config+0x466/0x497 [drm_kms_helper] [ 6033.229012] [<f7fd7ea3>] ? drm_fb_helper_restore+0x10/0x2a [drm_kms_helper] [ 6033.229012] [<f86f2577>] ? i915_driver_lastclose+0x2a/0x57 [i915] [ 6033.229012] [<f7f1989f>] ? drm_lastclose+0x45/0x23e [drm] [ 6033.229012] [<f7f1a0b4>] ? drm_release+0x462/0x4d7 [drm] Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: stable@kernel.org Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-01-08 23:10:41 +08:00
if (ret != 0) {
set->crtc->x = save_set.x;
set->crtc->y = save_set.y;
set->crtc->primary->fb = save_set.fb;
goto fail;
drm: Restore the old_fb upon modeset failure ... or else we may end up disabling the wrong framebuffer, leading to an OOPS, e.g: [ 6033.229012] kernel BUG at drivers/gpu/drm/i915/i915_gem.c:3271! [ 6033.229012] invalid opcode: 0000 [#1] SMP [ 6033.229012] last sysfs file: /sys/devices/virtual/backlight/acpi_video0/uevent [ 6033.229012] Modules linked in: sunrpc cpufreq_ondemand acpi_cpufreq mperf snd_hda_codec_analog snd_hda_intel snd_hda_codec snd_hwdep snd_seq snd_seq_device snd_pcm snd_timer thinkpad_acpi ppdev snd r852 sm_common iTCO_wdt uvcvideo i2c_i801 iTCO_vendor_support microcode wmi nand videodev nand_ids nand_ecc snd_page_alloc parport_pc parport mtd soundcore joydev v4l1_compat pcspkr uinput ipv6 sdhci_pci sdhci mmc_core yenta_socket i915 drm_kms_helper drm i2c_algo_bit i2c_core video output [last unloaded: scsi_wait_scan] [ 6033.229012] [ 6033.229012] Pid: 4834, comm: Xorg Not tainted 2.6.37-rc8+ #25 7661BL5/7661BL5 [ 6033.229012] EIP: 0060:[<f86fda5e>] EFLAGS: 00013246 CPU: 0 [ 6033.229012] EIP is at i915_gem_object_unpin+0x23/0x76 [i915] [ 6033.229012] EAX: f68a4000 EBX: f6831f00 ECX: 000600fa EDX: f68a8000 [ 6033.229012] ESI: f68a4014 EDI: f68a42b8 EBP: f2169c44 ESP: f2169c3c [ 6033.229012] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 [ 6033.229012] Process Xorg (pid: 4834, ti=f2168000 task=f21c8000 task.ti=f2168000) [ 6033.229012] Stack: [ 6033.229012] f3a84800 f68a4014 f2169c54 f87045d8 f3a84800 f872d9a8 f2169c68 f7fd8091 [ 6033.229012] f3b952a4 00000000 f68a414c f2169cf0 f7fd9377 00000000 00000000 f7fd98b0 [ 6033.229012] f7fd9f4e 0000000f f7f328a0 00000000 00000000 00000000 f2169ca4 f68a414c [ 6033.229012] Call Trace: [ 6033.229012] [<f87045d8>] ? intel_crtc_disable+0x36/0x41 [i915] [ 6033.229012] [<f7fd8091>] ? drm_helper_disable_unused_functions+0xcd/0xf9 [drm_kms_helper] [ 6033.229012] [<f7fd9377>] ? drm_crtc_helper_set_config+0x62a/0x7f7 [drm_kms_helper] [ 6033.229012] [<c04daa10>] ? __slab_free+0x1b/0xa4 [ 6033.229012] [<f7fd7e62>] ? drm_fb_helper_initial_config+0x466/0x497 [drm_kms_helper] [ 6033.229012] [<f7fd7ea3>] ? drm_fb_helper_restore+0x10/0x2a [drm_kms_helper] [ 6033.229012] [<f86f2577>] ? i915_driver_lastclose+0x2a/0x57 [i915] [ 6033.229012] [<f7f1989f>] ? drm_lastclose+0x45/0x23e [drm] [ 6033.229012] [<f7f1a0b4>] ? drm_release+0x462/0x4d7 [drm] Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: stable@kernel.org Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-01-08 23:10:41 +08:00
}
}
kfree(save_connectors);
kfree(save_encoders);
return 0;
fail:
/* Restore all previous data. */
count = 0;
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
*encoder = save_encoders[count++];
}
count = 0;
list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
