diff options
Diffstat (limited to 'drivers')
92 files changed, 5232 insertions, 475 deletions
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index 807a88a0f394..9d75ead2a1f9 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -1164,7 +1164,8 @@ static bool acpi_video_device_in_dod(struct acpi_video_device *device) return true; for (i = 0; i < video->attached_count; i++) { - if (video->attached_array[i].bind_info == device) + if ((video->attached_array[i].value.int_val & 0xfff) == + (device->device_id & 0xfff)) return true; } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index e45f83789809..49f1e6890587 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -321,6 +321,9 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x8c87), board_ahci }, /* 9 Series RAID */ { PCI_VDEVICE(INTEL, 0x8c8e), board_ahci }, /* 9 Series RAID */ { PCI_VDEVICE(INTEL, 0x8c8f), board_ahci }, /* 9 Series RAID */ + { PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */ + { PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */ { PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */ @@ -492,6 +495,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { * enabled. https://bugzilla.kernel.org/show_bug.cgi?id=60731 */ { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_nomsi }, + { PCI_VDEVICE(SAMSUNG, 0xa800), board_ahci_nomsi }, /* Enmotus */ { PCI_DEVICE(0x1c44, 0x8000), board_ahci }, diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 07bc7e4dbd04..65071591b143 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1488,7 +1488,7 @@ static int sata_fsl_probe(struct platform_device *ofdev) host_priv->csr_base = csr_base; irq = irq_of_parse_and_map(ofdev->dev.of_node, 0); - if (irq < 0) { + if (!irq) { dev_err(&ofdev->dev, "invalid irq from platform\n"); goto error_exit_with_cleanup; } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 24c2d7caedd5..c3413b6adb17 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -167,6 +167,8 @@ config DRM_SAVAGE source "drivers/gpu/drm/exynos/Kconfig" +source "drivers/gpu/drm/rockchip/Kconfig" + source "drivers/gpu/drm/vmwgfx/Kconfig" source "drivers/gpu/drm/gma500/Kconfig" diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 47d89869c5df..66e40398b3d3 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -49,6 +49,7 @@ obj-$(CONFIG_DRM_VMWGFX)+= vmwgfx/ obj-$(CONFIG_DRM_VIA) +=via/ obj-$(CONFIG_DRM_NOUVEAU) +=nouveau/ obj-$(CONFIG_DRM_EXYNOS) +=exynos/ +obj-$(CONFIG_DRM_ROCKCHIP) +=rockchip/ obj-$(CONFIG_DRM_GMA500) += gma500/ obj-$(CONFIG_DRM_UDL) += udl/ obj-$(CONFIG_DRM_AST) += ast/ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 102cd36799b1..4f7b275f2f7b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -102,15 +102,26 @@ struct device *kfd_chardev(void) static int kfd_open(struct inode *inode, struct file *filep) { struct kfd_process *process; + bool is_32bit_user_mode; if (iminor(inode) != 0) return -ENODEV; + is_32bit_user_mode = is_compat_task(); + + if (is_32bit_user_mode == true) { + dev_warn(kfd_device, + "Process %d (32-bit) failed to open /dev/kfd\n" + "32-bit processes are not supported by amdkfd\n", + current->pid); + return -EPERM; + } + process = kfd_create_process(current); if (IS_ERR(process)) return PTR_ERR(process); - process->is_32bit_user_mode = is_compat_task(); + process->is_32bit_user_mode = is_32bit_user_mode; dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n", process->pasid, process->is_32bit_user_mode); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c index 9abac48de499..935071410724 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c @@ -221,8 +221,14 @@ static int acquire_packet_buffer(struct kernel_queue *kq, queue_size_dwords; if (packet_size_in_dwords >= queue_size_dwords || - packet_size_in_dwords >= available_size) + packet_size_in_dwords >= available_size) { + /* + * make sure calling functions know + * acquire_packet_buffer() failed + */ + *buffer_ptr = NULL; return -ENOMEM; + } if (wptr + packet_size_in_dwords >= queue_size_dwords) { while (wptr > 0) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c index 2458ab7c0c6e..71699ad97d74 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c @@ -32,8 +32,7 @@ int kfd_pasid_init(void) { pasid_limit = max_num_of_processes; - pasid_bitmap = kzalloc(DIV_ROUND_UP(pasid_limit, BITS_PER_BYTE), - GFP_KERNEL); + pasid_bitmap = kzalloc(BITS_TO_LONGS(pasid_limit), GFP_KERNEL); if (!pasid_bitmap) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index b4f49ac13334..b85eb0b830b4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -196,7 +196,7 @@ static void kfd_process_destroy_delayed(struct rcu_head *rcu) mmdrop(p->mm); work = (struct kfd_process_release_work *) - kmalloc(sizeof(struct kfd_process_release_work), GFP_KERNEL); + kmalloc(sizeof(struct kfd_process_release_work), GFP_ATOMIC); if (work) { INIT_WORK((struct work_struct *) work, kfd_process_wq_release); diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index de79283eaea7..5213da499d39 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -725,6 +725,8 @@ void drm_crtc_cleanup(struct drm_crtc *crtc) WARN_ON(crtc->state && !crtc->funcs->atomic_destroy_state); if (crtc->state && crtc->funcs->atomic_destroy_state) crtc->funcs->atomic_destroy_state(crtc, crtc->state); + + memset(crtc, 0, sizeof(*crtc)); } EXPORT_SYMBOL(drm_crtc_cleanup); @@ -908,6 +910,11 @@ void drm_connector_cleanup(struct drm_connector *connector) struct drm_device *dev = connector->dev; struct drm_display_mode *mode, *t; + if (connector->tile_group) { + drm_mode_put_tile_group(dev, connector->tile_group); + connector->tile_group = NULL; + } + list_for_each_entry_safe(mode, t, &connector->probed_modes, head) drm_mode_remove(connector, mode); @@ -927,6 +934,8 @@ void drm_connector_cleanup(struct drm_connector *connector) if (connector->state && connector->funcs->atomic_destroy_state) connector->funcs->atomic_destroy_state(connector, connector->state); + + memset(connector, 0, sizeof(*connector)); } EXPORT_SYMBOL(drm_connector_cleanup); @@ -1068,6 +1077,8 @@ void drm_bridge_cleanup(struct drm_bridge *bridge) list_del(&bridge->head); dev->mode_config.num_bridge--; drm_modeset_unlock_all(dev); + + memset(bridge, 0, sizeof(*bridge)); } EXPORT_SYMBOL(drm_bridge_cleanup); @@ -1134,10 +1145,11 @@ void drm_encoder_cleanup(struct drm_encoder *encoder) drm_modeset_lock_all(dev); drm_mode_object_put(dev, &encoder->base); kfree(encoder->name); - encoder->name = NULL; list_del(&encoder->head); dev->mode_config.num_encoder--; drm_modeset_unlock_all(dev); + + memset(encoder, 0, sizeof(*encoder)); } EXPORT_SYMBOL(drm_encoder_cleanup); @@ -1257,6 +1269,8 @@ void drm_plane_cleanup(struct drm_plane *plane) WARN_ON(plane->state && !plane->funcs->atomic_destroy_state); if (plane->state && plane->funcs->atomic_destroy_state) plane->funcs->atomic_destroy_state(plane, plane->state); + + memset(plane, 0, sizeof(*plane)); } EXPORT_SYMBOL(drm_plane_cleanup); @@ -1339,6 +1353,11 @@ static int drm_mode_create_standard_connector_properties(struct drm_device *dev) "PATH", 0); dev->mode_config.path_property = dev_path; + dev->mode_config.tile_property = drm_property_create(dev, + DRM_MODE_PROP_BLOB | + DRM_MODE_PROP_IMMUTABLE, + "TILE", 0); + return 0; } @@ -3444,7 +3463,7 @@ void drm_fb_release(struct drm_file *priv) /* * When the file gets released that means no one else can access the fb - * list any more, so no need to grab fpriv->fbs_lock. And we need to to + * list any more, so no need to grab fpriv->fbs_lock. And we need to * avoid upsetting lockdep since the universal cursor code adds a * framebuffer while holding mutex locks. * @@ -4083,6 +4102,52 @@ int drm_mode_connector_set_path_property(struct drm_connector *connector, EXPORT_SYMBOL(drm_mode_connector_set_path_property); /** + * drm_mode_connector_set_tile_property - set tile property on connector + * @connector: connector to set property on. + * + * This looks up the tile information for a connector, and creates a + * property for userspace to parse if it exists. The property is of + * the form of 8 integers using ':' as a separator. + * + * Returns: + * Zero on success, errno on failure. + */ +int drm_mode_connector_set_tile_property(struct drm_connector *connector) +{ + struct drm_device *dev = connector->dev; + int ret, size; + char tile[256]; + + if (connector->tile_blob_ptr) + drm_property_destroy_blob(dev, connector->tile_blob_ptr); + + if (!connector->has_tile) { + connector->tile_blob_ptr = NULL; + ret = drm_object_property_set_value(&connector->base, + dev->mode_config.tile_property, 0); + return ret; + } + + snprintf(tile, 