diff options
| author | Dave Airlie <airlied@redhat.com> | 2025-04-14 08:29:49 +0300 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2025-04-14 08:29:49 +0300 |
| commit | 683058df13c7de4cf29fb4a929d431ca12313966 (patch) | |
| tree | f8f556cfe3edb870ea93c69586a4ed8998775291 /include | |
| parent | 8ffd015db85fea3e15a77027fda6c02ced4d2444 (diff) | |
| parent | e8bf4a1bdaeadb28d13b9a2bcfd5910fda06eede (diff) | |
| download | linux-683058df13c7de4cf29fb4a929d431ca12313966.tar.xz | |
Merge tag 'drm-misc-next-2025-04-09' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-next
drm-misc-next for v6.16-rc1:
UAPI Changes:
- Add ASAHI uapi header!
- Add apple fourcc modifiers.
- Add capset virtio definitions to UAPI.
- Extend EXPORT_SYNC_FILE for timeline syncobjs.
Cross-subsystem Changes:
- Adjust DMA-BUF sg handling to not cache map on attach.
- Update drm/ci, hlcdc, virtio, maintainers.
- Update fbdev todo.
- Allow setting dma-device for dma-buf import.
- Export efi_mem_desc_lookup to make efidrm build as a module.
Core Changes:
- Update drm scheduler docs.
- Use the correct resv object in TTM delayed destroy.
- Fix compiler warning with panic qr code, and other small fixes.
- drm/ci updates.
- Add debugfs file for listing all bridges.
- Small fixes to drm/client, ttm tests.
- Add documentation to display/hdmi.
- Add kunit tests for bridges.
- Dont fail managed device probing if connector polling fails.
- Create Kconfig.debug for drm core.
- Add tests for the drm scheduler.
- Add and use new access helpers for DPCPD.
- Add generic and optimized conversions for format-helper.
- Begin refcounting panel for improving lifetime handling.
- Unify simpledrm and ofdrm sysfb, and add extra features.
- Split hdmi audio in bridge to make DP audio work.
Driver Changes:
- Convert drivers to use devm_platform_ioremap_resource().
- Assorted small fixes to imx/legacy-bridg, gma500, pl111, nouveau, vc4,
vmwgfx, ast, mxsfb, xlnx, accel/qaic, v3d, bridge/imx8qxp-ldb, ofdrm,
bridge/fsl-ldb, udl, bridge/ti-sn65dsi86, bridge/anx7625, cirrus-qemu,
bridge/cdns-dsi, panel/sharp, panel/himax, bridge/sil902x, renesas,
imagination, various panels.
- Allow attaching more display to vkms.
- Add Powertip PH128800T004-ZZA01 panel.
- Add rotation quirk for ZOTAC panel.
- Convert bridge/tc358775 to atomic.
- Remove deprecated panel calls from synaptics, novatek, samsung panels.
- Refactor shmem helper page pinning and accel drivers using it.
- Add dmabuf support to accel/amdxdna.
- Use 4k page table format for panfrost/mediatek.
- Add common powerup/down dp link helper and use it.
- Assorted compiler warning fixes.
- Support dma-buf import for renesas
Signed-off-by: Dave Airlie <airlied@redhat.com>
# Conflicts:
# include/drm/drm_kunit_helpers.h
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://lore.kernel.org/r/e147ff95-697b-4067-9e2e-7cbd424e162a@linux.intel.com
Diffstat (limited to 'include')
| -rw-r--r-- | include/drm/display/drm_dp_helper.h | 94 | ||||
| -rw-r--r-- | include/drm/drm_atomic.h | 3 | ||||
| -rw-r--r-- | include/drm/drm_bridge.h | 195 | ||||
| -rw-r--r-- | include/drm/drm_bridge_helper.h | 12 | ||||
| -rw-r--r-- | include/drm/drm_device.h | 41 | ||||
| -rw-r--r-- | include/drm/drm_edid.h | 2 | ||||
| -rw-r--r-- | include/drm/drm_gem.h | 15 | ||||
| -rw-r--r-- | include/drm/drm_gem_shmem_helper.h | 45 | ||||
| -rw-r--r-- | include/drm/drm_kunit_helpers.h | 8 | ||||
| -rw-r--r-- | include/drm/drm_mipi_dsi.h | 1 | ||||
| -rw-r--r-- | include/drm/drm_mode_config.h | 4 | ||||
| -rw-r--r-- | include/drm/drm_panel.h | 41 | ||||
| -rw-r--r-- | include/drm/drm_probe_helper.h | 2 | ||||
| -rw-r--r-- | include/drm/gpu_scheduler.h | 112 | ||||
| -rw-r--r-- | include/linux/dma-buf.h | 27 | ||||
| -rw-r--r-- | include/linux/dma-fence.h | 25 | ||||
| -rw-r--r-- | include/linux/screen_info.h | 9 | ||||
| -rw-r--r-- | include/uapi/drm/asahi_drm.h | 1194 | ||||
| -rw-r--r-- | include/uapi/drm/drm.h | 4 | ||||
| -rw-r--r-- | include/uapi/drm/drm_fourcc.h | 45 | ||||
| -rw-r--r-- | include/uapi/drm/virtgpu_drm.h | 6 | ||||
| -rw-r--r-- | include/uapi/linux/virtio_gpu.h | 3 | ||||
| -rw-r--r-- | include/video/pixel_format.h | 41 |
23 files changed, 1801 insertions, 128 deletions
diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 5ae4241959f2..d9614e2c8939 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -528,13 +528,72 @@ ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, void *buffer, size_t size); /** + * drm_dp_dpcd_read_data() - read a series of bytes from the DPCD + * @aux: DisplayPort AUX channel (SST or MST) + * @offset: address of the (first) register to read + * @buffer: buffer to store the register values + * @size: number of bytes in @buffer + * + * Returns zero (0) on success, or a negative error + * code on failure. -EIO is returned if the request was NAKed by the sink or + * if the retry count was exceeded. If not all bytes were transferred, this + * function returns -EPROTO. Errors from the underlying AUX channel transfer + * function, with the exception of -EBUSY (which causes the transaction to + * be retried), are propagated to the caller. + */ +static inline int drm_dp_dpcd_read_data(struct drm_dp_aux *aux, + unsigned int offset, + void *buffer, size_t size) +{ + int ret; + + ret = drm_dp_dpcd_read(aux, offset, buffer, size); + if (ret < 0) + return ret; + if (ret < size) + return -EPROTO; + + return 0; +} + +/** + * drm_dp_dpcd_write_data() - write a series of bytes to the DPCD + * @aux: DisplayPort AUX channel (SST or MST) + * @offset: address of the (first) register to write + * @buffer: buffer containing the values to write + * @size: number of bytes in @buffer + * + * Returns zero (0) on success, or a negative error + * code on failure. -EIO is returned if the request was NAKed by the sink or + * if the retry count was exceeded. If not all bytes were transferred, this + * function returns -EPROTO. Errors from the underlying AUX channel transfer + * function, with the exception of -EBUSY (which causes the transaction to + * be retried), are propagated to the caller. + */ +static inline int drm_dp_dpcd_write_data(struct drm_dp_aux *aux, + unsigned int offset, + void *buffer, size_t size) +{ + int ret; + + ret = drm_dp_dpcd_write(aux, offset, buffer, size); + if (ret < 0) + return ret; + if (ret < size) + return -EPROTO; + + return 0; +} + +/** * drm_dp_dpcd_readb() - read a single byte from the DPCD * @aux: DisplayPort AUX channel * @offset: address of the register to read * @valuep: location where the value of the register will be stored * * Returns the number of bytes transferred (1) on success, or a negative - * error code on failure. + * error code on failure. In most of the cases you should be using + * drm_dp_dpcd_read_byte() instead. */ static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, unsigned int offset, u8 *valuep) @@ -549,7 +608,8 @@ static inline ssize_t drm_dp_dpcd_readb(struct drm_dp_aux *aux, * @value: value to write to the register * * Returns the number of bytes transferred (1) on success, or a negative - * error code on failure. + * error code on failure. In most of the cases you should be using + * drm_dp_dpcd_write_byte() instead. */ static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux, unsigned int offset, u8 value) @@ -557,6 +617,34 @@ static inline ssize_t drm_dp_dpcd_writeb(struct drm_dp_aux *aux, return drm_dp_dpcd_write(aux, offset, &value, 1); } +/** + * drm_dp_dpcd_read_byte() - read a single byte from the DPCD + * @aux: DisplayPort AUX channel + * @offset: address of the register to read + * @valuep: location where the value of the register will be stored + * + * Returns zero (0) on success, or a negative error code on failure. + */ +static inline int drm_dp_dpcd_read_byte(struct drm_dp_aux *aux, + unsigned int offset, u8 *valuep) +{ + return drm_dp_dpcd_read_data(aux, offset, valuep, 1); +} + +/** + * drm_dp_dpcd_write_byte() - write a single byte to the DPCD + * @aux: DisplayPort AUX channel + * @offset: address of the register to write + * @value: value to write to the register + * + * Returns zero (0) on success, or a negative error code on failure. + */ +static inline int drm_dp_dpcd_write_byte(struct drm_dp_aux *aux, + unsigned int offset, u8 value) +{ + return drm_dp_dpcd_write_data(aux, offset, &value, 1); +} + int drm_dp_read_dpcd_caps(struct drm_dp_aux *aux, u8 dpcd[DP_RECEIVER_CAP_SIZE]); @@ -566,6 +654,8 @@ int drm_dp_dpcd_read_link_status(struct drm_dp_aux *aux, int drm_dp_dpcd_read_phy_link_status(struct drm_dp_aux *aux, enum drm_dp_phy dp_phy, u8 link_status[DP_LINK_STATUS_SIZE]); +int drm_dp_link_power_up(struct drm_dp_aux *aux, unsigned char revision); +int drm_dp_link_power_down(struct drm_dp_aux *aux, unsigned char revision); int drm_dp_dpcd_write_payload(struct drm_dp_aux *aux, int vcpid, u8 start_time_slot, u8 time_slot_count); diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index 4c673f0698fe..38636a593c9d 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -625,6 +625,9 @@ drm_atomic_get_old_connector_for_encoder(const struct drm_atomic_state *state, struct drm_connector * drm_atomic_get_new_connector_for_encoder(const struct drm_atomic_state *state, struct drm_encoder *encoder); +struct drm_connector * +drm_atomic_get_connector_for_encoder(const struct drm_encoder *encoder, + struct drm_modeset_acquire_ctx *ctx); struct drm_crtc * drm_atomic_get_old_crtc_for_encoder(struct drm_atomic_state *state, diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index d4c75d59fa12..4e418a29a9ff 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -73,7 +73,7 @@ struct drm_bridge_funcs { * * Zero on success, error code on failure. */ - int (*attach)(struct drm_bridge *bridge, + int (*attach)(struct drm_bridge *bridge, struct drm_encoder *encoder, enum drm_bridge_attach_flags flags); /** @@ -681,8 +681,10 @@ struct drm_bridge_funcs { /** * @hdmi_audio_startup: * - * Called when ASoC starts an audio stream setup. The - * @hdmi_audio_startup() is optional. + * Called when ASoC starts an audio stream setup. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_AUDIO flag in their &drm_bridge->ops. * * Returns: * 0 on success, a negative error code otherwise @@ -693,8 +695,10 @@ struct drm_bridge_funcs { /** * @hdmi_audio_prepare: * Configures HDMI-encoder for audio stream. Can be called multiple - * times for each setup. Mandatory if HDMI audio is enabled in the - * bridge's configuration. + * times for each setup. + * + * This callback is optional but it must be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_AUDIO flag in their &drm_bridge->ops. * * Returns: * 0 on success, a negative error code otherwise @@ -707,8 +711,10 @@ struct drm_bridge_funcs { /** * @hdmi_audio_shutdown: * - * Shut down the audio stream. Mandatory if HDMI audio is enabled in - * the bridge's configuration. + * Shut down the audio stream. + * + * This callback is optional but it must be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_AUDIO flag in their &drm_bridge->ops. * * Returns: * 0 on success, a negative error code otherwise @@ -719,8 +725,10 @@ struct drm_bridge_funcs { /** * @hdmi_audio_mute_stream: * - * Mute/unmute HDMI audio stream. The @hdmi_audio_mute_stream callback - * is optional. + * Mute/unmute HDMI audio stream. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_AUDIO flag in their &drm_bridge->ops. * * Returns: * 0 on success, a negative error code otherwise @@ -730,6 +738,65 @@ struct drm_bridge_funcs { bool enable, int direction); /** + * @dp_audio_startup: + * + * Called when ASoC starts a DisplayPort audio stream setup. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_DP_AUDIO flag in their &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*dp_audio_startup)(struct drm_connector *connector, + struct drm_bridge *bridge); + + /** + * @dp_audio_prepare: + * Configures DisplayPort audio stream. Can be called multiple + * times for each setup. + * + * This callback is optional but it must be implemented by bridges that + * set the @DRM_BRIDGE_OP_DP_AUDIO flag in their &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*dp_audio_prepare)(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms); + + /** + * @dp_audio_shutdown: + * + * Shut down the DisplayPort audio stream. + * + * This callback is optional but it must be implemented by bridges that + * set the @DRM_BRIDGE_OP_DP_AUDIO flag in their &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + void (*dp_audio_shutdown)(struct drm_connector *connector, + struct drm_bridge *bridge); + + /** + * @dp_audio_mute_stream: + * + * Mute/unmute DisplayPort audio stream. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_DP_AUDIO flag in their &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ + int (*dp_audio_mute_stream)(struct drm_connector *connector, + struct drm_bridge *bridge, + bool enable, int direction); + + /** * @debugfs_init: * * Allows bridges to create bridge-specific debugfs files. @@ -814,6 +881,32 @@ enum drm_bridge_ops { * drivers. */ DRM_BRIDGE_OP_HDMI = BIT(4), + /** + * @DRM_BRIDGE_OP_HDMI_AUDIO: The bridge provides HDMI audio operations. + * Bridges that set this flag must implement the + * &drm_bridge_funcs->hdmi_audio_prepare and + * &drm_bridge_funcs->hdmi_audio_shutdown callbacks. + * + * Note: currently there can be at most one bridge in a chain that sets + * this bit. This is to simplify corresponding glue code in connector + * drivers. Also it is not possible to have a bridge in the chain that + * sets @DRM_BRIDGE_OP_DP_AUDIO if there is a bridge that sets this + * flag. + */ + DRM_BRIDGE_OP_HDMI_AUDIO = BIT(5), + /** + * @DRM_BRIDGE_OP_DP_AUDIO: The bridge provides DisplayPort audio operations. + * Bridges that set this flag must implement the + * &drm_bridge_funcs->dp_audio_prepare and + * &drm_bridge_funcs->dp_audio_shutdown callbacks. + * + * Note: currently there can be at most one bridge in a chain that sets + * this bit. This is to simplify corresponding glue code in connector + * drivers. Also it is not possible to have a bridge in the chain that + * sets @DRM_BRIDGE_OP_HDMI_AUDIO if there is a bridge that sets this + * flag. + */ + DRM_BRIDGE_OP_DP_AUDIO = BIT(6), }; /** @@ -840,6 +933,18 @@ struct drm_bridge { const struct drm_bridge_timings *timings; /** @funcs: control functions */ const struct drm_bridge_funcs *funcs; + + /** + * @container: Pointer to the private driver struct embedding this + * @struct drm_bridge. + */ + void *container; + + /** + * @refcount: reference count of users referencing this bridge. + */ + struct kref refcount; + /** @driver_private: pointer to the bridge driver's internal context */ void *driver_private; /** @ops: bitmask of operations supported by the bridge */ @@ -914,23 +1019,28 @@ struct drm_bridge { unsigned int max_bpc; /** - * @hdmi_audio_dev: device to be used as a parent for the HDMI Codec + * @hdmi_audio_dev: device to be used as a parent for the HDMI Codec if + * either of @DRM_BRIDGE_OP_HDMI_AUDIO or @DRM_BRIDGE_OP_DP_AUDIO is set. */ struct device *hdmi_audio_dev; /** * @hdmi_audio_max_i2s_playback_channels: maximum number of playback - * I2S channels for the HDMI codec + * I2S channels for the @DRM_BRIDGE_OP_HDMI_AUDIO or + * @DRM_BRIDGE_OP_DP_AUDIO. */ int hdmi_audio_max_i2s_playback_channels; /** - * @hdmi_audio_spdif_playback: set if HDMI codec has S/PDIF playback port + * @hdmi_audio_spdif_playback: set if this bridge has S/PDIF playback + * port for @DRM_BRIDGE_OP_HDMI_AUDIO or @DRM_BRIDGE_OP_DP_AUDIO. */ unsigned int hdmi_audio_spdif_playback : 1; /** - * @hdmi_audio_dai_port: sound DAI port, -1 if it is not enabled + * @hdmi_audio_dai_port: sound DAI port for either of + * @DRM_BRIDGE_OP_HDMI_AUDIO and @DRM_BRIDGE_OP_DP_AUDIO, -1 if it is + * not used. */ int hdmi_audio_dai_port; }; @@ -941,6 +1051,30 @@ drm_priv_to_bridge(struct drm_private_obj *priv) return container_of(priv, struct drm_bridge, base); } +struct drm_bridge *drm_bridge_get(struct drm_bridge *bridge); +void drm_bridge_put(struct drm_bridge *bridge); + +void *__devm_drm_bridge_alloc(struct device *dev, size_t size, size_t offset, + const struct drm_bridge_funcs *funcs); + +/** + * devm_drm_bridge_alloc - Allocate and initialize a bridge + * @dev: struct device of the bridge device + * @type: the type of the struct which contains struct &drm_bridge + * @member: the name of the &drm_bridge within @type + * @funcs: callbacks for this bridge + * + * The reference count of the returned bridge is initialized to 1. This + * reference will be automatically dropped via devm (by calling + * drm_bridge_put()) when @dev is removed. + * + * Returns: + * Pointer to new bridge, or ERR_PTR on failure. + */ +#define devm_drm_bridge_alloc(dev, type, member, funcs) \ + ((type *)__devm_drm_bridge_alloc(dev, sizeof(type), \ + offsetof(type, member), funcs)) + void drm_bridge_add(struct drm_bridge *bridge); int devm_drm_bridge_add(struct device *dev, struct drm_bridge *bridge); void drm_bridge_remove(struct drm_bridge *bridge); @@ -958,6 +1092,38 @@ static inline struct drm_bridge *of_drm_find_bridge(struct device_node *np) #endif /** + * drm_bridge_get_current_state() - Get the current bridge state + * @bridge: bridge object + * + * This function must be called with the modeset lock held. + * + * RETURNS: + * + * The current bridge state, or NULL if there is none. + */ +static inline struct drm_bridge_state * +drm_bridge_get_current_state(struct drm_bridge *bridge) +{ + if (!bridge) + return NULL; + + /* + * Only atomic bridges will have bridge->base initialized by + * drm_atomic_private_obj_init(), so we need to make sure we're + * working with one before we try to use the lock. + */ + if (!bridge->funcs || !bridge->funcs->atomic_reset) + return NULL; + + drm_modeset_lock_assert_held(&bridge->base.lock); + + if (!bridge->base.state) + return NULL; + + return drm_priv_to_bridge_state(bridge->base.state); +} + +/** * drm_bridge_get_next_bridge() - Get the next bridge in the chain * @bridge: bridge object * @@ -1108,4 +1274,7 @@ static inline struct drm_bridge *drmm_of_get_bridge(struct drm_device *drm, } #endif +void drm_bridge_debugfs_params(struct dentry *root); +void drm_bridge_debugfs_encoder_params(struct dentry *root, struct drm_encoder *encoder); + #endif diff --git a/include/drm/drm_bridge_helper.h b/include/drm/drm_bridge_helper.h new file mode 100644 index 000000000000..6c35b479ec2a --- /dev/null +++ b/include/drm/drm_bridge_helper.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#ifndef __DRM_BRIDGE_HELPER_H_ +#define __DRM_BRIDGE_HELPER_H_ + +struct drm_bridge; +struct drm_modeset_acquire_ctx; + +int drm_bridge_helper_reset_crtc(struct drm_bridge *bridge, + struct drm_modeset_acquire_ctx *ctx); + +#endif // __DRM_BRIDGE_HELPER_H_ diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h index 6ea54a578cda..e2f894f1b90a 100644 --- a/include/drm/drm_device.h +++ b/include/drm/drm_device.h @@ -65,6 +65,28 @@ struct drm_device { struct device *dev; /** + * @dma_dev: + * + * Device for DMA operations. Only required if the device @dev + * cannot perform DMA by itself. Should be NULL otherwise. Call + * drm_dev_dma_dev() to get the DMA device instead of using this + * field directly. Call drm_dev_set_dma_dev() to set this field. + * + * DRM devices are sometimes bound to virtual devices that cannot + * perform DMA by themselves. Drivers should set this field to the + * respective DMA controller. + * + * Devices on USB and other peripheral busses also cannot perform + * DMA by themselves. The @dma_dev field should point the bus + * controller that does DMA on behalve of such a device. Required + * for importing buffers via dma-buf. + * + * If set, the DRM core automatically releases the reference on the + * device. + */ + struct device *dma_dev; + + /** * @managed: * * Managed resources linked to the lifetime of this &drm_device as @@ -327,4 +349,23 @@ struct drm_device { struct dentry *debugfs_root; }; +void drm_dev_set_dma_dev(struct drm_device *dev, struct device *dma_dev); + +/** + * drm_dev_dma_dev - returns the DMA device for a DRM device + * @dev: DRM device + * + * Returns the DMA device of the given DRM device. By default, this + * the DRM device's parent. See drm_dev_set_dma_dev(). + * + * Returns: + * A DMA-capable device for the DRM device. + */ +static inline struct device *drm_dev_dma_dev(struct drm_device *dev) +{ + if (dev->dma_dev) + return dev->dma_dev; + return dev->dev; +} + #endif diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index eaac5e665892..b38409670868 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -437,7 +437,7 @@ bool drm_detect_monitor_audio(const struct edid *edid); enum hdmi_quantization_range drm_default_rgb_quant_range(const struct drm_display_mode *mode); int drm_add_modes_noedid(struct drm_connector *connector, - int hdisplay, int vdisplay); + unsigned int hdisplay, unsigned int vdisplay); int drm_edid_header_is_valid(const