*connector = save_connectors[count++];
}
/* Try to restore the config */
if (mode_changed &&
!drm_crtc_helper_set_mode(save_set.crtc, save_set.mode, save_set.x,
save_set.y, save_set.fb))
DRM_ERROR("failed to restore config after modeset failure\n");
kfree(save_connectors);
kfree(save_encoders);
return ret;
}
EXPORT_SYMBOL(drm_crtc_helper_set_config);
static int drm_helper_choose_encoder_dpms(struct drm_encoder *encoder)
{
int dpms = DRM_MODE_DPMS_OFF;
struct drm_connector *connector;
struct drm_device *dev = encoder->dev;
list_for_each_entry(connector, &dev->mode_config.connector_list, head)
if (connector->encoder == encoder)
if (connector->dpms < dpms)
dpms = connector->dpms;
return dpms;
}
/* Helper which handles bridge ordering around encoder dpms */
static void drm_helper_encoder_dpms(struct drm_encoder *encoder, int mode)
{
struct drm_bridge *bridge = encoder->bridge;
const struct drm_encoder_helper_funcs *encoder_funcs;
if (bridge) {
if (mode == DRM_MODE_DPMS_ON)
bridge->funcs->pre_enable(bridge);
else
bridge->funcs->disable(bridge);
}
encoder_funcs = encoder->helper_private;
if (encoder_funcs->dpms)
encoder_funcs->dpms(encoder, mode);
if (bridge) {
if (mode == DRM_MODE_DPMS_ON)
bridge->funcs->enable(bridge);
else
bridge->funcs->post_disable(bridge);
}
}
static int drm_helper_choose_crtc_dpms(struct drm_crtc *crtc)
{
int dpms = DRM_MODE_DPMS_OFF;
struct drm_connector *connector;
struct drm_device *dev = crtc->dev;
list_for_each_entry(connector, &dev->mode_config.connector_list, head)
if (connector->encoder && connector->encoder->crtc == crtc)
if (connector->dpms < dpms)
dpms = connector->dpms;
return dpms;
}
/**
* drm_helper_connector_dpms() - connector dpms helper implementation
* @connector: affected connector
* @mode: DPMS mode
*
* This is the main helper function provided by the crtc helper framework for
* implementing the DPMS connector attribute. It computes the new desired DPMS
* state for all encoders and crtcs in the output mesh and calls the ->dpms()
* callback provided by the driver appropriately.
*/
void drm_helper_connector_dpms(struct drm_connector *connector, int mode)
{
struct drm_encoder *encoder = connector->encoder;
struct drm_crtc *crtc = encoder ? encoder->crtc : NULL;
int old_dpms, encoder_dpms = DRM_MODE_DPMS_OFF;
if (mode == connector->dpms)
return;
old_dpms = connector->dpms;
connector->dpms = mode;
if (encoder)
encoder_dpms = drm_helper_choose_encoder_dpms(encoder);
/* from off to on, do crtc then encoder */
if (mode < old_dpms) {
if (crtc) {
const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
if (crtc_funcs->dpms)
(*crtc_funcs->dpms) (crtc,
drm_helper_choose_crtc_dpms(crtc));
}
if (encoder)
drm_helper_encoder_dpms(encoder, encoder_dpms);
}
/* from on to off, do encoder then crtc */
if (mode > old_dpms) {
if (encoder)
drm_helper_encoder_dpms(encoder, encoder_dpms);
if (crtc) {
const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
if (crtc_funcs->dpms)
(*crtc_funcs->dpms) (crtc,
drm_helper_choose_crtc_dpms(crtc));
}
}
return;
}
EXPORT_SYMBOL(drm_helper_connector_dpms);
/**
* drm_helper_mode_fill_fb_struct - fill out framebuffer metadata
* @fb: drm_framebuffer object to fill out
* @mode_cmd: metadata from the userspace fb creation request
*
* This helper can be used in a drivers fb_create callback to pre-fill the fb's
* metadata fields.