256, "%d:%d:%d:%d:%d:%d:%d:%d", + connector->tile_group->id, connector->tile_is_single_monitor, + connector->num_h_tile, connector->num_v_tile, + connector->tile_h_loc, connector->tile_v_loc, + connector->tile_h_size, connector->tile_v_size); + size = strlen(tile) + 1; + + connector->tile_blob_ptr = drm_property_create_blob(connector->dev, + size, tile); + if (!connector->tile_blob_ptr) + return -EINVAL; + + ret = drm_object_property_set_value(&connector->base, + dev->mode_config.tile_property, + connector->tile_blob_ptr->base.id); + return ret; +} +EXPORT_SYMBOL(drm_mode_connector_set_tile_property); + +/** * drm_mode_connector_update_edid_property - update the edid property of a connector * @connector: drm connector * @edid: new value of the edid property @@ -5152,6 +5217,7 @@ void drm_mode_config_init(struct drm_device *dev) INIT_LIST_HEAD(&dev->mode_config.property_blob_list); INIT_LIST_HEAD(&dev->mode_config.plane_list); idr_init(&dev->mode_config.crtc_idr); + idr_init(&dev->mode_config.tile_idr); drm_modeset_lock_all(dev); drm_mode_create_standard_connector_properties(dev); @@ -5239,6 +5305,7 @@ void drm_mode_config_cleanup(struct drm_device *dev) crtc->funcs->destroy(crtc); } + idr_destroy(&dev->mode_config.tile_idr); idr_destroy(&dev->mode_config.crtc_idr); drm_modeset_lock_fini(&dev->mode_config.connection_mutex); } @@ -5261,3 +5328,100 @@ struct drm_property *drm_mode_create_rotation_property(struct drm_device *dev, supported_rotations); } EXPORT_SYMBOL(drm_mode_create_rotation_property); + +/** + * DOC: Tile group + * + * Tile groups are used to represent tiled monitors with a unique + * integer identifier. Tiled monitors using DisplayID v1.3 have + * a unique 8-byte handle, we store this in a tile group, so we + * have a common identifier for all tiles in a monitor group. + */ +static void drm_tile_group_free(struct kref *kref) +{ + struct drm_tile_group *tg = container_of(kref, struct drm_tile_group, refcount); + struct drm_device *dev = tg->dev; + mutex_lock(&dev->mode_config.idr_mutex); + idr_remove(&dev->mode_config.tile_idr, tg->id); + mutex_unlock(&dev->mode_config.idr_mutex); + kfree(tg); +} + +/** + * drm_mode_put_tile_group - drop a reference to a tile group. + * @dev: DRM device + * @tg: tile group to drop reference to. + * + * drop reference to tile group and free if 0. + */ +void drm_mode_put_tile_group(struct drm_device *dev, + struct drm_tile_group *tg) +{ + kref_put(&tg->refcount, drm_tile_group_free); +} + +/** + * drm_mode_get_tile_group - get a reference to an existing tile group + * @dev: DRM device + * @topology: 8-bytes unique per monitor. + * + * Use the unique bytes to get a reference to an existing tile group. + * + * RETURNS: + * tile group or NULL if not found. + */ +struct drm_tile_group *drm_mode_get_tile_group(struct drm_device *dev, + char topology[8]) +{ + struct drm_tile_group *tg; + int id; + mutex_lock(&dev->mode_config.idr_mutex); + idr_for_each_entry(&dev->mode_config.tile_idr, tg, id) { + if (!memcmp(tg->group_data, topology, 8)) { + if (!kref_get_unless_zero(&tg->refcount)) + tg = NULL; + mutex_unlock(&dev->mode_config.idr_mutex); + return tg; + } + } + mutex_unlock(&dev->mode_config.idr_mutex); + return NULL; +} + +/** + * drm_mode_create_tile_group - create a tile group from a displayid description + * @dev: DRM device + * @topology: 8-bytes unique per monitor. + * + * Create a tile group for the unique monitor, and get a unique + * identifier for the tile group. + * + * RETURNS: + * new tile group or error. + */ +struct drm_tile_group *drm_mode_create_tile_group(struct drm_device *dev, + char topology[8]) +{ + struct drm_tile_group *tg; + int ret; + + tg = kzalloc(sizeof(*tg), GFP_KERNEL); + if (!tg) + return ERR_PTR(-ENOMEM); + + kref_init(&tg->refcount); + memcpy(tg->group_data, topology, 8); + tg->dev = dev; + + mutex_lock(&dev->mode_config.idr_mutex); + ret = idr_alloc(&dev->mode_config.tile_idr, tg, 1, 0, GFP_KERNEL); + if (ret >= 0) { + tg->id = ret; + } else { + kfree(tg); + tg = ERR_PTR(ret); + } + + mutex_unlock(&dev->mode_config.idr_mutex); + return tg; +} diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 959e2074b0d4..79968e39c8d0 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -186,10 +186,11 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, /* * The specification doesn't give any recommendation on how often to - * retry native transactions, so retry 7 times like for I2C-over-AUX - * transactions. + * retry native transactions. We used to retry 7 times like for + * aux i2c transactions but real world devices this wasn't + * sufficient, bump to 32 which makes Dell 4k monitors happier. */ - for (retry = 0; retry < 7; retry++) { + for (retry = 0; retry < 32; retry++) { mutex_lock(&aux->hw_mutex); err = aux->transfer(aux, &msg); diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 5682d7e9f1ec..9a5b68717ec8 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -839,6 +839,8 @@ static void drm_dp_put_mst_branch_device(struct drm_dp_mst_branch *mstb) static void drm_dp_port_teardown_pdt(struct drm_dp_mst_port *port, int old_pdt) { + struct drm_dp_mst_branch *mstb; + switch (old_pdt) { case DP_PEER_DEVICE_DP_LEGACY_CONV: case DP_PEER_DEVICE_SST_SINK: @@ -846,8 +848,9 @@ static void drm_dp_port_teardown_pdt(struct drm_dp_mst_port *port, int old_pdt) drm_dp_mst_unregister_i2c_bus(&port->aux); break; case DP_PEER_DEVICE_MST_BRANCHING: - drm_dp_put_mst_branch_device(port->mstb); + mstb = port->mstb; port->mstb = NULL; + drm_dp_put_mst_branch_device(mstb); break; } } @@ -858,6 +861,8 @@ static void drm_dp_destroy_port(struct kref *kref) struct drm_dp_mst_topology_mgr *mgr = port->mgr; if (!port->input) { port->vcpi.num_slots = 0; + + kfree(port->cached_edid); if (port->connector) (*port->mgr->cbs->destroy_connector)(mgr, port->connector); drm_dp_port_teardown_pdt(port, port->pdt); @@ -1097,6 +1102,10 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, char proppath[255]; build_mst_prop_path(port, mstb, proppath, sizeof(proppath)); port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath); + + if (port->port_num >= 8) { + port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); + } } /* put reference to this port */ @@ -2167,7 +2176,8 @@ EXPORT_SYMBOL(drm_dp_mst_hpd_irq); * This returns the current connection state for a port. It validates the * port pointer still exists so the caller doesn't require a reference */ -enum drm_connector_status drm_dp_mst_detect_port(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port) +enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector, + struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port) { enum drm_connector_status status = connector_status_disconnected; @@ -2186,6 +2196,10 @@ enum drm_connector_status drm_dp_mst_detect_port(struct drm_dp_mst_topology_mgr case DP_PEER_DEVICE_SST_SINK: status = connector_status_connected; + /* for logical ports - cache the EDID */ + if (port->port_num >= 8 && !port->cached_edid) { + port->cached_edid = drm_get_edid(connector, &port->aux.ddc); + } break; case DP_PEER_DEVICE_DP_LEGACY_CONV: if (port->ldps) @@ -2217,7 +2231,12 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_ if (!port) return NULL; - edid = drm_get_edid(connector, &port->aux.ddc); + if (port->cached_edid) + edid = drm_edid_duplicate(port->cached_edid); + else + edid = drm_get_edid(connector, &port->aux.ddc); + + drm_mode_connector_set_tile_property(connector); drm_dp_put_port(port); return edid; } diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index a7b5a71856a7..53bc7a628909 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -34,6 +34,7 @@ #include <linux/module.h> #include <drm/drmP.h> #include <drm/drm_edid.h> +#include <drm/drm_displayid.h> #define version_greater(edid, maj, min) \ (((edid)->version > (maj)) || \ @@ -1014,6 +1015,27 @@ module_param_named(edid_fixup, edid_fixup, int, 0400); MODULE_PARM_DESC(edid_fixup, "Minimum number of valid EDID header bytes (0-8, default 6)"); +static void drm_get_displayid(struct drm_connector *connector, + struct edid *edid); + +static int drm_edid_block_checksum(const u8 *raw_edid) +{ + int i; + u8 csum = 0; + for (i = 0; i < EDID_LENGTH; i++) + csum += raw_edid[i]; + + return csum; +} + +static bool drm_edid_is_zero(const u8 *in_edid, int length) +{ + if (memchr_inv(in_edid, 0, length)) + return false; + + return true; +} + /** * drm_edid_block_valid - Sanity check the EDID block (base or extension) * @raw_edid: pointer to raw EDID block @@ -1027,8 +1049,7 @@ MODULE_PARM_DESC(edid_fixup, */ bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid) { - int i; - u8 csum = 0; + u8 csum; struct edid *edid = (struct edid *)raw_edid; if (WARN_ON(!raw_edid)) @@ -1048,8 +1069,7 @@ bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid) } } - for (i = 0; i < EDID_LENGTH; i++) - csum += raw_edid[i]; + csum = drm_edid_block_checksum(raw_edid); if (csum) { if (print_bad_edid) { DRM_ERROR("EDID checksum is invalid, remainder is %d\n", csum); @@ -1080,9 +1100,13 @@ bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid) bad: if (print_bad_edid) { - printk(KERN_ERR "Raw EDID:\n"); - print_hex_dump(KERN_ERR, " \t", DUMP_PREFIX_NONE, 16, 1, + if (drm_edid_is_zero(raw_edid, EDID_LENGTH)) { + printk(KERN_ERR "EDID block is all zeroes\n"); + } else { + printk(KERN_ERR "Raw EDID:\n"); + print_hex_dump(KERN_ERR, " \t", DUMP_PREFIX_NONE, 16, 1, raw_edid, EDID_LENGTH, false); + } } return false; } @@ -1115,7 +1139,7 @@ EXPORT_SYMBOL(drm_edid_is_valid); #define DDC_SEGMENT_ADDR 0x30 /** * drm_do_probe_ddc_edid() - get EDID information via I2C - * @adapter: I2C device adaptor + * @data: I2C device adapter * @buf: EDID data buffer to be filled * @block: 128 byte EDID block to start fetching from * @len: EDID data buffer length to fetch @@ -1176,14 +1200,6 @@ drm_do_probe_ddc_edid(void *data, u8 *buf, unsigned int block, size_t len) return ret == xfers ? 