void *edid); bool drm_edid_is_valid(struct edid *edid); diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index 2bf893eabb4b..9b71f7a9f3f8 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -159,7 +159,8 @@ struct drm_gem_object_funcs { * @vmap: * * Returns a virtual address for the buffer. Used by the - * drm_gem_dmabuf_vmap() helper. + * drm_gem_dmabuf_vmap() helper. Called with a held GEM reservation + * lock. * * This callback is optional. */ @@ -169,7 +170,8 @@ struct drm_gem_object_funcs { * @vunmap: * * Releases the address previously returned by @vmap. Used by the - * drm_gem_dmabuf_vunmap() helper. + * drm_gem_dmabuf_vunmap() helper. Called with a held GEM reservation + * lock. * * This callback is optional. */ @@ -192,7 +194,8 @@ struct drm_gem_object_funcs { * @evict: * * Evicts gem object out from memory. Used by the drm_gem_object_evict() - * helper. Returns 0 on success, -errno otherwise. + * helper. Returns 0 on success, -errno otherwise. Called with a held + * GEM reservation lock. * * This callback is optional. */ @@ -537,8 +540,8 @@ void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages, void drm_gem_lock(struct drm_gem_object *obj); void drm_gem_unlock(struct drm_gem_object *obj); -int drm_gem_vmap_unlocked(struct drm_gem_object *obj, struct iosys_map *map); -void drm_gem_vunmap_unlocked(struct drm_gem_object *obj, struct iosys_map *map); +int drm_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map); +void drm_gem_vunmap(struct drm_gem_object *obj, struct iosys_map *map); int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles, int count, struct drm_gem_object ***objs_out); @@ -561,7 +564,7 @@ unsigned long drm_gem_lru_scan(struct drm_gem_lru *lru, unsigned long *remaining, bool (*shrink)(struct drm_gem_object *obj)); -int drm_gem_evict(struct drm_gem_object *obj); +int drm_gem_evict_locked(struct drm_gem_object *obj); /** * drm_gem_object_is_shared_for_memory_stats - helper for shared memory stats diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index cef5a6b5a4d6..b4f993da3cae 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -37,7 +37,18 @@ struct drm_gem_shmem_object { * Reference count on the pages table. * The pages are put when the count reaches zero. */ - unsigned int pages_use_count; + refcount_t pages_use_count; + + /** + * @pages_pin_count: + * + * Reference count on the pinned pages table. + * + * Pages are hard-pinned and reside in memory if count + * greater than zero. Otherwise, when count is zero, the pages are + * allowed to be evicted and purged by memory shrinker. + */ + refcount_t pages_pin_count; /** * @madv: State for madvise @@ -71,7 +82,7 @@ struct drm_gem_shmem_object { * Reference count on the virtual address. * The address are un-mapped when the count reaches zero. */ - unsigned int vmap_use_count; + refcount_t vmap_use_count; /** * @pages_mark_dirty_on_put: @@ -102,28 +113,28 @@ struct drm_gem_shmem_object *drm_gem_shmem_create_with_mnt(struct drm_device *de struct vfsmount *gemfs); void drm_gem_shmem_free(struct drm_gem_shmem_object *shmem); -void drm_gem_shmem_put_pages(struct drm_gem_shmem_object *shmem); +void drm_gem_shmem_put_pages_locked(struct drm_gem_shmem_object *shmem); int drm_gem_shmem_pin(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_unpin(struct drm_gem_shmem_object *shmem); -int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, - struct iosys_map *map); -void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, - struct iosys_map *map); +int drm_gem_shmem_vmap_locked(struct drm_gem_shmem_object *shmem, + struct iosys_map *map); +void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem, + struct iosys_map *map); int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct *vma); int drm_gem_shmem_pin_locked(struct drm_gem_shmem_object *shmem); void drm_gem_shmem_unpin_locked(struct drm_gem_shmem_object *shmem); -int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv); +int drm_gem_shmem_madvise_locked(struct drm_gem_shmem_object *shmem, int madv); static inline bool drm_gem_shmem_is_purgeable(struct drm_gem_shmem_object *shmem) { return (shmem->madv > 0) && - !shmem->vmap_use_count && shmem->sgt && + !refcount_read(&shmem->pages_pin_count) && shmem->sgt && !shmem->base.dma_buf && !drm_gem_is_imported(&shmem->base); } -void drm_gem_shmem_purge(struct drm_gem_shmem_object *shmem); +void drm_gem_shmem_purge_locked(struct drm_gem_shmem_object *shmem); struct sg_table *drm_gem_shmem_get_sg_table(struct drm_gem_shmem_object *shmem); struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_shmem_object *shmem); @@ -214,12 +225,12 @@ static inline struct sg_table *drm_gem_shmem_object_get_sg_table(struct drm_gem_ } /* - * drm_gem_shmem_object_vmap - GEM object function for drm_gem_shmem_vmap() + * drm_gem_shmem_object_vmap - GEM object function for drm_gem_shmem_vmap_locked() * @obj: GEM object * @map: Returns the kernel virtual address of the SHMEM GEM object's backing store. * - * This function wraps drm_gem_shmem_vmap(). Drivers that employ the shmem helpers should - * use it as their &drm_gem_object_funcs.vmap handler. + * This function wraps drm_gem_shmem_vmap_locked(). Drivers that employ the shmem + * helpers should use it as their &drm_gem_object_funcs.vmap handler. * * Returns: * 0 on success or a negative error code on failure. @@ -229,7 +240,7 @@ static inline int drm_gem_shmem_object_vmap(struct drm_gem_object *obj, { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - return drm_gem_shmem_vmap(shmem, map); + return drm_gem_shmem_vmap_locked(shmem, map); } /* @@ -237,15 +248,15 @@ static inline int drm_gem_shmem_object_vmap(struct drm_gem_object *obj, * @obj: GEM object * @map: Kernel virtual address where the SHMEM GEM object was mapped * - * This function wraps drm_gem_shmem_vunmap(). Drivers that employ the shmem helpers should - * use it as their &drm_gem_object_funcs.vunmap handler. + * This function wraps drm_gem_shmem_vunmap_locked(). Drivers that employ the shmem + * helpers should use it as their &drm_gem_object_funcs.vunmap handler. */ static inline void drm_gem_shmem_object_vunmap(struct drm_gem_object *obj, struct iosys_map *map) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - drm_gem_shmem_vunmap(shmem, map); + drm_gem_shmem_vunmap_locked(shmem, map); } /** diff --git a/include/drm/drm_kunit_helpers.h b/include/drm/drm_kunit_helpers.h index 1c62d1d4458c..4948379237e9 100644 --- a/include/drm/drm_kunit_helpers.h +++ b/include/drm/drm_kunit_helpers.h @@ -9,6 +9,7 @@ #include <kunit/test.h> +struct drm_connector; struct drm_crtc_funcs; struct drm_crtc_helper_funcs; struct drm_device; @@ -118,6 +119,13 @@ drm_kunit_helper_create_crtc(struct kunit *test, const struct drm_crtc_funcs *funcs, const struct drm_crtc_helper_funcs *helper_funcs); +int drm_kunit_helper_enable_crtc_connector(struct kunit *test, + struct drm_device *drm, + struct drm_crtc *crtc, + struct drm_connector *connector, + const struct drm_display_mode *mode, + struct drm_modeset_acquire_ctx *ctx); + int drm_kunit_add_mode_destroy_action(struct kunit *test, struct drm_display_mode *mode); diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index bd40a443385c..d6796ce9f5ff 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -293,6 +293,7 @@ void mipi_dsi_generic_write_multi(struct mipi_dsi_multi_context *ctx, const void *payload, size_t size); ssize_t mipi_dsi_generic_read(struct mipi_dsi_device *dsi, const void *params, size_t num_params, void *data, size_t size); +u32 drm_mipi_dsi_get_input_bus_fmt(enum mipi_dsi_pixel_format dsi_format); #define mipi_dsi_msleep(ctx, delay) \ do { \ diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h index 271765e2e9f2..4b8f0370b79b 100644 --- a/include/drm/drm_mode_config.h +++ b/include/drm/drm_mode_config.h @@ -532,8 +532,8 @@ struct drm_mode_config { */ struct list_head privobj_list; - int min_width, min_height; - int max_width, max_height; + unsigned int min_width, min_height; + unsigned int max_width, max_height; const struct drm_mode_config_funcs *funcs; /* output poll support */ diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index a9c042c8dea1..31d84f901c51 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -28,6 +28,7 @@ #include <linux/errno.h> #include <linux/list.h> #include <linux/mutex.h> +#include <linux/kref.h> struct backlight_device; struct dentry; @@ -266,12 +267,52 @@ struct drm_panel { * If true then the panel has been enabled. */ bool enabled; + + /** + * @container: Pointer to the private driver struct embedding this + * @struct drm_panel. + */ + void *container; + + /** + * @refcount: reference count of users referencing this panel. + */ + struct kref refcount; }; +void *__devm_drm_panel_alloc(struct device *dev, size_t size, size_t offset, + const struct drm_panel_funcs *funcs, + int connector_type); + +/** + * devm_drm_panel_alloc - Allocate and initialize a refcounted panel. + * + * @dev: struct device of the panel device + * @type: the type of the struct which contains struct &drm_panel + * @member: the name of the &drm_panel within @type + * @funcs: callbacks for this panel + * @connector_type: the connector type (DRM_MODE_CONNECTOR_*) corresponding to + * the panel interface + * + * The reference count of the returned panel is initialized to 1. This + * reference will be automatically dropped via devm (by calling + * drm_panel_put()) when @dev is removed. + * + * Returns: + * Pointer to container structure embedding the panel, ERR_PTR on failure. + */ +#define devm_drm_panel_alloc(dev, type, member, funcs, connector_type) \ + ((type *)__devm_drm_panel_alloc(dev, sizeof(type), \ + offsetof(type, member), funcs, \ + connector_type)) + void drm_panel_init(struct drm_panel *panel, struct device *dev, const struct drm_panel_funcs *funcs, int connector_type); +struct drm_panel *drm_panel_get(struct drm_panel *panel); +void drm_panel_put(struct drm_panel *panel); + void drm_panel_add(struct drm_panel *panel); void drm_panel_remove(struct drm_panel *panel); diff --git a/include/drm/drm_probe_helper.h b/include/drm/drm_probe_helper.h index d6ce7b218b77..840ae5f798c2 100644 --- a/include/drm/drm_probe_helper.h +++ b/include/drm/drm_probe_helper.h @@ -17,7 +17,7 @@ int drm_helper_probe_detect(struct drm_connector *connector, struct drm_modeset_acquire_ctx *ctx, bool force); -int drmm_kms_helper_poll_init(struct drm_device *dev); +void drmm_kms_helper_poll_init(struct drm_device *dev); void