*/
void drm_helper_mode_fill_fb_struct(struct drm_framebuffer *fb,
struct drm_mode_fb_cmd2 *mode_cmd)
{
int i;
fb->width = mode_cmd->width;
fb->height = mode_cmd->height;
for (i = 0; i < 4; i++) {
fb->pitches[i] = mode_cmd->pitches[i];
fb->offsets[i] = mode_cmd->offsets[i];
drm: add support for tiled/compressed/etc modifier in addfb2 In DRM/KMS we are lacking a good way to deal with tiled/compressed formats. Especially in the case of dmabuf/prime buffer sharing, where we cannot always rely on under-the-hood flags passed to driver specific gem-create ioctl to pass around these extra flags. The proposal is to add a per-plane format modifier. This allows to, if necessary, use different tiling patters for sub-sampled planes, etc. The format modifiers are added at the end of the ioctl struct, so for legacy userspace it will be zero padded. v1: original v1.5: increase modifier to 64b v2: Incorporate review comments from the big thread, plus a few more. - Add a getcap so that userspace doesn't have to jump through hoops. - Allow modifiers only when a flag is set. That way drivers know when they're dealing with old userspace and need to fish out e.g. tiling from other information. - After rolling out checks for ->modifier to all drivers I've decided that this is way too fragile and needs an explicit opt-in flag. So do that instead. - Add a define (just for documentation really) for the "NONE" modifier. Imo we don't need to add mask #defines since drivers really should only do exact matches against values defined with fourcc_mod_code. - Drop the Samsung tiling modifier on Rob's request since he's not yet sure whether that one is accurate. v3: - Also add a new ->modifier[] array to struct drm_framebuffer and fill it in drm_helper_mode_fill_fb_struct. Requested by Tvrkto Uruslin. - Remove TODO in comment and add code comment that modifiers should be properly documented, requested by Rob. Cc: Rob Clark <robdclark@gmail.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com> Cc: Daniel Stone <daniel@fooishbar.org> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> Cc: Michel Dänzer <michel@daenzer.net> Signed-off-by: Rob Clark <robdclark@gmail.com> (v1.5) Reviewed-by: Rob Clark <robdclark@gmail.com> Reviewed-by: Daniel Stone <daniels@collabora.com> Acked-by: Dave Airlie <airlied@redhat.com> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
2015-02-05 22:41:52 +08:00
fb->modifier[i] = mode_cmd->modifier[i];
}
drm_fb_get_bpp_depth(mode_cmd->pixel_format, &fb->depth,
&fb->bits_per_pixel);
fb->pixel_format = mode_cmd->pixel_format;
fb->flags = mode_cmd->flags;
}
EXPORT_SYMBOL(drm_helper_mode_fill_fb_struct);
/**
* drm_helper_resume_force_mode - force-restore mode setting configuration
* @dev: drm_device which should be restored
*
* Drivers which use the mode setting helpers can use this function to
* force-restore the mode setting configuration e.g. on resume or when something
* else might have trampled over the hw state (like some overzealous old BIOSen
* tended to do).
*
* This helper doesn't provide a error return value since restoring the old
* config should never fail due to resource allocation issues since the driver
* has successfully set the restored configuration already. Hence this should
* boil down to the equivalent of a few dpms on calls, which also don't provide
* an error code.
*
* Drivers where simply restoring an old configuration again might fail (e.g.