0 : -1; } -static bool drm_edid_is_zero(u8 *in_edid, int length) -{ - if (memchr_inv(in_edid, 0, length)) - return false; - - return true; -} - /** * drm_do_get_edid - get EDID data using a custom EDID block read function * @connector: connector we're probing @@ -1308,10 +1324,15 @@ EXPORT_SYMBOL(drm_probe_ddc); struct edid *drm_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter) { + struct edid *edid; + if (!drm_probe_ddc(adapter)) return NULL; - return drm_do_get_edid(connector, drm_do_probe_ddc_edid, adapter); + edid = drm_do_get_edid(connector, drm_do_probe_ddc_edid, adapter); + if (edid) + drm_get_displayid(connector, edid); + return edid; } EXPORT_SYMBOL(drm_get_edid); @@ -2406,7 +2427,7 @@ add_detailed_modes(struct drm_connector *connector, struct edid *edid, /* * Search EDID for CEA extension block. */ -static u8 *drm_find_cea_extension(struct edid *edid) +static u8 *drm_find_edid_extension(struct edid *edid, int ext_id) { u8 *edid_ext = NULL; int i; @@ -2418,7 +2439,7 @@ static u8 *drm_find_cea_extension(struct edid *edid) /* Find CEA extension */ for (i = 0; i < edid->extensions; i++) { edid_ext = (u8 *)edid + EDID_LENGTH * (i + 1); - if (edid_ext[0] == CEA_EXT) + if (edid_ext[0] == ext_id) break; } @@ -2428,6 +2449,16 @@ static u8 *drm_find_cea_extension(struct edid *edid) return edid_ext; } +static u8 *drm_find_cea_extension(struct edid *edid) +{ + return drm_find_edid_extension(edid, CEA_EXT); +} + +static u8 *drm_find_displayid_extension(struct edid *edid) +{ + return drm_find_edid_extension(edid, DISPLAYID_EXT); +} + /* * Calculate the alternate clock for the CEA mode * (60Hz vs. 59.94Hz etc.) @@ -3888,3 +3919,123 @@ drm_hdmi_vendor_infoframe_from_display_mode(struct hdmi_vendor_infoframe *frame, return 0; } EXPORT_SYMBOL(drm_hdmi_vendor_infoframe_from_display_mode); + +static int drm_parse_display_id(struct drm_connector *connector, + u8 *displayid, int length, + bool is_edid_extension) +{ + /* if this is an EDID extension the first byte will be 0x70 */ + int idx = 0; + struct displayid_hdr *base; + struct displayid_block *block; + u8 csum = 0; + int i; + + if (is_edid_extension) + idx = 1; + + base = (struct displayid_hdr *)&displayid[idx]; + + DRM_DEBUG_KMS("base revision 0x%x, length %d, %d %d\n", + base->rev, base->bytes, base->prod_id, base->ext_count); + + if (base->bytes + 5 > length - idx) + return -EINVAL; + + for (i = idx; i <= base->bytes + 5; i++) { + csum += displayid[i]; + } + if (csum) { + DRM_ERROR("DisplayID checksum invalid, remainder is %d\n", csum); + return -EINVAL; + } + + block = (struct displayid_block *)&displayid[idx + 4]; + DRM_DEBUG_KMS("block id %d, rev %d, len %d\n", + block->tag, block->rev, block->num_bytes); + + switch (block->tag) { + case DATA_BLOCK_TILED_DISPLAY: { + struct displayid_tiled_block *tile = (struct displayid_tiled_block *)block; + + u16 w, h; + u8 tile_v_loc, tile_h_loc; + u8 num_v_tile, num_h_tile; + struct drm_tile_group *tg; + + w = tile->tile_size[0] | tile->tile_size[1] << 8; + h = tile->tile_size[2] | tile->tile_size[3] << 8; + + num_v_tile = (tile->topo[0] & 0xf) | (tile->topo[2] & 0x30); + num_h_tile = (tile->topo[0] >> 4) | ((tile->topo[2] >> 2) & 0x30); + tile_v_loc = (tile->topo[1] & 0xf) | ((tile->topo[2] & 0x3) << 4); + tile_h_loc = (tile->topo[1] >> 4) | (((tile->topo[2] >> 2) & 0x3) << 4); + + connector->has_tile = true; + if (tile->tile_cap & 0x80) + connector->tile_is_single_monitor = true; + + connector->num_h_tile = num_h_tile + 1; + connector->num_v_tile = num_v_tile + 1; + connector->tile_h_loc = tile_h_loc; + connector->tile_v_loc = tile_v_loc; + connector->tile_h_size = w + 1; + connector->tile_v_size = h + 1; + + DRM_DEBUG_KMS("tile cap 0x%x\n", tile->tile_cap); + DRM_DEBUG_KMS("tile_size %d x %d\n", w + 1, h + 1); + DRM_DEBUG_KMS("topo num tiles %dx%d, location %dx%d\n", + num_h_tile + 1, num_v_tile + 1, tile_h_loc, tile_v_loc); + DRM_DEBUG_KMS("vend %c%c%c\n", tile->topology_id[0], tile->topology_id[1], tile->topology_id[2]); + + tg = drm_mode_get_tile_group(connector->dev, tile->topology_id); + if (!tg) { + tg = drm_mode_create_tile_group(connector->dev, tile->topology_id); + } + if (!tg) + return -ENOMEM; + + if (connector->tile_group != tg) { + /* if we haven't got a pointer, + take the reference, drop ref to old tile group */ + if (connector->tile_group) { + drm_mode_put_tile_group(connector->dev, connector->tile_group); + } + connector->tile_group = tg; + } else + /* if same tile group, then release the ref we just took. */ + drm_mode_put_tile_group(connector->dev, tg); + } + break; + default: + printk("unknown displayid tag %d\n", block->tag); + break; + } + return 0; +} + +static void drm_get_displayid(struct drm_connector *connector, + struct edid *edid) +{ + void *displayid = NULL; + int ret; + connector->has_tile = false; + displayid = drm_find_displayid_extension(edid); + if (!displayid) { + /* drop reference to any tile group we had */ + goto out_drop_ref; + } + + ret = drm_parse_display_id(connector, displayid, EDID_LENGTH, true); + if (ret < 0) + goto out_drop_ref; + if (!connector->has_tile) + goto out_drop_ref; + return; +out_drop_ref: + if (connector->tile_group) { + drm_mode_put_tile_group(connector->dev, connector->tile_group); + connector->tile_group = NULL; + } + return; +} diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 09d47e9ba026..52ce26d6b4fb 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -347,9 +347,18 @@ bool drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) { struct drm_device *dev = fb_helper->dev; bool ret; + bool do_delayed = false; + drm_modeset_lock_all(dev); ret = restore_fbdev_mode(fb_helper); + + do_delayed = fb_helper->delayed_hotplug; + if (do_delayed) + fb_helper->delayed_hotplug = false; drm_modeset_unlock_all(dev); + + if (do_delayed) + drm_fb_helper_hotplug_event(fb_helper); return ret; } EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked); @@ -888,10 +897,6 @@ int drm_fb_helper_set_par(struct fb_info *info) drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); - if (fb_helper->delayed_hotplug) { - fb_helper->delayed_hotplug = false; - drm_fb_helper_hotplug_event(fb_helper); - } return 0; } EXPORT_SYMBOL(drm_fb_helper_set_par); @@ -995,19 +1000,21 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper, crtc_count = 0; for (i = 0; i < fb_helper->crtc_count; i++) { struct drm_display_mode *desired_mode; + int x, y; desired_mode = fb_helper->crtc_info[i].desired_mode; - + x = fb_helper->crtc_info[i].x; + y = fb_helper->crtc_info[i].y; if (desired_mode) { if (gamma_size == 0) gamma_size = fb_helper->crtc_info[i].mode_set.crtc->gamma_size; - if (desired_mode->hdisplay < sizes.fb_width) - sizes.fb_width = desired_mode->hdisplay; - if (desired_mode->vdisplay < sizes.fb_height) - sizes.fb_height = desired_mode->vdisplay; - if (desired_mode->hdisplay > sizes.surface_width) - sizes.surface_width = desired_mode->hdisplay; - if (desired_mode->vdisplay > sizes.surface_height) - sizes.surface_height = desired_mode->vdisplay; + if (desired_mode->hdisplay + x < sizes.fb_width) + sizes.fb_width = desired_mode->hdisplay + x; + if (desired_mode->vdisplay + y < sizes.fb_height) + sizes.fb_height = desired_mode->vdisplay + y; + if (desired_mode->hdisplay + x > sizes.surface_width) + sizes.surface_width = desired_mode->hdisplay + x; + if (desired_mode->vdisplay + y > sizes.surface_height) + sizes.surface_height = desired_mode->vdisplay + y; crtc_count++; } } @@ -1307,6 +1314,7 @@ static void drm_enable_connectors(struct drm_fb_helper *fb_helper, static bool drm_target_cloned(struct drm_fb_helper *fb_helper, struct drm_display_mode **modes, + struct drm_fb_offset *offsets, bool *enabled, int width, int height) { int count, i, j; @@ -1378,27 +1386,88 @@ static bool drm_target_cloned(struct drm_fb_helper *fb_helper, return false; } +static int drm_get_tile_offsets(struct drm_fb_helper *fb_helper, + struct drm_display_mode **modes, + struct drm_fb_offset *offsets, + int idx, + int h_idx, int v_idx) +{ + struct drm_fb_helper_connector *fb_helper_conn; + int i; + int hoffset = 0, voffset = 0; + + for (i = 0; i < fb_helper->connector_count; i++) { + fb_helper_conn = fb_helper->connector_info[i]; + if (!fb_helper_conn->connector->has_tile) + continue; + + if (!modes[i] && (h_idx || v_idx)) { + DRM_DEBUG_KMS("no modes for connector tiled %d %d\n", i, + fb_helper_conn->connector->base.id); + continue; + } + if (fb_helper_conn->connector->tile_h_loc < h_idx) + hoffset += modes[i]->hdisplay; + + if (fb_helper_conn->connector->tile_v_loc < v_idx) + voffset += modes[i]->vdisplay; + } + offsets[idx].x = hoffset; + offsets[idx].y = voffset; + DRM_DEBUG_KMS("returned %d %d for %d %d\n", hoffset, voffset, h_idx, v_idx); + return 0; +} + static bool drm_target_preferred(struct drm_fb_helper *fb_helper, struct drm_display_mode **modes, + struct drm_fb_offset *offsets, bool *enabled, int width, int height) { struct drm_fb_helper_connector *fb_helper_conn; int i; - + uint64_t conn_configured = 0, mask; + int tile_pass = 0; + mask = (1 << fb_helper->connector_count) - 1; +retry: for (i = 0; i < fb_helper->connector_count; i++) { fb_helper_conn = fb_helper->connector_info[i]; - if (enabled[i] == false) + if (conn_configured & (1 << i)) continue; + if (enabled[i] == false) { + conn_configured |= (1 << i); + continue; + } + + /* first pass over all the untiled connectors */ + if (tile_pass == 0 && fb_helper_conn->connector->has_tile) + continue; + + if (tile_pass == 1) { + if (fb_helper_conn->connector->tile_h_loc != 0 || + fb_helper_conn->connector->tile_v_loc != 0) + continue; + + } else { + if (fb_helper_conn->connector->tile_h_loc != tile_pass -1 && + fb_helper_conn->connector->tile_v_loc != tile_pass - 1) + /* if this tile_pass doesn't cover any of the tiles - keep going */ + continue; + + /* find the tile offsets for this pass - need + to find all tiles left and above */ + drm_get_tile_offsets(fb_helper, modes, offsets, + i, fb_helper_conn->connector->tile_h_loc, fb_helper_conn->connector->tile_v_loc); + } DRM_DEBUG_KMS("looking for cmdline mode on connector %d\n", fb_helper_conn->connector->base.id); /* got for command line mode first */ modes[i] = drm_pick_cmdline_mode(fb_helper_conn, width, height); if (!modes[i]) { - DRM_DEBUG_KMS("looking for preferred mode on connector %d\n", - fb_helper_conn->connector->base.id); + DRM_DEBUG_KMS("looking for preferred mode on connector %d %d\n", + fb_helper_conn->connector->base.id, fb_helper_conn->connector->tile_group ? fb_helper_conn->connector->tile_group->id : 0); modes[i] = drm_has_preferred_mode(fb_helper_conn, width, height); } /* No preferred modes, pick one off the list */ @@ -1408,6 +1477,12 @@ static bool drm_target_preferred(struct drm_fb_helper *fb_helper, } DRM_DEBUG_KMS("found mode %s\n", modes[i] ? modes[i]->name : "none"); + conn_configured |= (1 << i); + } + + if ((conn_configured & mask) != mask) { + tile_pass++; + goto retry; } return true; } @@ -1497,6 +1572,7 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper) struct drm_device *dev = fb_helper->dev; struct drm_fb_helper_crtc **crtcs; struct drm_display_mode **modes; + struct drm_fb_offset *offsets; struct drm_mode_set *modeset; bool *enabled; int width, height; @@ -1511,9 +1587,11 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper) sizeof(struct drm_fb_helper_crtc *), GFP_KERNEL); modes = kcalloc(dev->mode_config.num_connector, sizeof(struct drm_display_mode *), GFP_KERNEL); + offsets = kcalloc(dev->mode_config.num_connector, + sizeof(struct drm_fb_offset), GFP_KERNEL); enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool), GFP_KERNEL); - if (!crtcs || !modes || !enabled) { + if (!crtcs || !modes || !enabled || !offsets) { DRM_ERROR("Memory allocation failed\n"); goto out; } @@ -1523,14 +1601,16 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper) if (!(fb_helper->funcs->initial_config && fb_helper->funcs->initial_config(fb_helper, crtcs, modes, + offsets, enabled, width, height))) { memset(modes, 0, dev->mode_config.num_connector*sizeof(modes[0])); memset(crtcs, 0, dev->mode_config.num_connector*sizeof(crtcs[0])); + memset(offsets, 0, dev->mode_config.num_connector*sizeof(offsets[0])); - if (!drm_target_cloned(fb_helper, - modes, enabled, width, height) && - !drm_target_preferred(fb_helper, - modes, enabled, width, height)) + if (!drm_target_cloned(fb_helper, modes, offsets, + enabled, width, height) && + !drm_target_preferred(fb_helper, modes, offsets, + enabled, width, height)) DRM_ERROR("Unable to find initial modes\n"); DRM_DEBUG_KMS("picking CRTCs for %dx%d config\n", @@ -1550,18 +1630,23 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper) for (i = 0; i < fb_helper->connector_count; i++) { struct drm_display_mode *mode = modes[i]; struct drm_fb_helper_crtc *fb_crtc = crtcs[i]; + struct drm_fb_offset *offset = &offsets[i]; modeset = &fb_crtc->mode_set; if (mode && fb_crtc) { - DRM_DEBUG_KMS("desired mode %s set on crtc %d\n", - mode->name, fb_crtc->mode_set.crtc->base.id); + DRM_DEBUG_KMS("desired mode %s set on crtc %d (%d,%d)\n", + mode->name, fb_crtc->mode_set.crtc->base.id, offset->x, offset->y); fb_crtc->desired_mode = mode; + fb_crtc->x = offset->x; + fb_crtc->y = offset->y; if (modeset->mode) drm_mode_destroy(dev, modeset->mode); modeset->mode = drm_mode_duplicate(dev, fb_crtc->desired_mode); modeset->connectors[modeset->num_connectors++] = fb_helper->connector_info[i]->connector; modeset->fb = fb_helper->fb; + modeset->x = offset->x; + modeset->y = offset->y; } } @@ -1578,6 +1663,7 @@ static void drm_setup_crtcs(struct drm_fb_helper *fb_helper) out: kfree(crtcs); kfree(modes); + kfree(offsets); kfree(enabled); } diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c index 91e1105f2800..0b9514b6cd64 100644 --- a/drivers/gpu/drm/drm_fops.c +++ b/drivers/gpu/drm/drm_fops.c @@ -527,6 +527,7 @@ ssize_t drm_read(struct file *filp, char __user *buffer, if (copy_to_user(buffer + total, e->event, e->event->length)) { total = -EFAULT; + e->destroy(e); break; } diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 0e47df4ef24e..f5a5f18efa5b 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -166,7 +166,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc) spin_lock_irqsave(&dev->vblank_time_lock, irqflags); /* - * If the vblank interrupt was already disbled update the count + * If the vblank interrupt was already disabled update the count * and timestamp to maintain the appearance that the counter * has been ticking all along until this time. This makes the * count account for the entire time between drm_vblank_on() and diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 03d0b0cb8e05..fb3e3d429191 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4565,7 +4565,6 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc) ironlake_fdi_disable(crtc); ironlake_disable_pch_transcoder(dev_priv, pipe); - intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true); if (HAS_PCH_CPT(dev)) { /* disable TRANS_DP_CTL */ @@ -4636,8 +4635,6 @@ static void haswell_crtc_disable(struct drm_crtc *crtc) if (intel_crtc->config.has_pch_encoder) { lpt_disable_pch_transcoder(dev_priv); - intel_set_pch_fifo_underrun_reporting(dev_priv, TRANSCODER_A, - true); intel_ddi_fdi_disable(crtc); } diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index bfe359506377..7f8c6a66680a 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -283,7 +283,7 @@ intel_dp_mst_detect(struct drm_connector *connector, bool force) struct intel_connector *intel_connector = to_intel_connector(connector); struct intel_dp *intel_dp = intel_connector->mst_port; - return drm_dp_mst_detect_port(&intel_dp->mst_mgr, intel_connector->port); + return drm_dp_mst_detect_port(connector, &intel_dp->mst_mgr, intel_connector->port); } static int @@ -414,6 +414,8 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo intel_dp_add_properties(intel_dp, connector); drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0); + drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0); + drm_mode_connector_set_path_property(connector, pathprop); drm_reinit_primary_mode_group(dev); mutex_lock(&dev->mode_config.mutex); diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index f2183b554cbc..850cf7d6578c 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -324,6 +324,7 @@ intel_fb_helper_crtc(struct drm_fb_helper *fb_helper, struct drm_crtc *crtc) static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, struct drm_fb_helper_crtc **crtcs, struct drm_display_mode **modes, + struct drm_fb_offset *offsets, bool *enabled, int width, int height) { struct drm_device *dev = fb_helper->dev; @@ -332,6 +333,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, bool fallback = true; int num_connectors_enabled = 0; int num_connectors_detected = 0; + uint64_t conn_configured = 0, mask; + int pass = 0; save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool), GFP_KERNEL); @@ -339,7 +342,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, return false; memcpy(save_enabled, enabled, dev->mode_config.num_connector); - + mask = (1 << fb_helper->connector_count) - 1; +retry: for (i = 0; i < fb_helper->connector_count; i++) { struct drm_fb_helper_connector *fb_conn; struct drm_connector *connector; @@ -349,12 +353,19 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, fb_conn = fb_helper->connector_info[i]; connector = fb_conn->connector; + if (conn_configured & (1 << i)) + continue; + + if (pass == 0 && !connector->has_tile) + continue; + if (connector->status == connector_status_connected) num_connectors_detected++; if (!enabled[i]) { DRM_DEBUG_KMS("connector %s not enabled, skipping\n", connector->name); + conn_configured |= (1 << i); continue; } @@ -373,6 +384,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, DRM_DEBUG_KMS("connector %s has no encoder or crtc, skipping\n", connector->name); enabled[i] = false; + conn_configured |= (1 << i); continue; } @@ -400,8 +412,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, /* try for preferred next */ if (!modes[i]) { - DRM_DEBUG_KMS("looking for preferred mode on connector %s\n", - connector->name); + DRM_DEBUG_KMS("looking for preferred mode on connector %s %d\n", + connector->name, connector->has_tile); modes[i] = drm_has_preferred_mode(fb_conn, width, height); } @@ -444,6 +456,12 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, modes[i]->flags & DRM_MODE_FLAG_INTERLACE ? "i" :""); fallback = false; + conn_configured |= (1 << i); + } + + if ((conn_configured & mask) != mask) { + pass++; + goto retry; } /* diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index c03d457a5150..14654d628ca4 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -899,6 +899,17 @@ void intel_lvds_init(struct drm_device *dev) int pipe; u8 pin; + /* + * Unlock registers and just leave them unlocked. Do this before + * checking quirk lists to avoid bogus WARNINGs. + */ + if (HAS_PCH_SPLIT(dev)) { + I915_WRITE(PCH_PP_CONTROL, + I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS); + } else { + I915_WRITE(PP_CONTROL, + I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); + } if (!intel_lvds_supported(dev)) return; @@ -1097,17 +1108,6 @@ out: lvds_encoder->a3_power = I915_READ(lvds_encoder->reg) & LVDS_A3_POWER_MASK; - /* - * Unlock registers and just - * leave them unlocked - */ - if (HAS_PCH_SPLIT(dev)) { - I915_WRITE(PCH_PP_CONTROL, - I915_READ(PCH_PP_CONTROL) | PANEL_UNLOCK_REGS); - } else { - I915_WRITE(PP_CONTROL, - I915_READ(PP_CONTROL) | PANEL_UNLOCK_REGS); - } lvds_connector->lid_notifier.notifier_call = intel_lid_notify; if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) { DRM_DEBUG_KMS("lid notifier registration failed\n"); diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c index cd05677ad4b7..72a40f95d048 100644 --- a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c +++ b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c @@ -218,7 +218,6 @@ nvc0_identify(struct nouveau_device *device) device->oclass[NVDEV_ENGINE_BSP ] = &nvc0_bsp_oclass; device->oclass[NVDEV_ENGINE_PPP ] = &nvc0_ppp_oclass; device->oclass[NVDEV_ENGINE_COPY0 ] = &nvc0_copy0_oclass; - device->oclass[NVDEV_ENGINE_COPY1 ] = &nvc0_copy1_oclass; device->oclass[NVDEV_ENGINE_DISP ] = nva3_disp_oclass; device->oclass[NVDEV_ENGINE_PERFMON] = &nvc0_perfmon_oclass; break; diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nv04.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nv04.c index 5ae6a43893b5..1931057f9962 100644 --- a/drivers/gpu/drm/nouveau/core/engine/fifo/nv04.c +++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nv04.c @@ -551,8 +551,8 @@ nv04_fifo_intr(struct nouveau_subdev *subdev) } if (status & 0x40000000) { - nouveau_fifo_uevent(&priv->base); nv_wr32(priv, 0x002100, 0x40000000); + nouveau_fifo_uevent(&priv->base); status &= ~0x40000000; } } diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c index 1fe1f8fbda0c..074d434c3077 100644 --- a/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c +++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c @@ -740,6 +740,8 @@ nvc0_fifo_intr_engine_unit(struct nvc0_fifo_priv *priv, int engn) u32 inte = nv_rd32(priv, 0x002628); u32 unkn; + nv_wr32(priv, 0x0025a8 + (engn * 0x04), intr); + for (unkn = 0; unkn < 8; unkn++) { u32 ints = (intr >> (unkn * 0x04)) & inte; if (ints & 0x1) { @@ -751,8 +753,6 @@ nvc0_fifo_intr_engine_unit(struct nvc0_fifo_priv *priv, int engn) nv_mask(priv, 0x002628, ints, 0); } } - - nv_wr32(priv, 0x0025a8 + (engn * 0x04), intr); } static void diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c index fc9ef663f25a..6a8db7c80bd1 100644 --- a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c +++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c @@ -982,8 +982,8 @@ nve0_fifo_intr(struct nouveau_subdev *subdev) } if (stat & 0x80000000) { - nve0_fifo_intr_engine(priv); nv_wr32(priv, 0x002100, 0x80000000); + nve0_fifo_intr_engine(priv); stat &= ~0x80000000; } diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index afb93bb72f97..65910e3aed0c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -664,7 +664,6 @@ nouveau_pmops_suspend(struct device *dev) pci_save_state(pdev); pci_disable_device(pdev); - pci_ignore_hotplug(pdev); pci_set_power_state(pdev, PCI_D3hot); return 0; } @@ -732,6 +731,7 @@ nouveau_pmops_runtime_suspend(struct device *dev) ret = nouveau_do_suspend(drm_dev, true); pci_save_state(pdev); pci_disable_device(pdev); + pci_ignore_hotplug(pdev); pci_set_power_state(pdev, PCI_D3cold); drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF; return ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 515cd9aebb99..f32a434724e3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -52,20 +52,24 @@ nouveau_fctx(struct nouveau_fence *fence) return container_of(fence->base.lock, struct nouveau_fence_chan, lock); } -static void +static int nouveau_fence_signal(struct nouveau_fence *fence) { + int drop = 0; + fence_signal_locked(&fence->base); list_del(&fence->head); + rcu_assign_pointer(fence->channel, NULL); if (test_bit(FENCE_FLAG_USER_BITS, &fence->base.flags)) { struct nouveau_fence_chan *fctx = nouveau_fctx(fence); if (!--fctx->notify_ref) - nvif_notify_put(&fctx->notify); + drop = 1; } fence_put(&fence->base); + return drop; } static struct nouveau_fence * @@ -88,16 +92,23 @@ nouveau_fence_context_del(struct nouveau_fence_chan *fctx) { struct nouveau_fence *fence; - nvif_notify_fini(&fctx->notify); - spin_lock_irq(&fctx->lock); while (!list_empty(&fctx->pending)) { fence = list_entry(fctx->pending.next, typeof(*fence), head); - nouveau_fence_signal(fence); - fence->channel = NULL; + if (nouveau_fence_signal(fence)) + nvif_notify_put(&fctx->notify); } spin_unlock_irq(&fctx->lock); + + nvif_notify_fini(&fctx->notify); + fctx->dead = 1; + + /* + * Ensure that all accesses to fence->channel complete before freeing + * the channel. + */ + synchronize_rcu(); } static void @@ -112,21 +123,23 @@ nouveau_fence_context_free(struct nouveau_fence_chan *fctx) kref_put(&fctx->fence_ref, nouveau_fence_context_put); } -static void +static int nouveau_fence_update(struct nouveau_channel *chan, struct nouveau_fence_chan *fctx) { struct nouveau_fence *fence; - + int drop = 0; u32 seq = fctx->read(chan); while (!list_empty(&fctx->pending)) { fence = list_entry(fctx->pending.next, typeof(*fence), head); if ((int)(seq - fence->base.seqno) < 0) - return; + break; - nouveau_fence_signal(fence); + drop |= nouveau_fence_signal(fence); } + + return drop; } static int @@ -135,18 +148,21 @@ nouveau_fence_wait_uevent_handler(struct nvif_notify *notify) struct nouveau_fence_chan *fctx = container_of(notify, typeof(*fctx), notify); unsigned long flags; + int ret = NVIF_NOTIFY_KEEP; spin_lock_irqsave(&fctx->lock, flags); if (!list_empty(&fctx->pending)) { struct nouveau_fence *fence; + struct nouveau_channel *chan; fence = list_entry(fctx->pending.next, typeof(*fence), head); - nouveau_fence_update(fence->channel, fctx); + chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock)); + if (nouveau_fence_update(fence->channel, fctx)) + ret = NVIF_NOTIFY_DROP; } spin_unlock_irqrestore(&fctx->lock, flags); - /* Always return keep here. NVIF refcount is handled with nouveau_fence_update */ - return NVIF_NOTIFY_KEEP; + return ret; } void @@ -262,7 +278,10 @@ nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan) if (!ret) { fence_get(&fence->base); spin_lock_irq(&fctx->lock); - nouveau_fence_update(chan, fctx); + + if (nouveau_fence_update(chan, fctx)) + nvif_notify_put(&fctx->notify); + list_add_tail(&fence->head, &fctx->pending); spin_unlock_irq(&fctx->lock); } @@ -276,13 +295,16 @@ nouveau_fence_done(struct nouveau_fence *fence) if (fence->base.ops == &nouveau_fence_ops_legacy || fence->base.ops == &nouveau_fence_ops_uevent) { struct nouveau_fence_chan *fctx = nouveau_fctx(fence); + struct nouveau_channel *chan; unsigned long flags; if (test_bit(FENCE_FLAG_SIGNALED_BIT, &fence->base.flags)) return true; spin_lock_irqsave(&fctx->lock, flags); - nouveau_fence_update(fence->channel, fctx); + chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock)); + if (chan && nouveau_fence_update(chan, fctx)) + nvif_notify_put(&fctx->notify); spin_unlock_irqrestore(&fctx->lock, flags); } return fence_is_signaled(&fence->base); @@ -387,12 +409,18 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e if (fence && (!exclusive || !fobj || !fobj->shared_count)) { struct nouveau_channel *prev = NULL; + bool must_wait = true; f = nouveau_local_fence(fence, chan->drm); - if (f) - prev = f->channel; + if (f) { + rcu_read_lock(); + prev = rcu_dereference(f->channel); + if (prev && (prev == chan || fctx->sync(f, prev, chan) == 0)) + must_wait = false; + rcu_read_unlock(); + } - if (!prev || (prev != chan && (ret = fctx->sync(f, prev, chan)))) + if (must_wait) ret = fence_wait(fence, intr); return ret; @@ -403,19 +431,22 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e for (i = 0; i < fobj->shared_count && !ret; ++i) { struct nouveau_channel *prev = NULL; + bool must_wait = true; fence = rcu_dereference_protected(fobj->shared[i], reservation_object_held(resv)); f = nouveau_local_fence(fence, chan->drm); - if (f) - prev = f->channel; + if (f) { + rcu_read_lock(); + prev = rcu_dereference(f->channel); + if (prev && (prev == chan || fctx->sync(f, prev, chan) == 0)) + must_wait = false; + rcu_read_unlock(); + } - if (!prev || (prev != chan && (ret = fctx->sync(f, prev, chan)))) + if (must_wait) ret = fence_wait(fence, intr); - - if (ret) - break; } return ret; @@ -463,7 +494,7 @@ static const char *nouveau_fence_get_timeline_name(struct fence *f) struct nouveau_fence *fence = from_fence(f); struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - return fence->channel ? fctx->name : "dead channel"; + return !fctx->dead ? fctx->name : "dead channel"; } /* @@ -476,9 +507,16 @@ static bool nouveau_fence_is_signaled(struct fence *f) { struct nouveau_fence *fence = from_fence(f); struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - struct nouveau_channel *chan = fence->channel; + struct nouveau_channel *chan; + bool ret = false; + + rcu_read_lock(); + chan = rcu_dereference(fence->channel); + if (chan) + ret = (int)(fctx->read(chan) - fence->base.seqno) >= 0; + rcu_read_unlock(); - return (int)(fctx->read(chan) - fence->base.seqno) >= 0; + return ret; } static bool nouveau_fence_no_signaling(struct fence *f) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 943b0b17b1fc..96e461c6f68f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -14,7 +14,7 @@ struct nouveau_fence { bool sysmem; - struct nouveau_channel *channel; + struct nouveau_channel __rcu *channel; unsigned long timeout; }; @@ -47,7 +47,7 @@ struct nouveau_fence_chan { char name[32]; struct nvif_notify notify; - int notify_ref; + int notify_ref, dead; }; struct nouveau_fence_priv { diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index 446e71ca36cb..d9b25684ac98 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -264,7 +264,8 @@ int qxl_release_reserve_list(struct qxl_release *release, bool no_intr) if (list_is_singular(&release->bos)) return 0; - ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos, !no_intr); + ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos, + !no_intr, NULL); if (ret) return ret; diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 30d242b25078..d59ec491dbb9 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -2039,6 +2039,7 @@ int atombios_crtc_mode_set(struct drm_crtc *crtc, atombios_crtc_set_base(crtc, x, y, old_fb); atombios_overscan_setup(crtc, mode, adjusted_mode); atombios_scaler_setup(crtc); + radeon_cursor_reset(crtc); /* update the hw version fpr dpm */ radeon_crtc->hw_mode = *adjusted_mode; diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index 3f898d020ae6..f373a81ba3d5 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -937,7 +937,7 @@ static void ci_fan_ctrl_set_static_mode(struct radeon_device *rdev, u32 mode) tmp |= TMIN(0); WREG32_SMC(CG_FDO_CTRL2, tmp); - tmp = RREG32_SMC(CG_FDO_CTRL2) & FDO_PWM_MODE_MASK; + tmp = RREG32_SMC(CG_FDO_CTRL2) & ~FDO_PWM_MODE_MASK; tmp |= FDO_PWM_MODE(mode); WREG32_SMC(CG_FDO_CTRL2, tmp); } @@ -1162,7 +1162,7 @@ static int ci_fan_ctrl_set_fan_speed_rpm(struct radeon_device *rdev, tmp |= TARGET_PERIOD(tach_period); WREG32_SMC(CG_TACH_CTRL, tmp); - ci_fan_ctrl_set_static_mode(rdev, FDO_PWM_MODE_STATIC); + ci_fan_ctrl_set_static_mode(rdev, FDO_PWM_MODE_STATIC_RPM); return 0; } @@ -1178,7 +1178,7 @@ static void ci_fan_ctrl_set_default_mode(struct radeon_device *rdev) tmp |= FDO_PWM_MODE(pi->fan_ctrl_default_mode); WREG32_SMC(CG_FDO_CTRL2, tmp); - tmp = RREG32_SMC(CG_FDO_CTRL2) & TMIN_MASK; + tmp = RREG32_SMC(CG_FDO_CTRL2) & ~TMIN_MASK; tmp |= TMIN(pi->t_min); WREG32_SMC(CG_FDO_CTRL2, tmp); pi->fan_ctrl_is_in_default_mode = true; @@ -5849,7 +5849,6 @@ int ci_dpm_init(struct radeon_device *rdev) rdev->pm.dpm.dyn_state.max_clock_voltage_on_ac; pi->fan_ctrl_is_in_default_mode = true; - rdev->pm.dpm.fan.ucode_fan_control = false; return 0; } diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h index e4e88ca8b82e..ba85986febea 100644 --- a/drivers/gpu/drm/radeon/cikd.h +++ b/drivers/gpu/drm/radeon/cikd.h @@ -213,18 +213,18 @@ #define CG_FDO_CTRL0 0xC0300064 #define FDO_STATIC_DUTY(x) ((x) << 0) -#define FDO_STATIC_DUTY_MASK 0x0000000F +#define FDO_STATIC_DUTY_MASK 0x000000FF #define FDO_STATIC_DUTY_SHIFT 0 #define CG_FDO_CTRL1 0xC0300068 #define FMAX_DUTY100(x) ((x) << 0) -#define FMAX_DUTY100_MASK 0x0000000F +#define FMAX_DUTY100_MASK 0x000000FF #define FMAX_DUTY100_SHIFT 0 #define CG_FDO_CTRL2 0xC030006C #define TMIN(x) ((x) << 0) -#define TMIN_MASK 0x0000000F +#define TMIN_MASK 0x000000FF #define TMIN_SHIFT 0 #define FDO_PWM_MODE(x) ((x) << 11) -#define FDO_PWM_MODE_MASK (3 << 11) +#define FDO_PWM_MODE_MASK (7 << 11) #define FDO_PWM_MODE_SHIFT 11 #define TACH_PWM_RESP_RATE(x) ((x) << 25) #define TACH_PWM_RESP_RATE_MASK (0x7f << 25) diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 5c8b358f9fba..924b1b7ab455 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -35,7 +35,7 @@ #define MIN(a,b) (((a)<(b))?(a):(b)) int r600_dma_cs_next_reloc(struct radeon_cs_parser *p, - struct radeon_cs_reloc **cs_reloc); + struct radeon_bo_list **cs_reloc); struct evergreen_cs_track { u32 group_size; u32 nbanks; @@ -1094,7 +1094,7 @@ static int evergreen_cs_parse_packet0(struct radeon_cs_parser *p, static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) { struct evergreen_cs_track *track = (struct evergreen_cs_track *)p->track; - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; u32 last_reg; u32 m, i, tmp, *ib; int r; @@ -1792,7 +1792,7 @@ static bool evergreen_is_safe_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) static int evergreen_packet3_check(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt) { - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; struct evergreen_cs_track *track; volatile u32 *ib; unsigned idx; @@ -2661,7 +2661,7 @@ int evergreen_cs_parse(struct radeon_cs_parser *p) p->track = NULL; return r; } - } while (p->idx < p->chunks[p->chunk_ib_idx].length_dw); + } while (p->idx < p->chunk_ib->length_dw); #if 0 for (r = 0; r < p->ib.length_dw; r++) { printk(KERN_INFO "%05d 0x%08X\n", r, p->ib.ptr[r]); @@ -2684,8 +2684,8 @@ int evergreen_cs_parse(struct radeon_cs_parser *p) **/ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) { - struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx]; - struct radeon_cs_reloc *src_reloc, *dst_reloc, *dst2_reloc; + struct radeon_cs_chunk *ib_chunk = p->chunk_ib; + struct radeon_bo_list *src_reloc, *dst_reloc, *dst2_reloc; u32 header, cmd, count, sub_cmd; volatile u32 *ib = p->ib.ptr; u32 idx; @@ -3100,7 +3100,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("Unknown packet type %d at %d !