drm_kms_helper_poll_init(struct drm_device *dev); void drm_kms_helper_poll_fini(struct drm_device *dev); bool drm_helper_hpd_irq_event(struct drm_device *dev); diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 50928a7ae98e..1a7e377d4cbb 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -383,8 +383,15 @@ struct drm_sched_job { struct xarray dependencies; }; +/** + * enum drm_gpu_sched_stat - the scheduler's status + * + * @DRM_GPU_SCHED_STAT_NONE: Reserved. Do not use. + * @DRM_GPU_SCHED_STAT_NOMINAL: Operation succeeded. + * @DRM_GPU_SCHED_STAT_ENODEV: Error: Device is not available anymore. + */ enum drm_gpu_sched_stat { - DRM_GPU_SCHED_STAT_NONE, /* Reserve 0 */ + DRM_GPU_SCHED_STAT_NONE, DRM_GPU_SCHED_STAT_NOMINAL, DRM_GPU_SCHED_STAT_ENODEV, }; @@ -410,10 +417,36 @@ struct drm_sched_backend_ops { struct drm_sched_entity *s_entity); /** - * @run_job: Called to execute the job once all of the dependencies - * have been resolved. This may be called multiple times, if - * timedout_job() has happened and drm_sched_job_recovery() - * decides to try it again. + * @run_job: Called to execute the job once all of the dependencies + * have been resolved. + * + * @sched_job: the job to run + * + * The deprecated drm_sched_resubmit_jobs() (called by &struct + * drm_sched_backend_ops.timedout_job) can invoke this again with the + * same parameters. Using this is discouraged because it violates + * dma_fence rules, notably dma_fence_init() has to be called on + * already initialized fences for a second time. Moreover, this is + * dangerous because attempts to allocate memory might deadlock with + * memory management code waiting for the reset to complete. + * + * TODO: Document what drivers should do / use instead. + * + * This method is called in a workqueue context - either from the + * submit_wq the driver passed through drm_sched_init(), or, if the + * driver passed NULL, a separate, ordered workqueue the scheduler + * allocated. + * + * Note that the scheduler expects to 'inherit' its own reference to + * this fence from the callback. It does not invoke an extra + * dma_fence_get() on it. Consequently, this callback must take a + * reference for the scheduler, and additional ones for the driver's + * respective needs. + * + * Return: + * * On success: dma_fence the driver must signal once the hardware has + * completed the job ("hardware fence"). + * * On failure: NULL or an ERR_PTR. */ struct dma_fence *(*run_job)(struct drm_sched_job *sched_job); @@ -421,43 +454,52 @@ struct drm_sched_backend_ops { * @timedout_job: Called when a job has taken too long to execute, * to trigger GPU recovery. * - * This method is called in a workqueue context. + * @sched_job: The job that has timed out + * + * Drivers typically issue a reset to recover from GPU hangs. + * This procedure looks very different depending on whether a firmware + * or a hardware scheduler is being used. + * + * For a FIRMWARE SCHEDULER, each ring has one scheduler, and each + * scheduler has one entity. Hence, the steps taken typically look as + * follows: * - * Drivers typically issue a reset to recover from GPU hangs, and this - * procedure usually follows the following workflow: + * 1. Stop the scheduler using drm_sched_stop(). This will pause the + * scheduler workqueues and cancel the timeout work, guaranteeing + * that nothing is queued while the ring is being removed. + * 2. Remove the ring. The firmware will make sure that the + * corresponding parts of the hardware are resetted, and that other + * rings are not impacted. + * 3. Kill the entity and the associated scheduler. * - * 1. Stop the scheduler using drm_sched_stop(). This will park the - * scheduler thread and cancel the timeout work, guaranteeing that - * nothing is queued while we reset the hardware queue - * 2. Try to gracefully stop non-faulty jobs (optional) - * 3. Issue a GPU reset (driver-specific) - * 4. Re-submit jobs using drm_sched_resubmit_jobs() - * 5. Restart the scheduler using drm_sched_start(). At that point, new - * jobs can be queued, and the scheduler thread is unblocked + * + * For a HARDWARE SCHEDULER, a scheduler instance schedules jobs from + * one or more entities to one ring. This implies that all entities + * associated with the affected scheduler cannot be torn down, because + * this would effectively also affect innocent userspace processes which + * did not submit faulty jobs (for example). + * + * Consequently, the procedure to recover with a hardware scheduler + * should look like this: + * + * 1. Stop all schedulers impacted by the reset using drm_sched_stop(). + * 2. Kill the entity the faulty job stems from. + * 3. Issue a GPU reset on all faulty rings (driver-specific). + * 4. Re-submit jobs on all schedulers impacted by re-submitting them to + * the entities which are still alive. + * 5. Restart all schedulers that were stopped in step #1 using + * drm_sched_start(). * * Note that some GPUs have distinct hardware queues but need to reset * the GPU globally, which requires extra synchronization between the - * timeout handler of the different &drm_gpu_scheduler. One way to - * achieve this synchronization is to create an ordered workqueue - * (using alloc_ordered_workqueue()) at the driver level, and pass this - * queue to drm_sched_init(), to guarantee that timeout handlers are - * executed sequentially. The above workflow needs to be slightly - * adjusted in that case: - * - * 1. Stop all schedulers impacted by the reset using drm_sched_stop() - * 2. Try to gracefully stop non-faulty jobs on all queues impacted by - * the reset (optional) - * 3. Issue a GPU reset on all faulty queues (driver-specific) - * 4. Re-submit jobs on all schedulers impacted by the reset using - * drm_sched_resubmit_jobs() - * 5. Restart all schedulers that were stopped in step #1 using - * drm_sched_start() + * timeout handlers of different schedulers. One way to achieve this + * synchronization is to create an ordered workqueue (using + * alloc_ordered_workqueue()) at the driver level, and pass this queue + * as drm_sched_init()'s @timeout_wq parameter. This will guarantee + * that timeout handlers are executed sequentially. * - * Return DRM_GPU_SCHED_STAT_NOMINAL, when all is normal, - * and the underlying driver has started or completed recovery. + * Return: The scheduler's status, defined by &enum drm_gpu_sched_stat * - * Return DRM_GPU_SCHED_STAT_ENODEV, if the device is no longer - * available, i.e. has been unplugged. */ enum drm_gpu_sched_stat (*timedout_job)(struct drm_sched_job *sched_job); diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 36216d28d8bd..544f8f8c3f44 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -35,15 +35,6 @@ struct dma_buf_attachment; */ struct dma_buf_ops { /** - * @cache_sgt_mapping: - * - * If true the framework will cache the first mapping made for each - * attachment. This avoids creating mappings for attachments multiple - * times. - */ - bool cache_sgt_mapping; - - /** * @attach: * * This is called from dma_buf_attach() to make sure that a given @@ -493,8 +484,6 @@ struct dma_buf_attach_ops { * @dmabuf: buffer for this attachment. * @dev: device attached to the buffer. * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf. - * @sgt: cached mapping. - * @dir: direction of cached mapping. * @peer2peer: true if the importer can handle peer resources without pages. * @priv: exporter specific attachment data. * @importer_ops: importer operations for this attachment, if provided @@ -514,8 +503,6 @@ struct dma_buf_attachment { struct dma_buf *dmabuf; struct device *dev; struct list_head node; - struct sg_table *sgt; - enum dma_data_direction dir; bool peer2peer; const struct dma_buf_attach_ops *importer_ops; void *importer_priv; @@ -583,20 +570,6 @@ static inline bool dma_buf_is_dynamic(struct dma_buf *dmabuf) return !!dmabuf->ops->pin; } -/** - * dma_buf_attachment_is_dynamic - check if a DMA-buf attachment uses dynamic - * mappings - * @attach: the DMA-buf attachment to check - * - * Returns true if a DMA-buf importer wants to call the map/unmap functions with - * the dma_resv lock held. - */ -static inline bool -dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach) -{ - return !!attach->importer_ops; -} - struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf, struct device *dev); struct dma_buf_attachment * diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index e7ad819962e3..b12776883d14 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -169,8 +169,8 @@ struct dma_fence_ops { * implementation know that there is another driver waiting on the * signal (ie. hw->sw case). * - * This function can be called from atomic context, but not - * from irq context, so normal spinlocks can be used. + * This is called with irq's disabled, so only spinlocks which disable + * IRQ's can be used in the code outside of this callback. * * A return value of false indicates the fence already passed, * or some failure occurred that made it impossible to enable @@ -239,27 +239,6 @@ struct dma_fence_ops { void (*release)(struct dma_fence *fence); /** - * @fence_value_str: - * - * Callback to fill in free-form debug info specific to this fence, like - * the sequence number. - * - * This callback is optional. - */ - void (*fence_value_str)(struct dma_fence *fence, char *str, int size); - - /** - * @timeline_value_str: - * - * Fills in the current value of the timeline as a string, like the - * sequence number. Note that the specific fence passed to this function - * should not matter, drivers should only use it to look up the - * corresponding timeline structures. - */ - void (*timeline_value_str)(struct dma_fence *fence, - char *str, int size); - - /** * @set_deadline: * * Callback to allow a fence waiter to inform the fence signaler of diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index 6a4a3cec4638..923d68e07679 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -126,8 +126,17 @@ static inline unsigned int screen_info_video_type(const struct screen_info *si) return VIDEO_TYPE_CGA; } +static inline u32 __screen_info_vesapm_info_base(const struct screen_info *si) +{ + if (si->vesapm_seg < 0xc000) + return 0; + return (si->vesapm_seg << 4) + si->vesapm_off; +} + ssize_t screen_info_resources(const struct screen_info *si, struct resource *r, size_t num); +u32 __screen_info_lfb_bits_per_pixel(const struct screen_info *si); + #if defined(CONFIG_PCI) void screen_info_apply_fixups(void); struct pci_dev *screen_info_pci_dev(const struct screen_info *si); diff --git a/include/uapi/drm/asahi_drm.h b/include/uapi/drm/asahi_drm.h new file mode 100644 index 000000000000..de67f1c603af --- /dev/null +++ b/include/uapi/drm/asahi_drm.h @@ -0,0 +1,1194 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright (C) The Asahi Linux Contributors + * Copyright (C) 2018-2023 Collabora Ltd. + * Copyright (C) 2014-2018 Broadcom + */ +#ifndef _ASAHI_DRM_H_ +#define _ASAHI_DRM_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/** + * DOC: Introduction to the Asahi UAPI + * + * This documentation describes the Asahi IOCTLs. + * + * Just a few generic rules about the data passed to the Asahi IOCTLs (cribbed + * from Panthor): + * + * - Structures must be aligned on 64-bit/8-byte. If the object is not + * naturally aligned, a padding field must be added. + * - Fields must be explicitly aligned to their natural type alignment with + * pad[0..N] fields. + * - All padding fields will be checked by the driver to make sure they are + * zeroed. + * - Flags can be added, but not removed/replaced. + * - New fields can be added to the main structures (the structures + * directly passed to the ioctl). Those fields can be added at the end of + * the structure, or replace existing padding fields. Any new field being + * added must preserve the behavior that existed before those fields were + * added when a value of zero is passed. + * - New fields can be added to indirect objects (objects pointed by the + * main structure), iff those objects are passed a size to reflect the + * size known by the userspace driver (see + * drm_asahi_cmd_header::size). + * - If the kernel driver is too old to know some fields, those will be + * ignored if zero, and otherwise rejected (and so will be zero on output). + * - If userspace is too old to know some fields, those will be zeroed + * (input) before the structure is parsed by the kernel driver. + * - Each new flag/field addition must come with a driver version update so + * the userspace driver doesn't have to guess which flags are supported. + * - Structures should not contain unions, as this would defeat the + * extensibility of such structures. + * - IOCTLs can't be removed or replaced. New IOCTL IDs should be placed + * at the end of the drm_asahi_ioctl_id enum. + */ + +/** + * enum drm_asahi_ioctl_id - IOCTL IDs + * + * Place new ioctls at the end, don't re-order, don't replace or remove entries. + * + * These IDs are not meant to be used directly. Use the DRM_IOCTL_ASAHI_xxx + * definitions instead. + */ +enum drm_asahi_ioctl_id { + /** @DRM_ASAHI_GET_PARAMS: Query device properties. */ + DRM_ASAHI_GET_PARAMS = 0, + + /** @DRM_ASAHI_GET_TIME: Query device time. */ + DRM_ASAHI_GET_TIME, + + /** @DRM_ASAHI_VM_CREATE: Create a GPU VM address space. */ + DRM_ASAHI_VM_CREATE, + + /** @DRM_ASAHI_VM_DESTROY: Destroy a VM. */ + DRM_ASAHI_VM_DESTROY, + + /** @DRM_ASAHI_VM_BIND: Bind/unbind memory to a VM. */ + DRM_ASAHI_VM_BIND, + + /** @DRM_ASAHI_GEM_CREATE: Create a buffer object. */ + DRM_ASAHI_GEM_CREATE, + + /** + * @DRM_ASAHI_GEM_MMAP_OFFSET: Get offset to pass to mmap() to map a + * given GEM handle. + */ + DRM_ASAHI_GEM_MMAP_OFFSET, + + /** @DRM_ASAHI_GEM_BIND_OBJECT: Bind memory as a special object */ + DRM_ASAHI_GEM_BIND_OBJECT, + + /** @DRM_ASAHI_QUEUE_CREATE: Create a scheduling queue. */ + DRM_ASAHI_QUEUE_CREATE, + + /** @DRM_ASAHI_QUEUE_DESTROY: Destroy a scheduling queue. */ + DRM_ASAHI_QUEUE_DESTROY, + + /** @DRM_ASAHI_SUBMIT: Submit commands to a queue. */ + DRM_ASAHI_SUBMIT, +}; + +#define DRM_ASAHI_MAX_CLUSTERS 64 + +/** + * struct drm_asahi_params_global - Global parameters. + * + * This struct may be queried by drm_asahi_get_params. + */ +struct drm_asahi_params_global { + /** @features: Feature bits from drm_asahi_feature */ + __u64 features; + + /** @gpu_generation: GPU generation, e.g. 13 for G13G */ + __u32 gpu_generation; + + /** @gpu_variant: GPU variant as a character, e.g. 'C' for G13C */ + __u32 gpu_variant; + + /** + * @gpu_revision: GPU revision in BCD, e.g. 0x00 for 'A0' or + * 0x21 for 'C1' + */ + __u32 gpu_revision; + + /** @chip_id: Chip ID in BCD, e.g. 0x8103 for T8103 */ + __u32 chip_id; + + /** @num_dies: Number of dies in the SoC */ + __u32 num_dies; + + /** @num_clusters_total: Number of GPU clusters (across all dies) */ + __u32 num_clusters_total; + + /** + * @num_cores_per_cluster: Number of logical cores per cluster + * (including inactive/nonexistent) + */ + __u32 num_cores_per_cluster; + + /** @max_frequency_khz: Maximum GPU core clock frequency */ + __u32 max_frequency_khz; + + /** @core_masks: Bitmask of present/enabled cores per cluster */ + __u64 core_masks[DRM_ASAHI_MAX_CLUSTERS]; + + /** + * @vm_start: VM range start VMA. Together with @vm_end, this defines + * the window of valid GPU VAs. Userspace is expected to subdivide VAs + * out of this window. + * + * This window contains all virtual addresses that userspace needs to + * know about. There may be kernel-internal GPU VAs outside this range, + * but that detail is not relevant here. + */ + __u64 vm_start; + + /** @vm_end: VM range end VMA */ + __u64 vm_end; + + /** + * @vm_kernel_min_size: Minimum kernel VMA window size. + * + * When creating a VM, userspace is required to carve out a section of + * virtual addresses (within the range given by @vm_start and + * @vm_end). The kernel will allocate various internal structures + * within the specified VA range. + * + * Allowing userspace to choose the VA range for the kernel, rather than + * the kernel reserving VAs and requiring userspace to cope, can assist + * in implementing SVM. + */ + __u64 vm_kernel_min_size; + + /** + * @max_commands_per_submission: Maximum number of supported commands + * per submission. This mirrors firmware limits. Userspace must split up + * larger command buffers, which may require inserting additional + * synchronization. + */ + __u32 max_commands_per_submission; + + /** + * @max_attachments: Maximum number of drm_asahi_attachment's per + * command + */ + __u32 max_attachments; + + /** + * @command_timestamp_frequency_hz: Timebase frequency for timestamps + * written during command execution, specified via drm_asahi_timestamp + * structures. As this rate is controlled by the firmware, it is a + * queryable parameter. + * + * Userspace must divide by this frequency to convert timestamps to + * seconds, rather than hardcoding a particular firmware's rate. + */ + __u64 command_timestamp_frequency_hz; +}; + +/** + * enum drm_asahi_feature - Feature bits + * + * This covers only features that userspace cannot infer from the architecture + * version. Most features don't need to be here. + */ +enum drm_asahi_feature { + /** + * @DRM_ASAHI_FEATURE_SOFT_FAULTS: GPU has "soft fault" enabled. Shader + * loads of unmapped memory will return zero. Shader stores to unmapped + * memory will be silently discarded. Note that only shader load/store + * is affected. Other hardware units are not affected, notably including + * texture sampling. + * + * Soft fault is set when initializing the GPU and cannot be runtime + * toggled. Therefore, it is exposed as a feature bit and not a + * userspace-settable flag on the VM. When soft fault is enabled, + * userspace can speculate memory accesses more aggressively. + */ + DRM_ASAHI_FEATURE_SOFT_FAULTS = (1UL) << 0, +}; + +/** + * struct drm_asahi_get_params - Arguments passed to DRM_IOCTL_ASAHI_GET_PARAMS + */ +struct drm_asahi_get_params { + /** @param_group: Parameter group to fetch (MBZ) */ + __u32 param_group; + + /** @pad: MBZ */ + __u32 pad; + + /** @pointer: User pointer to write parameter struct */ + __u64 pointer; + + /** + * @size: Size of the user buffer. In case of older userspace, this may + * be less than sizeof(struct drm_asahi_params_global). The kernel will + * not write past the length specified here, allowing extensibility. + */ + __u64 size; +}; + +/** + * struct drm_asahi_vm_create - Arguments passed to DRM_IOCTL_ASAHI_VM_CREATE + */ +struct drm_asahi_vm_create { + /** + * @kernel_start: Start of the kernel-reserved address range. See + * drm_asahi_params_global::vm_kernel_min_size. + * + * Both @kernel_start and @kernel_end must be within the range of + * valid VAs given by drm_asahi_params_global::vm_start and + * drm_asahi_params_global::vm_end. The size of the kernel range + * (@kernel_end - @kernel_start) must be at least + * drm_asahi_params_global::vm_kernel_min_size. + * + * Userspace must not bind any memory on this VM into this reserved + * range, it is for kernel use only. + */ + __u64 kernel_start; + + /** + * @kernel_end: End of the kernel-reserved address range. See + * @kernel_start. + */ + __u64 kernel_end; + + /** @vm_id: Returned VM ID */ + __u32 vm_id; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * struct drm_asahi_vm_destroy - Arguments passed to DRM_IOCTL_ASAHI_VM_DESTROY + */ +struct drm_asahi_vm_destroy { + /** @vm_id: VM ID to be destroyed */ + __u32 vm_id; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * enum drm_asahi_gem_flags - Flags for GEM creation + */ +enum drm_asahi_gem_flags { + /** + * @DRM_ASAHI_GEM_WRITEBACK: BO should be CPU-mapped as writeback. + * + * Map as writeback instead of write-combine. This optimizes for CPU + * reads. + */ + DRM_ASAHI_GEM_WRITEBACK = (1L << 0), + + /** + * @DRM_ASAHI_GEM_VM_PRIVATE: BO is private to this GPU VM (no exports). + */ + DRM_ASAHI_GEM_VM_PRIVATE = (1L << 1), +}; + +/** + * struct drm_asahi_gem_create - Arguments passed to DRM_IOCTL_ASAHI_GEM_CREATE + */ +struct drm_asahi_gem_create { + /** @size: Size of the BO */ + __u64 size; + + /** @flags: Combination of drm_asahi_gem_flags flags. */ + __u32 flags; + + /** + * @vm_id: VM ID to assign to the BO, if DRM_ASAHI_GEM_VM_PRIVATE is set + */ + __u32 vm_id; + + /** @handle: Returned GEM handle for the BO */ + __u32 handle; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * struct drm_asahi_gem_mmap_offset - Arguments passed to + * DRM_IOCTL_ASAHI_GEM_MMAP_OFFSET + */ +struct drm_asahi_gem_mmap_offset { + /** @handle: Handle for the object being mapped. */ + __u32 handle; + + /** @flags: Must be zero */ + __u32 flags; + + /** @offset: The fake offset to use for subsequent mmap call */ + __u64 offset; +}; + +/** + * enum drm_asahi_bind_flags - Flags for GEM binding + */ +enum drm_asahi_bind_flags { + /** + * @DRM_ASAHI_BIND_UNBIND: Instead of binding a GEM object to the range, + * simply unbind the GPU VMA