* due to slight differences in allocating shared resources when the
* configuration is restored in a different order than when userspace set it up)
* need to use their own restore logic.
*/
void drm_helper_resume_force_mode(struct drm_device *dev)
{
struct drm_crtc *crtc;
struct drm_encoder *encoder;
const struct drm_crtc_helper_funcs *crtc_funcs;
int encoder_dpms;
bool ret;
drm_modeset_lock_all(dev);
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
if (!crtc->enabled)
continue;
ret = drm_crtc_helper_set_mode(crtc, &crtc->mode,
crtc->x, crtc->y, crtc->primary->fb);
/* Restoring the old config should never fail! */
if (ret == false)
DRM_ERROR("failed to set mode on crtc %p\n", crtc);
/* Turn off outputs that were already powered off */
if (drm_helper_choose_crtc_dpms(crtc)) {
list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
if(encoder->crtc != crtc)
continue;
encoder_dpms = drm_helper_choose_encoder_dpms(
encoder);
drm_helper_encoder_dpms(encoder, encoder_dpms);
}
crtc_funcs = crtc->helper_private;
if (crtc_funcs->dpms)
(*crtc_funcs->dpms) (crtc,
drm_helper_choose_crtc_dpms(crtc));
}
}
/* disable the unused connectors while restoring the modesetting */
drm/crtc-helper: fix locking for drm_helper_disable_unused_functions We have two calling contexts for thise function: - In the crtc helper code itself as part of the ->set_config implementation. In this calling context all modeset locks are already held, as they should. - In drivers not implementing fastboot before the fbdev/fbcon setup and initialization. This has been added for all drivers in commit 76a39dbfb2d1bc45219839e5a95d4ceaf6ca114f Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Sun Jan 20 23:12:54 2013 +0100 drm/fb-helper: don't disable everything in initial_config In this calling context we do not hold any modeset locks since the immediately following call to initialize the fbev emulation grabs all these locks themselves. - There are two exceptions to the above rule: shmob doesn't have fbdev emulation support. I've manually checked the callchain up to the driver load function and no kms locks are held. The right fix therefore is to split this helper into an internal and external version and add the required locking to the function exported to drivers. This remedies locking inconsistencies exposed by me adding locking WARNs as part of the recent kerneldoc abi polishing done in commit 62ff94a5492175759546f8bc61383189d6b49122 Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 22:18:47 2014 +0100 drm/crtc-helper: remove LOCKING from kerneldoc and commit 63951385052f7974155fa38f962f0f4e9847f90a Author: Daniel Vetter <daniel.vetter@ffwll.ch> Date: Thu Jan 23 15:14:15 2014 +0100 drm/doc: Repleace LOCKING kerneldoc sections in drm_modes.c v2: It helps when I actually git add the entire thing. Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Tested-by: Thierry Reding <treding@nvidia.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2014-03-20 21:26:34 +08:00
__drm_helper_disable_unused_functions(dev);
drm_modeset_unlock_all(dev);
}
EXPORT_SYMBOL(drm_helper_resume_force_mode);
/**
* drm_helper_crtc_mode_set - mode_set implementation for atomic plane helpers
* @crtc: DRM CRTC
* @mode: DRM display mode which userspace requested
* @adjusted_mode: DRM display mode adjusted by ->mode_fixup callbacks
* @x: x offset of the CRTC scanout area on the underlying framebuffer
* @y: y offset of the CRTC scanout area on the underlying framebuffer
* @old_fb: previous framebuffer
*
* This function implements a callback useable as the ->mode_set callback
* required by the crtc helpers. Besides the atomic plane helper functions for
* the primary plane the driver must also provide the ->mode_set_nofb callback
* to set up the crtc.
*
* This is a transitional helper useful for converting drivers to the atomic
* interfaces.