range. + */ + DRM_ASAHI_BIND_UNBIND = (1L << 0), + + /** @DRM_ASAHI_BIND_READ: Map BO with GPU read permission */ + DRM_ASAHI_BIND_READ = (1L << 1), + + /** @DRM_ASAHI_BIND_WRITE: Map BO with GPU write permission */ + DRM_ASAHI_BIND_WRITE = (1L << 2), + + /** + * @DRM_ASAHI_BIND_SINGLE_PAGE: Map a single page of the BO repeatedly + * across the VA range. + * + * This is useful to fill a VA range with scratch pages or zero pages. + * It is intended as a mechanism to accelerate sparse. + */ + DRM_ASAHI_BIND_SINGLE_PAGE = (1L << 3), +}; + +/** + * struct drm_asahi_gem_bind_op - Description of a single GEM bind operation. + */ +struct drm_asahi_gem_bind_op { + /** @flags: Combination of drm_asahi_bind_flags flags. */ + __u32 flags; + + /** @handle: GEM object to bind (except for UNBIND) */ + __u32 handle; + + /** + * @offset: Offset into the object (except for UNBIND). + * + * For a regular bind, this is the beginning of the region of the GEM + * object to bind. + * + * For a single-page bind, this is the offset to the single page that + * will be repeatedly bound. + * + * Must be page-size aligned. + */ + __u64 offset; + + /** + * @range: Number of bytes to bind/unbind to @addr. + * + * Must be page-size aligned. + */ + __u64 range; + + /** + * @addr: Address to bind to. + * + * Must be page-size aligned. + */ + __u64 addr; +}; + +/** + * struct drm_asahi_vm_bind - Arguments passed to + * DRM_IOCTL_ASAHI_VM_BIND + */ +struct drm_asahi_vm_bind { + /** @vm_id: The ID of the VM to bind to */ + __u32 vm_id; + + /** @num_binds: number of binds in this IOCTL. */ + __u32 num_binds; + + /** + * @stride: Stride in bytes between consecutive binds. This allows + * extensibility of drm_asahi_gem_bind_op. + */ + __u32 stride; + + /** @pad: MBZ */ + __u32 pad; + + /** + * @userptr: User pointer to an array of @num_binds structures of type + * @drm_asahi_gem_bind_op and size @stride bytes. + */ + __u64 userptr; +}; + +/** + * enum drm_asahi_bind_object_op - Special object bind operation + */ +enum drm_asahi_bind_object_op { + /** @DRM_ASAHI_BIND_OBJECT_OP_BIND: Bind a BO as a special GPU object */ + DRM_ASAHI_BIND_OBJECT_OP_BIND = 0, + + /** @DRM_ASAHI_BIND_OBJECT_OP_UNBIND: Unbind a special GPU object */ + DRM_ASAHI_BIND_OBJECT_OP_UNBIND = 1, +}; + +/** + * enum drm_asahi_bind_object_flags - Special object bind flags + */ +enum drm_asahi_bind_object_flags { + /** + * @DRM_ASAHI_BIND_OBJECT_USAGE_TIMESTAMPS: Map a BO as a timestamp + * buffer. + */ + DRM_ASAHI_BIND_OBJECT_USAGE_TIMESTAMPS = (1L << 0), +}; + +/** + * struct drm_asahi_gem_bind_object - Arguments passed to + * DRM_IOCTL_ASAHI_GEM_BIND_OBJECT + */ +struct drm_asahi_gem_bind_object { + /** @op: Bind operation (enum drm_asahi_bind_object_op) */ + __u32 op; + + /** @flags: Combination of drm_asahi_bind_object_flags flags. */ + __u32 flags; + + /** @handle: GEM object to bind/unbind (BIND) */ + __u32 handle; + + /** @vm_id: The ID of the VM to operate on (MBZ currently) */ + __u32 vm_id; + + /** @offset: Offset into the object (BIND only) */ + __u64 offset; + + /** @range: Number of bytes to bind/unbind (BIND only) */ + __u64 range; + + /** @object_handle: Object handle (out for BIND, in for UNBIND) */ + __u32 object_handle; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * enum drm_asahi_cmd_type - Command type + */ +enum drm_asahi_cmd_type { + /** + * @DRM_ASAHI_CMD_RENDER: Render command, executing on the render + * subqueue. Combined vertex and fragment operation. + * + * Followed by a @drm_asahi_cmd_render payload. + */ + DRM_ASAHI_CMD_RENDER = 0, + + /** + * @DRM_ASAHI_CMD_COMPUTE: Compute command on the compute subqueue. + * + * Followed by a @drm_asahi_cmd_compute payload. + */ + DRM_ASAHI_CMD_COMPUTE = 1, + + /** + * @DRM_ASAHI_SET_VERTEX_ATTACHMENTS: Software command to set + * attachments for subsequent vertex shaders in the same submit. + * + * Followed by (possibly multiple) @drm_asahi_attachment payloads. + */ + DRM_ASAHI_SET_VERTEX_ATTACHMENTS = 2, + + /** + * @DRM_ASAHI_SET_FRAGMENT_ATTACHMENTS: Software command to set + * attachments for subsequent fragment shaders in the same submit. + * + * Followed by (possibly multiple) @drm_asahi_attachment payloads. + */ + DRM_ASAHI_SET_FRAGMENT_ATTACHMENTS = 3, + + /** + * @DRM_ASAHI_SET_COMPUTE_ATTACHMENTS: Software command to set + * attachments for subsequent compute shaders in the same submit. + * + * Followed by (possibly multiple) @drm_asahi_attachment payloads. + */ + DRM_ASAHI_SET_COMPUTE_ATTACHMENTS = 4, +}; + +/** + * enum drm_asahi_priority - Scheduling queue priority. + * + * These priorities are forwarded to the firmware to influence firmware + * scheduling. The exact policy is ultimately decided by firmware, but + * these enums allow userspace to communicate the intentions. + */ +enum drm_asahi_priority { + /** @DRM_ASAHI_PRIORITY_LOW: Low priority queue. */ + DRM_ASAHI_PRIORITY_LOW = 0, + + /** @DRM_ASAHI_PRIORITY_MEDIUM: Medium priority queue. */ + DRM_ASAHI_PRIORITY_MEDIUM = 1, + + /** + * @DRM_ASAHI_PRIORITY_HIGH: High priority queue. + * + * Reserved for future extension. + */ + DRM_ASAHI_PRIORITY_HIGH = 2, + + /** + * @DRM_ASAHI_PRIORITY_REALTIME: Real-time priority queue. + * + * Reserved for future extension. + */ + DRM_ASAHI_PRIORITY_REALTIME = 3, +}; + +/** + * struct drm_asahi_queue_create - Arguments passed to + * DRM_IOCTL_ASAHI_QUEUE_CREATE + */ +struct drm_asahi_queue_create { + /** @flags: MBZ */ + __u32 flags; + + /** @vm_id: The ID of the VM this queue is bound to */ + __u32 vm_id; + + /** @priority: One of drm_asahi_priority */ + __u32 priority; + + /** @queue_id: The returned queue ID */ + __u32 queue_id; + + /** + * @usc_exec_base: GPU base address for all USC binaries (shaders) on + * this queue. USC addresses are 32-bit relative to this 64-bit base. + * + * This sets the following registers on all queue commands: + * + * USC_EXEC_BASE_TA (vertex) + * USC_EXEC_BASE_ISP (fragment) + * USC_EXEC_BASE_CP (compute) + * + * While the hardware lets us configure these independently per command, + * we do not have a use case for this. Instead, we expect userspace to + * fix a 4GiB VA carveout for USC memory and pass its base address here. + */ + __u64 usc_exec_base; +}; + +/** + * struct drm_asahi_queue_destroy - Arguments passed to + * DRM_IOCTL_ASAHI_QUEUE_DESTROY + */ +struct drm_asahi_queue_destroy { + /** @queue_id: The queue ID to be destroyed */ + __u32 queue_id; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * enum drm_asahi_sync_type - Sync item type + */ +enum drm_asahi_sync_type { + /** @DRM_ASAHI_SYNC_SYNCOBJ: Binary sync object */ + DRM_ASAHI_SYNC_SYNCOBJ = 0, + + /** @DRM_ASAHI_SYNC_TIMELINE_SYNCOBJ: Timeline sync object */ + DRM_ASAHI_SYNC_TIMELINE_SYNCOBJ = 1, +}; + +/** + * struct drm_asahi_sync - Sync item + */ +struct drm_asahi_sync { + /** @sync_type: One of drm_asahi_sync_type */ + __u32 sync_type; + + /** @handle: The sync object handle */ + __u32 handle; + + /** @timeline_value: Timeline value for timeline sync objects */ + __u64 timeline_value; +}; + +/** + * define DRM_ASAHI_BARRIER_NONE - Command index for no barrier + * + * This special value may be passed in to drm_asahi_command::vdm_barrier or + * drm_asahi_command::cdm_barrier to indicate that the respective subqueue + * should not wait on any previous work. + */ +#define DRM_ASAHI_BARRIER_NONE (0xFFFFu) + +/** + * struct drm_asahi_cmd_header - Top level command structure + * + * This struct is core to the command buffer definition and therefore is not + * extensible. + */ +struct drm_asahi_cmd_header { + /** @cmd_type: One of drm_asahi_cmd_type */ + __u16 cmd_type; + + /** + * @size: Size of this command, not including this header. + * + * For hardware commands, this enables extensibility of commands without + * requiring extra command types. Passing a command that is shorter + * than expected is explicitly allowed for backwards-compatibility. + * Truncated fields will be zeroed. + * + * For the synthetic attachment setting commands, this implicitly + * encodes the number of attachments. These commands take multiple + * fixed-size @drm_asahi_attachment structures as their payload, so size + * equals number of attachments * sizeof(struct drm_asahi_attachment). + */ + __u16 size; + + /** + * @vdm_barrier: VDM (render) command index to wait on. + * + * Barriers are indices relative to the beginning of a given submit. A + * barrier of 0 waits on commands submitted to the respective subqueue + * in previous submit ioctls. A barrier of N waits on N previous + * commands on the subqueue within the current submit ioctl. As a + * special case, passing @DRM_ASAHI_BARRIER_NONE avoids waiting on any + * commands in the subqueue. + * + * Examples: + * + * 0: This waits on all previous work. + * + * NONE: This does not wait for anything on this subqueue. + * + * 1: This waits on the first render command in the submit. + * This is valid only if there are multiple render commands in the + * same submit. + * + * Barriers are valid only for hardware commands. Synthetic software + * commands to set attachments must pass NONE here. + */ + __u16 vdm_barrier; + + /** + * @cdm_barrier: CDM (compute) command index to wait on. + * + * See @vdm_barrier, and replace VDM/render with CDM/compute. + */ + __u16 cdm_barrier; +}; + +/** + * struct drm_asahi_submit - Arguments passed to DRM_IOCTL_ASAHI_SUBMIT + */ +struct drm_asahi_submit { + /** + * @syncs: An optional pointer to an array of drm_asahi_sync. The first + * @in_sync_count elements are in-syncs, then the remaining + * @out_sync_count elements are out-syncs. Using a single array with + * explicit partitioning simplifies handling. + */ + __u64 syncs; + + /** + * @cmdbuf: Pointer to the command buffer to submit. + * + * This is a flat command buffer. By design, it contains no CPU + * pointers, which makes it suitable for a virtgpu wire protocol without + * requiring any serializing/deserializing step. + * + * It consists of a series of commands. Each command begins with a + * fixed-size @drm_asahi_cmd_header header and is followed by a + * variable-length payload according to the type and size in the header. + * + * The combined count of "real" hardware commands must be nonzero and at + * most drm_asahi_params_global::max_commands_per_submission. + */ + __u64 cmdbuf; + + /** @flags: Flags for command submission (MBZ) */ + __u32 flags; + + /** @queue_id: The queue ID to be submitted to */ + __u32 queue_id; + + /** + * @in_sync_count: Number of sync objects to wait on before starting + * this job. + */ + __u32 in_sync_count; + + /** + * @out_sync_count: Number of sync objects to signal upon completion of + * this job. + */ + __u32 out_sync_count; + + /** @cmdbuf_size: Command buffer size in bytes */ + __u32 cmdbuf_size; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * struct drm_asahi_attachment - Describe an "attachment". + * + * Attachments are any memory written by shaders, notably including render + * target attachments written by the end-of-tile program. This is purely a hint + * about the accessed memory regions. It is optional to specify, which is + * fortunate as it cannot be specified precisely with bindless access anyway. + * But where possible, it's probably a good idea for userspace to include these + * hints, forwarded to the firmware. + * + * This struct is implicitly sized and therefore is not extensible. + */ +struct drm_asahi_attachment { + /** @pointer: Base address of the attachment */ + __u64 pointer; + + /** @size: Size of the attachment in bytes */ + __u64 size; + + /** @pad: MBZ */ + __u32 pad; + + /** @flags: MBZ */ + __u32 flags; +}; + +enum drm_asahi_render_flags { + /** + * @DRM_ASAHI_RENDER_VERTEX_SCRATCH: A vertex stage shader uses scratch + * memory. + */ + DRM_ASAHI_RENDER_VERTEX_SCRATCH = (1U << 0), + + /** + * @DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES: Process even empty tiles. + * This must be set when clearing render targets. + */ + DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES = (1U << 1), + + /** + * @DRM_ASAHI_RENDER_NO_VERTEX_CLUSTERING: Run vertex stage on a single + * cluster (on multi-cluster GPUs) + * + * This harms performance but can workaround certain sync/coherency + * bugs, and therefore is useful for debugging. + */ + DRM_ASAHI_RENDER_NO_VERTEX_CLUSTERING = (1U << 2), + + /** + * @DRM_ASAHI_RENDER_DBIAS_IS_INT: Use integer depth bias formula. + * + * Graphics specifications contain two alternate formulas for depth + * bias, a float formula used with floating-point depth buffers and an + * integer formula using with unorm depth buffers. This flag specifies + * that the integer formula should be used. If omitted, the float + * formula is used instead. + * + * This corresponds to bit 18 of the relevant hardware control register, + * so we match that here for efficiency. + */ + DRM_ASAHI_RENDER_DBIAS_IS_INT = (1U << 18), +}; + +/** + * struct drm_asahi_zls_buffer - Describe a depth or stencil buffer. + * + * These fields correspond to hardware registers in the ZLS (Z Load/Store) unit. + * There are three hardware registers for each field respectively for loads, + * stores, and partial renders. In practice, it makes sense to set all to the + * same values, except in exceptional cases not yet implemented in userspace, so + * we do not duplicate here for simplicity/efficiency. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_zls_buffer { + /** @base: Base address of the buffer */ + __u64 base; + + /** + * @comp_base: If the load buffer is compressed, address of the + * compression metadata section. + */ + __u64 comp_base; + + /** + * @stride: If layered rendering is enabled, the number of bytes + * between each layer of the buffer. + */ + __u32 stride; + + /** + * @comp_stride: If layered rendering is enabled, the number of bytes + * between each layer of the compression metadata. + */ + __u32 comp_stride; +}; + +/** + * struct drm_asahi_timestamp - Describe a timestamp write. + * + * The firmware can optionally write the GPU timestamp at render pass + * granularities, but it needs to be mapped specially via + * DRM_IOCTL_ASAHI_GEM_BIND_OBJECT. This structure therefore describes where to + * write as a handle-offset pair, rather than a GPU address like normal. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_timestamp { + /** + * @handle: Handle of the timestamp buffer, or 0 to skip this + * timestamp. If nonzero, this must equal the value returned in + * drm_asahi_gem_bind_object::object_handle. + */ + __u32 handle; + + /** @offset: Offset to write into the timestamp buffer */ + __u32 offset; +}; + +/** + * struct drm_asahi_timestamps - Describe timestamp writes. + * + * Each operation that can be timestamped, can be timestamped at the start and + * end. Therefore, drm_asahi_timestamp structs always come in pairs, bundled + * together into drm_asahi_timestamps. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_timestamps { + /** @start: Timestamp recorded at the start of the operation */ + struct drm_asahi_timestamp start; + + /** @end: Timestamp recorded at the end of the operation */ + struct drm_asahi_timestamp end; +}; + +/** + * struct drm_asahi_helper_program - Describe helper program configuration. + * + * The helper program is a compute-like kernel required for various hardware + * functionality. Its most important role is dynamically allocating + * scratch/stack memory for individual subgroups, by partitioning a static + * allocation shared for the whole device. It is supplied by userspace via + * drm_asahi_helper_program and internally dispatched by the hardware as needed. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_helper_program { + /** + * @binary: USC address to the helper program binary. This is a tagged + * pointer with configuration in the bottom bits. + */ + __u32 binary; + + /** @cfg: Additional configuration bits for the helper program. */ + __u32 cfg; + + /** + * @data: Data passed to the helper program. This value is not + * interpreted by the kernel, firmware, or hardware in any way. It is + * simply a sideband for userspace, set with the submit ioctl and read + * via special registers inside the helper program. + * + * In practice, userspace will pass a 64-bit GPU VA here pointing to the + * actual arguments, which presumably don't fit in 64-bits. + */ + __u64 data; +}; + +/** + * struct drm_asahi_bg_eot - Describe a background or end-of-tile program. + * + * The background and end-of-tile programs are dispatched by the hardware at the + * beginning and end of rendering. As the hardware "tilebuffer" is simply local + * memory, these programs are necessary to implement API-level render targets. + * The fragment-like background program is responsible for loading either the + * clear colour or the existing render target contents, while the compute-like + * end-of-tile program stores the tilebuffer contents to memory. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_bg_eot { + /** + * @usc: USC address of the hardware USC words binding resources + * (including images and uniforms) and the program itself. Note this is + * an additional layer of indirection compared to the helper program, + * avoiding the need for a sideband for data. This is a tagged pointer + * with additional configuration in the bottom bits. + */ + __u32 usc; + + /** + * @rsrc_spec: Resource specifier for the program. This is a packed + * hardware data structure describing the required number of registers, + * uniforms, bound textures, and bound samplers. + */ + __u32 rsrc_spec; +}; + +/** + * struct drm_asahi_cmd_render - Command to submit 3D + * + * This command submits a single render pass. The hardware control stream may + * include many draws and subpasses, but within the command, the framebuffer + * dimensions and attachments are fixed. + * + * The hardware requires the firmware to set a large number of Control Registers + * setting up state at render pass granularity before each command rendering 3D. + * The firmware bundles this state into data structures. Unfortunately, we + * cannot expose either any of that directly to userspace, because the + * kernel-firmware ABI is not stable. Although we can guarantee the firmware + * updates in tandem with the kernel, we cannot break old userspace when + * upgrading the firmware and kernel. Therefore, we need to abstract well the + * data structures to avoid tying our hands with future firmwares. + * + * The bulk of drm_asahi_cmd_render therefore consists of values of hardware + * control registers, marshalled via the firmware interface. + * + * The framebuffer/tilebuffer dimensions are also specified here. In addition to + * being passed to the firmware/hardware, the kernel requires these dimensions + * to calculate various essential tiling-related data structures. It is + * unfortunate that our submits are heavier than on vendors with saner + * hardware-software interfaces. The upshot is all of this information is + * readily available to userspace with all current APIs. + * + * It looks odd - but it's not overly burdensome and it ensures we can remain + * compatible with old userspace. + */ +struct drm_asahi_cmd_render { + /** @flags: Combination of drm_asahi_render_flags flags. */ + __u32 flags; + + /** + * @isp_zls_pixels: ISP_ZLS_PIXELS register value. This contains the + * depth/stencil width/height, which may differ from the framebuffer + * width/height. + */ + __u32 isp_zls_pixels; + + /** + * @vdm_ctrl_stream_base: VDM_CTRL_STREAM_BASE register value. GPU + * address to the beginning of the VDM control stream. + */ + __u64 vdm_ctrl_stream_base; + + /** @vertex_helper: Helper program used for the vertex shader */ + struct drm_asahi_helper_program vertex_helper; + + /** @fragment_helper: Helper program used for the fragment shader */ + struct drm_asahi_helper_program fragment_helper; + + /** + * @isp_scissor_base: ISP_SCISSOR_BASE register value. GPU address of an + * array of scissor descriptors indexed in the render pass. + */ + __u64 isp_scissor_base; + + /** + * @isp_dbias_base: ISP_DBIAS_BASE register value. GPU address of an + * array of depth bias values indexed in the render pass. + */ + __u64 isp_dbias_base; + + /** + * @isp_oclqry_base: ISP_OCLQRY_BASE register value. GPU address of an + * array of occlusion query results written by the render pass. + */ + __u64 isp_oclqry_base; + + /** @depth: Depth buffer */ + struct drm_asahi_zls_buffer depth; + + /** @stencil: Stencil buffer */ + struct drm_asahi_zls_buffer stencil; + + /** @zls_ctrl: ZLS_CTRL register value */ + __u64 zls_ctrl; + + /** @ppp_multisamplectl: PPP_MULTISAMPLECTL register value */ + __u64 ppp_multisamplectl; + + /** + * @sampler_heap: Base address of the sampler heap. This heap is used + * for both vertex shaders and fragment shaders. The registers are + * per-stage, but there is no known use case for separate heaps. + */ + __u64 sampler_heap; + + /** @ppp_ctrl: PPP_CTRL register value */ + __u32 ppp_ctrl; + + /** @width_px: Framebuffer width in pixels */ + __u16 width_px; + + /** @height_px: Framebuffer height in pixels */ + __u16 height_px; + + /** @layers: Number of layers in the framebuffer */ + __u16 layers; + + /** @sampler_count: Number of samplers in the sampler heap. */ + __u16 sampler_count; + + /** @utile_width_px: Width of a logical tilebuffer tile in pixels */ + __u8 utile_width_px; + + /** @utile_height_px: Height of a logical tilebuffer tile in pixels */ + __u8 utile_height_px; + + /** @samples: # of samples in the framebuffer. Must be 1, 2, or 4. */ + __u8 samples; + + /** @sample_size_B: # of bytes in the tilebuffer required per sample. */ + __u8 sample_size_B; + + /** + * @isp_merge_upper_x: 32-bit float used in the hardware triangle + * merging. Calculate as: tan(60 deg) * width. + * + * Making these values UAPI avoids requiring floating-point calculations + * in the kernel in the hot path. + */ + __u32 isp_merge_upper_x; + + /** + * @isp_merge_upper_y: 32-bit float. Calculate as: tan(60 deg) * height. + * See @isp_merge_upper_x. + */ + __u32 isp_merge_upper_y; + + /** @bg: Background program run for each tile at the start */ + struct drm_asahi_bg_eot bg; + + /** @eot: End-of-tile program ran for each tile at the end */ + struct drm_asahi_bg_eot eot; + + /** + * @partial_bg: Background program ran at the start of each tile when + * resuming the render pass during a partial render. + */ + struct drm_asahi_bg_eot partial_bg; + + /** + * @partial_eot: End-of-tile program ran at the end of each tile when + * pausing the render pass during a partial render. + */ + struct drm_asahi_bg_eot partial_eot; + + /** + * @isp_bgobjdepth: ISP_BGOBJDEPTH register value. This is the depth + * buffer clear value, encoded in the depth buffer's format: either a + * 32-bit float or a 16-bit unorm (with upper bits zeroed). + */ + __u32 isp_bgobjdepth; + + /** + * @isp_bgobjvals: ISP_BGOBJVALS register value. The bottom 8-bits + * contain the stencil buffer clear value. + */ + __u32 isp_bgobjvals; + + /** @ts_vtx: Timestamps for the vertex portion of the render */ + struct drm_asahi_timestamps ts_vtx; + + /** @ts_frag: Timestamps for the fragment portion of the render */ + struct drm_asahi_timestamps ts_frag; +}; + +/** + * struct drm_asahi_cmd_compute - Command to submit compute + * + * This command submits a control stream consisting of compute dispatches. There + * is essentially no limit on how many compute dispatches may be included in a + * single compute command, although timestamps are at command granularity. + */ +struct drm_asahi_cmd_compute { + /** @flags: MBZ */ + __u32 flags; + + /** @sampler_count: Number of samplers in the sampler heap. */ + __u32 sampler_count; + + /** + * @cdm_ctrl_stream_base: CDM_CTRL_STREAM_BASE register value. GPU + * address to the beginning of the CDM control stream. + */ + __u64 cdm_ctrl_stream_base; + + /** + * @cdm_ctrl_stream_end: GPU base address to the end of the hardware + * control stream. Note this only considers the first contiguous segment + * of the control stream, as the stream might jump elsewhere. + */ + __u64 cdm_ctrl_stream_end; + + /** @sampler_heap: Base address of the sampler heap. */ + __u64 sampler_heap; + + /** @helper: Helper program used for this compute command */ + struct drm_asahi_helper_program helper; + + /** @ts: Timestamps for the compute command */ + struct drm_asahi_timestamps ts; +}; + +/** + * struct drm_asahi_get_time - Arguments passed to DRM_IOCTL_ASAHI_GET_TIME + */ +struct drm_asahi_get_time { + /** @flags: MBZ. */ + __u64 flags; + + /** @gpu_timestamp: On return, the GPU timestamp in nanoseconds. */ + __u64 gpu_timestamp; +}; + +/** + * DRM_IOCTL_ASAHI() - Build an Asahi IOCTL number + * @__access: Access type. Must be R, W or RW. + * @__id: One of the DRM_ASAHI_xxx id. + * @__type: Suffix of the type being passed to the IOCTL. + * + * Don't use this macro directly, use the DRM_IOCTL_ASAHI_xxx + * values instead. + * + * Return: An IOCTL number to be passed to ioctl() from userspace. + */ +#define DRM_IOCTL_ASAHI(__access, __id, __type) \ + DRM_IO ## __access(DRM_COMMAND_BASE + DRM_ASAHI_ ## __id, \ + struct drm_asahi_ ## __type) + +/* Note: this is an enum so that it can be resolved by Rust bindgen. */ +enum { + DRM_IOCTL_ASAHI_GET_PARAMS = DRM_IOCTL_ASAHI(W, GET_PARAMS, get_params), + DRM_IOCTL_ASAHI_GET_TIME = DRM_IOCTL_ASAHI(WR, GET_TIME, get_time), + DRM_IOCTL_ASAHI_VM_CREATE = DRM_IOCTL_ASAHI(WR, VM_CREATE, vm_create), + DRM_IOCTL_ASAHI_VM_DESTROY = DRM_IOCTL_ASAHI(W, VM_DESTROY, vm_destroy), + DRM_IOCTL_ASAHI_VM_BIND = DRM_IOCTL_ASAHI(W, VM_BIND, vm_bind), + DRM_IOCTL_ASAHI_GEM_CREATE = DRM_IOCTL_ASAHI(WR, GEM_CREATE, gem_create), + DRM_IOCTL_ASAHI_GEM_MMAP_OFFSET = DRM_IOCTL_ASAHI(WR, GEM_MMAP_OFFSET, gem_mmap_offset), + DRM_IOCTL_ASAHI_GEM_BIND_OBJECT = DRM_IOCTL_ASAHI(WR, GEM_BIND_OBJECT, gem_bind_object), + DRM_IOCTL_ASAHI_QUEUE_CREATE = DRM_IOCTL_ASAHI(WR, QUEUE_CREATE, queue_create), + DRM_IOCTL_ASAHI_QUEUE_DESTROY = DRM_IOCTL_ASAHI(W, QUEUE_DESTROY, queue_destroy), + DRM_IOCTL_ASAHI_SUBMIT = DRM_IOCTL_ASAHI(W, SUBMIT, submit), +}; + +#if defined(__cplusplus) +} +#endif + +#endif /* _ASAHI_DRM_H_ */ diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 7fba37b94401..e63a71d3c607 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -905,13 +905,17 @@ struct drm_syncobj_destroy { }; #define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE (1 << 1) #define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_TIMELINE (1 << 1) struct drm_syncobj_handle { __u32 handle; __u32 flags; __s32 fd; __u32 pad; + + __u64 point; }; struct drm_syncobj_transfer { diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index e41a3cec6a9e..81202a50dc9e 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -422,6 +422,7 @@ extern "C" { #define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09 #define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a #define DRM_FORMAT_MOD_VENDOR_MTK 0x0b +#define DRM_FORMAT_MOD_VENDOR_APPLE 0x0c /* add more to the end as needed */ @@ -1495,6 +1496,50 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) #define DRM_FORMAT_MOD_MTK_16L_32S_TILE DRM_FORMAT_MOD_MTK(MTK_FMT_MOD_TILE_16L32S) /* + * Apple GPU-tiled layouts. + * + * Apple GPUs support nonlinear tilings with optional lossless compression. + * + * GPU-tiled images are divided into 16KiB tiles: + * + * Bytes per pixel Tile size + * --------------- --------- + * 1 128x128 + * 2 128x64 + * 4 64x64 + * 8 64x32 + * 16 32x32 + * + * Tiles are raster-order. Pixels within a tile are interleaved (Morton order). + * + * Compressed images pad the body to 128-bytes and are immediately followed by a + * metadata section. The metadata section rounds the image dimensions to + * powers-of-two and contains 8 bytes for each 16x16 compression subtile. + * Subtiles are interleaved (Morton order). + * + * All images are 128-byte aligned. + * + * These layouts fundamentally do not have meaningful strides. No matter how we + * specify strides for these layouts, userspace unaware of Apple image layouts + * will be unable to use correctly the specified stride for any purpose. + * Userspace aware of the image layouts do not use strides. The most "correct" + * convention would be setting the image stride to 0. Unfortunately, some + * software assumes the stride is at least (width * bytes per pixel). We + * therefore require that stride equals (width * bytes per pixel). Since the + * stride is arbitrary here, we pick the simplest convention. + * + * Although containing two sections, compressed image layouts are treated in + * software as a single plane. This is modelled after AFBC, a similar + * scheme. Attempting to separate the sections to be "explicit" in DRM would + * only generate more confusion, as software does not treat the image this way. + * + * For detailed information on the hardware image layouts, see + * https://docs.mesa3d.org/drivers/asahi.html#image-layouts + */ +#define DRM_FORMAT_MOD_APPLE_GPU_TILED fourcc_mod_code(APPLE, 1) +#define DRM_FORMAT_MOD_APPLE_GPU_TILED_COMPRESSED fourcc_mod_code(APPLE, 2) + +/* * AMD modifiers * * Memory layout: diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index c2ce71987e9b..9debb320c34b 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -163,6 +163,12 @@ struct drm_virtgpu_3d_wait { __u32 flags; }; +#define VIRTGPU_DRM_CAPSET_VIRGL 1 +#define VIRTGPU_DRM_CAPSET_VIRGL2 2 +#define VIRTGPU_DRM_CAPSET_GFXSTREAM_VULKAN 3 +#define VIRTGPU_DRM_CAPSET_VENUS 4 +#define VIRTGPU_DRM_CAPSET_CROSS_DOMAIN 5 +#define VIRTGPU_DRM_CAPSET_DRM 6 struct drm_virtgpu_get_caps { __u32 cap_set_id; __u32 cap_set_ver; diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index bf2c9cabd207..be109777d10d 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -309,8 +309,9 @@ struct virtio_gpu_cmd_submit { #define VIRTIO_GPU_CAPSET_VIRGL 1 #define VIRTIO_GPU_CAPSET_VIRGL2 2 -/* 3 is reserved for gfxstream */ +#define VIRTIO_GPU_CAPSET_GFXSTREAM_VULKAN 3 #define VIRTIO_GPU_CAPSET_VENUS 4 +#define VIRTIO_GPU_CAPSET_CROSS_DOMAIN 5 #define VIRTIO_GPU_CAPSET_DRM 6 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ diff --git a/include/video/pixel_format.h b/include/video/pixel_format.h new file mode 100644 index 000000000000..b5104b2a3a13 --- /dev/null +++ b/include/video/pixel_format.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef VIDEO_PIXEL_FORMAT_H +#define VIDEO_PIXEL_FORMAT_H + +struct pixel_format { + unsigned char bits_per_pixel; + bool indexed; + union { + struct { + struct { + unsigned char offset; + unsigned char length; + } alpha, red, green, blue; + }; + struct { + unsigned char offset; + unsigned char length; + } index; + }; +}; + +#define PIXEL_FORMAT_XRGB1555 \ + { 16, false, { .alpha = {0, 0}, .red = {10, 5}, .green = {5, 5}, .blue = {0, 5} } } + +#define PIXEL_FORMAT_RGB565 \ + { 16, false, { .alpha = {0, 0}, .red = {11, 5}, .green = {5, 6}, .blue = {0, 5} } } + +#define PIXEL_FORMAT_RGB888 \ + { 24, false, { .alpha = {0, 0}, .red = {16, 8}, .green = {8, 8}, .blue = {0, 8} } } + +#define PIXEL_FORMAT_XRGB8888 \ + { 32, false, { .alpha = {0, 0}, .red = {16, 8}, .green = {8, 8}, .blue = {0, 8} } } + +#define PIXEL_FORMAT_XBGR8888 \ + { 32, false, { .alpha = {0, 0}, .red = {0, 8}, .green = {8, 8}, .blue = {16, 8} } } + +#define PIXEL_FORMAT_XRGB2101010 \ + { 32, false, { .alpha = {0, 0}, .red = {20, 10}, .green = {10, 10}, .blue = {0, 10} } } + +#endif |