*/
int drm_helper_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode,
struct drm_display_mode *adjusted_mode, int x, int y,
struct drm_framebuffer *old_fb)
{
struct drm_crtc_state *crtc_state;
const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
int ret;
if (crtc->funcs->atomic_duplicate_state)
crtc_state = crtc->funcs->atomic_duplicate_state(crtc);
else if (crtc->state)
crtc_state = kmemdup(crtc->state, sizeof(*crtc_state),
GFP_KERNEL);
else
crtc_state = kzalloc(sizeof(*crtc_state), GFP_KERNEL);
if (!crtc_state)
return -ENOMEM;
crtc_state->crtc = crtc;
crtc_state->enable = true;
crtc_state->planes_changed = true;
drm: Atomic crtc/connector updates using crtc/plane helper interfaces So this is finally the integration of the crtc and plane helper interfaces into the atomic helper functions. In the check function we now have a few steps: - First we update the output routing and figure out which crtcs need a full mode set. Suitable encoders are selected using ->best_encoder, with the same semantics as the crtc helpers of implicitly disabling all connectors currently using the encoder. - Then we pull all other connectors into the state update which feed from a crtc which changes. This must be done do catch mode changes and similar updates - atomic updates are differences on top of the current state. - Then we call all the various ->mode_fixup to compute the adjusted mode. Note that here we have a slight semantic difference compared to the crtc helpers: We have not yet updated the encoder->crtc link when calling the encoder's ->mode_fixup function. But that's a requirement when converting to atomic since we want to prepare the entire state completely contained with the over drm_atomic_state structure. So this must be carefully checked when converting drivers over to atomic helpers. - Finally we do call the atomic_check functions on planes and crtcs. The commit function is also quite a beast: - The only step that can fail is done first, namely pinning the framebuffers. After that we cross the point of no return, an async commit would push all that into the worker thread. - The disabling of encoders and connectors is a bit tricky, since depending upon the final state we need to select different crtc helper functions. - Software tracking is a bit clarified compared to the crtc helpers: We commit the software state before starting to touch the hardware, like crtc helpers. But since we just swap them we still have the old state (i.e. the current hw state) around, which is really handy to write simple disable functions. So no more drm_crtc_helper_disable_all_unused_functions kind of fun because we're leaving unused crtcs/encoders behind. Everything gets shut down in-order now, which is one of the key differences of the i915 helpers compared to crtc helpers and a really nice additional guarantee. - Like with the plane helpers the atomic commit function waits for one vblank to pass before calling the framebuffer cleanup function. Compared to Rob's helper approach there's a bunch of upsides: - All the interfaces which can fail are called in the ->check hook (i.e. ->best_match and the various ->mode_fixup hooks). This means that drivers can just reuse those functions and don't need to move everything into ->atomic_check callbacks. If drivers have no need for additional constraint checking beyong their existing crtc helper callbacks they don't need to do anything. - The actual commit operation is properly stage: First we prepare framebuffers, which can potentially still fail (due to memory exhausting). This is important for the async case, where this must be done synchronously to correctly return errors. - The output configuration changes (done with crtc helper functions) and the plane update (using atomic plane helpers) are correctly interleaved: First we shut down any crtcs that need changing, then we update planes and finally we enable everything again. Hardware without GO bits must be more careful with ordering, which this sequence enables. - Also for hardware with shared output resources (like display PLLs) we first must shut down the old configuration before we can enable the new one. Otherwise we can hit an impossible intermediate state where there's not enough PLLs (which is the point behind atomic updates). v2: - Ensure that users of ->check update crtc_state->enable correctly. - Update the legacy state in crtc/plane structures. Eventually we want to remove that, but for now the drm core still expects this (especially the plane->fb pointer). v3: A few changes for better async handling: - Reorder the software side state commit so that it happens all before we touch the hardware. This way async support becomes very easy since we can punt all the actual hw touching to a worker thread. And as long as we synchronize with that thread (flushing or cancelling, depending upon what the driver can handle) before we commit the next software state there's no need for any locking in the worker thread at all. Which greatly simplifies things. And as long as we synchronize with all relevant threads we can have a lot of them (e.g. per-crtc for per-crtc updates) running in parallel. - Expose pre/post plane commit steps separately. We need to expose the actual hw commit step anyway for drivers to be able to implement asynchronous commit workers. But if we expose pre/post and plane commit steps individually we allow drivers to selectively use atomic helpers. - I've forgotten to call encoder/bridge ->mode_set functions, fix this. v4: Add debug output and fix a mixup between current and new state that resulted in crtcs not getting updated correctly. And in an Oops ... v5: - Be kind to driver writers in the vblank wait functions.. if thing aren't working yet, and vblank irq will never come, then let's not block forever.. especially under console-lock. - Correctly clear connector_state->best_encoder when disabling. Spotted while trying to understand a report from Rob Clark. - Only steal encoder if it actually changed, otherwise hilarity ensues if we steal from the current connector and so set the ->crtc pointer unexpectedly to NULL. Reported by Rob Clark. - Bail out in disable_outputs if an output currently doesn't have a best_encoder - this means it's already disabled. v6: Fixupe kerneldoc as reported by Paulo. And also fix up kerneldoc in drm_crtc.h. v7: Take ownership of the atomic state and clean it up with drm_atomic_state_free(). v8 Various improvements all over: - Polish code comments and kerneldoc. - Improve debug output to make sure all failure cases are logged. - Treat enabled crtc with no connectors as invalid input from userspace. - Don't ignore the return value from mode_fixup(). v9: - Improve debug output for crtc_state->mode_changed. v10: - Fixup the vblank waiting code to properly balance the vblank_get/put calls. - Better comments when checking/computing crtc->mode_changed v11: Fixup the encoder stealing logic: We can't look at encoder->crtc since that's not in the atomic state structures and might be updated asynchronously in and async commit. Instead we need to inspect all the connector states and check whether the encoder is currently in used and if so, on which crtc. v12: Review from Sean: - A few spelling fixes. - Flatten control flow indent by converting if blocks to early continue/return in 2 places. - Capture connectors_for_crtc return value in int num_connectors instead of bool has_connectors and do an explicit int->bool conversion with !!. I think the helper is more useful for drivers if it returns the number of connectors (e.g. to detect cloning configurations), so decided to keep that return value. Cc: Sean Paul <seanpaul@chromium.org> Cc: Paulo Zanoni <przanoni@gmail.com> Cc: Rob Clark <robdclark@gmail.com> Reviewed-by: Sean Paul <seanpaul@chromium.org> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-09-16 23:50:47 +08:00
crtc_state->mode_changed = true;
drm_mode_copy(&crtc_state->mode, mode);
drm_mode_copy(&crtc_state->adjusted_mode, adjusted_mode);
if (crtc_funcs->atomic_check) {
ret = crtc_funcs->atomic_check(crtc, crtc_state);
if (ret) {
if (crtc->funcs->atomic_destroy_state) {
crtc->funcs->atomic_destroy_state(crtc,
crtc_state);
} else {
kfree(crtc_state);
}
return ret;
}
}
swap(crtc->state, crtc_state);
crtc_funcs->mode_set_nofb(crtc);
if (crtc_state) {
if (crtc->funcs->atomic_destroy_state)
crtc->funcs->atomic_destroy_state(crtc, crtc_state);
else
kfree(crtc_state);
}
return drm_helper_crtc_mode_set_base(crtc, x, y, old_fb);
}
EXPORT_SYMBOL(drm_helper_crtc_mode_set);
/**
* drm_helper_crtc_mode_set_base - mode_set_base implementation for atomic plane helpers
* @crtc: DRM CRTC
* @x: x offset of the CRTC scanout area on the underlying framebuffer
* @y: y offset of the CRTC scanout area on the underlying framebuffer
* @old_fb: previous framebuffer
*
* This function implements a callback useable as the ->mode_set_base used
* required by the crtc helpers. The driver must provide the atomic plane helper
* functions for the primary plane.
*
* This is a transitional helper useful for converting drivers to the atomic
* interfaces.
*/
int drm_helper_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
struct drm_framebuffer *old_fb)
{
struct drm_plane_state *plane_state;
struct drm_plane *plane = crtc->primary;
if (plane->funcs->atomic_duplicate_state)
plane_state = plane->funcs->atomic_duplicate_state(plane);
else if (plane->state)
drm/atomic: Refcounting for plane_state->fb So my original plan was that the drm core refcounts framebuffers like with the legacy ioctls. But that doesn't work for a bunch of reasons: - State objects might live longer than until the next fb change happens for a plane. For example delayed cleanup work only happens _after_ the pageflip ioctl has completed. So this definitely doesn't work without the plane state holding its own references. - The other issue is transition from legacy to atomic implementations, where the driver works under a mix of both worlds. Which means legacy paths might not properly update the ->fb pointer under plane->state->fb. Which is a bit a problem when then someone comes around and _does_ try to clean it up when it's long gone. The second issue is just a bit a transition bug, since drivers should update plane->state->fb in all the paths that aren't converted yet. But a bit more robustness for the transition can't hurt - we pull similar tricks with cleaning up the old fb in the transitional helpers already. The pattern for drivers that transition is if (plane->state) drm_atomic_set_fb_for_plane(plane->state, plane->fb); inserted after the fb update has logically completed at the end of ->set_config (or ->set_base/mode_set if using the crtc helpers), ->page_flip, ->update_plane or any other entry point which updates plane->fb. v2: Update kerneldoc - copypasta fail. v3: Fix spelling in the commit message (Sean). Reviewed-by: Sean Paul <seanpaul@chromium.org> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
2014-11-05 05:57:27 +08:00
plane_state = drm_atomic_helper_plane_duplicate_state(plane);
else
plane_state = kzalloc(sizeof(*plane_state), GFP_KERNEL);
if (!plane_state)
return -ENOMEM;
plane_state->plane = plane;
plane_state->crtc = crtc;
drm/atomic: Refcounting for plane_state->fb So my original plan was that the drm core refcounts framebuffers like with the legacy ioctls. But that doesn't work for a bunch of reasons: - State objects might live longer than until the next fb change happens for a plane. For example delayed cleanup work only happens _after_ the pageflip ioctl has completed. So this definitely doesn't work without the plane state holding its own references. - The other issue is transition from legacy to atomic implementations, where the driver works under a mix of both worlds. Which means legacy paths might not properly update the ->fb pointer under plane->state->fb. Which is a bit a problem when then someone comes around and _does_ try to clean it up when it's long gone. The second issue is just a bit a transition bug, since drivers should update plane->state->fb in all the paths that aren't converted yet. But a bit more robustness for the transition can't hurt - we pull similar tricks with cleaning up the old fb in the transitional helpers already. The pattern for drivers that transition is if (plane->state) drm_atomic_set_fb_for_plane(plane->state, plane->fb); inserted after the fb update has logically completed at the end of ->set_config (or ->set_base/mode_set if using the crtc helpers), ->page_flip, ->update_plane or any other entry point which updates plane->fb. v2: Update kerneldoc - copypasta fail. v3: Fix spelling in the commit message (Sean). Reviewed-by: Sean Paul <seanpaul@chromium.org> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
2014-11-05 05:57:27 +08:00
drm_atomic_set_fb_for_plane(plane_state, crtc->primary->fb);
plane_state->crtc_x = 0;
plane_state->crtc_y = 0;
plane_state->crtc_h = crtc->mode.vdisplay;
plane_state->crtc_w = crtc->mode.hdisplay;
plane_state->src_x = x << 16;
plane_state->src_y = y << 16;
plane_state->src_h = crtc->mode.vdisplay << 16;
plane_state->src_w = crtc->mode.hdisplay << 16;
return drm_plane_helper_commit(plane, plane_state, old_fb);
}
EXPORT_SYMBOL(drm_helper_crtc_mode_set_base);