\n", cmd, idx); return -EINVAL; } - } while (p->idx < p->chunks[p->chunk_ib_idx].length_dw); + } while (p->idx < p->chunk_ib->length_dw); #if 0 for (r = 0; r < p->ib->length_dw; r++) { printk(KERN_INFO "%05d 0x%08X\n", r, p->ib.ptr[r]); diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index b53b31a7b76f..74f06d540591 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -1254,7 +1254,7 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p, int r; u32 tile_flags = 0; u32 tmp; - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; u32 value; r = radeon_cs_packet_next_reloc(p, &reloc, 0); @@ -1293,7 +1293,7 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p, int idx) { unsigned c, i; - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; struct r100_cs_track *track; int r = 0; volatile uint32_t *ib; @@ -1542,7 +1542,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt, unsigned idx, unsigned reg) { - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; struct r100_cs_track *track; volatile uint32_t *ib; uint32_t tmp; @@ -1901,7 +1901,7 @@ int r100_cs_track_check_pkt3_indx_buffer(struct radeon_cs_parser *p, static int r100_packet3_check(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt) { - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; struct r100_cs_track *track; unsigned idx; volatile uint32_t *ib; @@ -2061,7 +2061,7 @@ int r100_cs_parse(struct radeon_cs_parser *p) } if (r) return r; - } while (p->idx < p->chunks[p->chunk_ib_idx].length_dw); + } while (p->idx < p->chunk_ib->length_dw); return 0; } diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c index 732d4938aab7..c70e6d5bcd19 100644 --- a/drivers/gpu/drm/radeon/r200.c +++ b/drivers/gpu/drm/radeon/r200.c @@ -146,7 +146,7 @@ int r200_packet0_check(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt, unsigned idx, unsigned reg) { - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; struct r100_cs_track *track; volatile uint32_t *ib; uint32_t tmp; diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c index 1bc4704034ce..064ad5569cca 100644 --- a/drivers/gpu/drm/radeon/r300.c +++ b/drivers/gpu/drm/radeon/r300.c @@ -598,7 +598,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt, unsigned idx, unsigned reg) { - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; struct r100_cs_track *track; volatile uint32_t *ib; uint32_t tmp, tile_flags = 0; @@ -1142,7 +1142,7 @@ fail: static int r300_packet3_check(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt) { - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; struct r100_cs_track *track; volatile uint32_t *ib; unsigned idx; @@ -1283,7 +1283,7 @@ int r300_cs_parse(struct radeon_cs_parser *p) if (r) { return r; } - } while (p->idx < p->chunks[p->chunk_ib_idx].length_dw); + } while (p->idx < p->chunk_ib->length_dw); return 0; } diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index c47537a1ddba..acc1f99c84d9 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -969,7 +969,7 @@ static int r600_cs_parse_packet0(struct radeon_cs_parser *p, static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) { struct r600_cs_track *track = (struct r600_cs_track *)p->track; - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; u32 m, i, tmp, *ib; int r; @@ -1626,7 +1626,7 @@ static bool r600_is_safe_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) static int r600_packet3_check(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt) { - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; struct r600_cs_track *track; volatile u32 *ib; unsigned idx; @@ -2316,7 +2316,7 @@ int r600_cs_parse(struct radeon_cs_parser *p) p->track = NULL; return r; } - } while (p->idx < p->chunks[p->chunk_ib_idx].length_dw); + } while (p->idx < p->chunk_ib->length_dw); #if 0 for (r = 0; r < p->ib.length_dw; r++) { printk(KERN_INFO "%05d 0x%08X\n", r, p->ib.ptr[r]); @@ -2351,10 +2351,10 @@ static void r600_cs_parser_fini(struct radeon_cs_parser *parser, int error) static int r600_cs_parser_relocs_legacy(struct radeon_cs_parser *p) { - if (p->chunk_relocs_idx == -1) { + if (p->chunk_relocs == NULL) { return 0; } - p->relocs = kzalloc(sizeof(struct radeon_cs_reloc), GFP_KERNEL); + p->relocs = kzalloc(sizeof(struct radeon_bo_list), GFP_KERNEL); if (p->relocs == NULL) { return -ENOMEM; } @@ -2398,7 +2398,7 @@ int r600_cs_legacy(struct drm_device *dev, void *data, struct drm_file *filp, /* Copy the packet into the IB, the parser will read from the * input memory (cached) and write to the IB (which can be * uncached). */ - ib_chunk = &parser.chunks[parser.chunk_ib_idx]; + ib_chunk = parser.chunk_ib; parser.ib.length_dw = ib_chunk->length_dw; *l = parser.ib.length_dw; if (copy_from_user(ib, ib_chunk->user_ptr, ib_chunk->length_dw * 4)) { @@ -2435,24 +2435,24 @@ void r600_cs_legacy_init(void) * GPU offset using the provided start. **/ int r600_dma_cs_next_reloc(struct radeon_cs_parser *p, - struct radeon_cs_reloc **cs_reloc) + struct radeon_bo_list **cs_reloc) { struct radeon_cs_chunk *relocs_chunk; unsigned idx; *cs_reloc = NULL; - if (p->chunk_relocs_idx == -1) { + if (p->chunk_relocs == NULL) { DRM_ERROR("No relocation chunk !\n"); return -EINVAL; } - relocs_chunk = &p->chunks[p->chunk_relocs_idx]; + relocs_chunk = p->chunk_relocs; idx = p->dma_reloc_idx; if (idx >= p->nrelocs) { DRM_ERROR("Relocs at %d after relocations chunk end %d !\n", idx, p->nrelocs); return -EINVAL; } - *cs_reloc = p->relocs_ptr[idx]; + *cs_reloc = &p->relocs[idx]; p->dma_reloc_idx++; return 0; } @@ -2472,8 +2472,8 @@ int r600_dma_cs_next_reloc(struct radeon_cs_parser *p, **/ int r600_dma_cs_parse(struct radeon_cs_parser *p) { - struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx]; - struct radeon_cs_reloc *src_reloc, *dst_reloc; + struct radeon_cs_chunk *ib_chunk = p->chunk_ib; + struct radeon_bo_list *src_reloc, *dst_reloc; u32 header, cmd, count, tiled; volatile u32 *ib = p->ib.ptr; u32 idx, idx_value; @@ -2619,7 +2619,7 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("Unknown packet type %d at %d !\n", cmd, idx); return -EINVAL; } - } while (p->idx < p->chunks[p->chunk_ib_idx].length_dw); + } while (p->idx < p->chunk_ib->length_dw); #if 0 for (r = 0; r < p->ib->length_dw; r++) { printk(KERN_INFO "%05d 0x%08X\n", r, p->ib.ptr[r]); diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 3207bb60715e..54529b837afa 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -450,6 +450,15 @@ struct radeon_mman { #endif }; +struct radeon_bo_list { + struct radeon_bo *robj; + struct ttm_validate_buffer tv; + uint64_t gpu_offset; + unsigned prefered_domains; + unsigned allowed_domains; + uint32_t tiling_flags; +}; + /* bo virtual address in a specific vm */ struct radeon_bo_va { /* protected by bo being reserved */ @@ -920,6 +929,9 @@ struct radeon_vm { struct rb_root va; + /* protecting invalidated and freed */ + spinlock_t status_lock; + /* BOs moved, but not yet updated in the PT */ struct list_head invalidated; @@ -1044,19 +1056,7 @@ void cayman_dma_fini(struct radeon_device *rdev); /* * CS. */ -struct radeon_cs_reloc { - struct drm_gem_object *gobj; - struct radeon_bo *robj; - struct ttm_validate_buffer tv; - uint64_t gpu_offset; - unsigned prefered_domains; - unsigned allowed_domains; - uint32_t tiling_flags; - uint32_t handle; -}; - struct radeon_cs_chunk { - uint32_t chunk_id; uint32_t length_dw; uint32_t *kdata; void __user *user_ptr; @@ -1074,16 +1074,15 @@ struct radeon_cs_parser { unsigned idx; /* relocations */ unsigned nrelocs; - struct radeon_cs_reloc *relocs; - struct radeon_cs_reloc **relocs_ptr; - struct radeon_cs_reloc *vm_bos; + struct radeon_bo_list *relocs; + struct radeon_bo_list *vm_bos; struct list_head validated; unsigned dma_reloc_idx; /* indices of various chunks */ - int chunk_ib_idx; - int chunk_relocs_idx; - int chunk_flags_idx; - int chunk_const_ib_idx; + struct radeon_cs_chunk *chunk_ib; + struct radeon_cs_chunk *chunk_relocs; + struct radeon_cs_chunk *chunk_flags; + struct radeon_cs_chunk *chunk_const_ib; struct radeon_ib ib; struct radeon_ib const_ib; void *track; @@ -1097,7 +1096,7 @@ struct radeon_cs_parser { static inline u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx) { - struct radeon_cs_chunk *ibc = &p->chunks[p->chunk_ib_idx]; + struct radeon_cs_chunk *ibc = p->chunk_ib; if (ibc->kdata) return ibc->kdata[idx]; @@ -2975,7 +2974,7 @@ int radeon_vm_manager_init(struct radeon_device *rdev); void radeon_vm_manager_fini(struct radeon_device *rdev); int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm); void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm); -struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev, +struct radeon_bo_list *radeon_vm_get_bos(struct radeon_device *rdev, struct radeon_vm *vm, struct list_head *head); struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev, @@ -3089,7 +3088,7 @@ bool radeon_cs_packet_next_is_pkt3_nop(struct radeon_cs_parser *p); void radeon_cs_dump_packet(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt); int radeon_cs_packet_next_reloc(struct radeon_cs_parser *p, - struct radeon_cs_reloc **cs_reloc, + struct radeon_bo_list **cs_reloc, int nomm); int r600_cs_common_vline_parse(struct radeon_cs_parser *p, uint32_t *vline_start_end, diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 75f22e5e999f..c830863bc98a 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -77,22 +77,18 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) struct drm_device *ddev = p->rdev->ddev; struct radeon_cs_chunk *chunk; struct radeon_cs_buckets buckets; - unsigned i, j; - bool duplicate, need_mmap_lock = false; + unsigned i; + bool need_mmap_lock = false; int r; - if (p->chunk_relocs_idx == -1) { + if (p->chunk_relocs == NULL) { return 0; } - chunk = &p->chunks[p->chunk_relocs_idx]; + chunk = p->chunk_relocs; p->dma_reloc_idx = 0; /* FIXME: we assume that each relocs use 4 dwords */ p->nrelocs = chunk->length_dw / 4; - p->relocs_ptr = kcalloc(p->nrelocs, sizeof(void *), GFP_KERNEL); - if (p->relocs_ptr == NULL) { - return -ENOMEM; - } - p->relocs = kcalloc(p->nrelocs, sizeof(struct radeon_cs_reloc), GFP_KERNEL); + p->relocs = kcalloc(p->nrelocs, sizeof(struct radeon_bo_list), GFP_KERNEL); if (p->relocs == NULL) { return -ENOMEM; } @@ -101,31 +97,17 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) for (i = 0; i < p->nrelocs; i++) { struct drm_radeon_cs_reloc *r; + struct drm_gem_object *gobj; unsigned priority; - duplicate = false; r = (struct drm_radeon_cs_reloc *)&chunk->kdata[i*4]; - for (j = 0; j < i; j++) { - if (r->handle == p->relocs[j].handle) { - p->relocs_ptr[i] = &p->relocs[j]; - duplicate = true; - break; - } - } - if (duplicate) { - p->relocs[i].handle = 0; - continue; - } - - p->relocs[i].gobj = drm_gem_object_lookup(ddev, p->filp, - r->handle); - if (p->relocs[i].gobj == NULL) { + gobj = drm_gem_object_lookup(ddev, p->filp, r->handle); + if (gobj == NULL) { DRM_ERROR("gem object lookup failed 0x%x\n", r->handle); return -ENOENT; } - p->relocs_ptr[i] = &p->relocs[i]; - p->relocs[i].robj = gem_to_radeon_bo(p->relocs[i].gobj); + p->relocs[i].robj = gem_to_radeon_bo(gobj); /* The userspace buffer priorities are from 0 to 15. A higher * number means the buffer is more important. @@ -184,7 +166,6 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p) p->relocs[i].tv.bo = &p->relocs[i].robj->tbo; p->relocs[i].tv.shared = !r->write_domain; - p->relocs[i].handle = r->handle; radeon_cs_buckets_add(&buckets, &p->relocs[i].tv.head, priority); @@ -251,22 +232,19 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority static int radeon_cs_sync_rings(struct radeon_cs_parser *p) { - int i, r = 0; + struct radeon_bo_list *reloc; + int r; - for (i = 0; i < p->nrelocs; i++) { + list_for_each_entry(reloc, &p->validated, tv.head) { struct reservation_object *resv; - if (!p->relocs[i].robj) - continue; - - resv = p->relocs[i].robj->tbo.resv; + resv = reloc->robj->tbo.resv; r = radeon_sync_resv(p->rdev, &p->ib.sync, resv, - p->relocs[i].tv.shared); - + reloc->tv.shared); if (r) - break; + return r; } - return r; + return 0; } /* XXX: note that this is called from the legacy UMS CS ioctl as well */ @@ -286,10 +264,10 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) p->idx = 0; p->ib.sa_bo = NULL; p->const_ib.sa_bo = NULL; - p->chunk_ib_idx = -1; - p->chunk_relocs_idx = -1; - p->chunk_flags_idx = -1; - p->chunk_const_ib_idx = -1; + p->chunk_ib = NULL; + p->chunk_relocs = NULL; + p->chunk_flags = NULL; + p->chunk_const_ib = NULL; p->chunks_array = kcalloc(cs->num_chunks, sizeof(uint64_t), GFP_KERNEL); if (p->chunks_array == NULL) { return -ENOMEM; @@ -316,24 +294,23 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) return -EFAULT; } p->chunks[i].length_dw = user_chunk.length_dw; - p->chunks[i].chunk_id = user_chunk.chunk_id; - if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_RELOCS) { - p->chunk_relocs_idx = i; + if (user_chunk.chunk_id == RADEON_CHUNK_ID_RELOCS) { + p->chunk_relocs = &p->chunks[i]; } - if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_IB) { - p->chunk_ib_idx = i; + if (user_chunk.chunk_id == RADEON_CHUNK_ID_IB) { + p->chunk_ib = &p->chunks[i]; /* zero length IB isn't useful */ if (p->chunks[i].length_dw == 0) return -EINVAL; } - if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_CONST_IB) { - p->chunk_const_ib_idx = i; + if (user_chunk.chunk_id == RADEON_CHUNK_ID_CONST_IB) { + p->chunk_const_ib = &p->chunks[i]; /* zero length CONST IB isn't useful */ if (p->chunks[i].length_dw == 0) return -EINVAL; } - if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) { - p->chunk_flags_idx = i; + if (user_chunk.chunk_id == RADEON_CHUNK_ID_FLAGS) { + p->chunk_flags = &p->chunks[i]; /* zero length flags aren't useful */ if (p->chunks[i].length_dw == 0) return -EINVAL; @@ -342,10 +319,10 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) size = p->chunks[i].length_dw; cdata = (void __user *)(unsigned long)user_chunk.chunk_data; p->chunks[i].user_ptr = cdata; - if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_CONST_IB) + if (user_chunk.chunk_id == RADEON_CHUNK_ID_CONST_IB) continue; - if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_IB) { + if (user_chunk.chunk_id == RADEON_CHUNK_ID_IB) { if (!p->rdev || !(p->rdev->flags & RADEON_IS_AGP)) continue; } @@ -358,7 +335,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) if (copy_from_user(p->chunks[i].kdata, cdata, size)) { return -EFAULT; } - if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) { + if (user_chunk.chunk_id == RADEON_CHUNK_ID_FLAGS) { p->cs_flags = p->chunks[i].kdata[0]; if (p->chunks[i].length_dw > 1) ring = p->chunks[i].kdata[1]; @@ -399,8 +376,8 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data) static int cmp_size_smaller_first(void *priv, struct list_head *a, struct list_head *b) { - struct radeon_cs_reloc *la = list_entry(a, struct radeon_cs_reloc, tv.head); - struct radeon_cs_reloc *lb = list_entry(b, struct radeon_cs_reloc, tv.head); + struct radeon_bo_list *la = list_entry(a, struct radeon_bo_list, tv.head); + struct radeon_bo_list *lb = list_entry(b, struct radeon_bo_list, tv.head); /* Sort A before B if A is smaller. */ return (int)la->robj->tbo.num_pages - (int)lb->robj->tbo.num_pages; @@ -441,13 +418,15 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error, bo if (parser->relocs != NULL) { for (i = 0; i < parser->nrelocs; i++) { - if (parser->relocs[i].gobj) - drm_gem_object_unreference_unlocked(parser->relocs[i].gobj); + struct radeon_bo *bo = parser->relocs[i].robj; + if (bo == NULL) + continue; + + drm_gem_object_unreference_unlocked(&bo->gem_base); } } kfree(parser->track); kfree(parser->relocs); - kfree(parser->relocs_ptr); drm_free_large(parser->vm_bos); for (i = 0; i < parser->nchunks; i++) drm_free_large(parser->chunks[i].kdata); @@ -462,7 +441,7 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev, { int r; - if (parser->chunk_ib_idx == -1) + if (parser->chunk_ib == NULL) return 0; if (parser->cs_flags & RADEON_CS_USE_VM) @@ -505,9 +484,6 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p, if (r) return r; - radeon_sync_resv(p->rdev, &p->ib.sync, vm->page_directory->tbo.resv, - true); - r = radeon_vm_clear_freed(rdev, vm); if (r) return r; @@ -525,10 +501,6 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p, for (i = 0; i < p->nrelocs; i++) { struct radeon_bo *bo; - /* ignore duplicates */ - if (p->relocs_ptr[i] != &p->relocs[i]) - continue; - bo = p->relocs[i].robj; bo_va = radeon_vm_bo_find(vm, bo); if (bo_va == NULL) { @@ -553,7 +525,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, struct radeon_vm *vm = &fpriv->vm; int r; - if (parser->chunk_ib_idx == -1) + if (parser->chunk_ib == NULL) return 0; if ((parser->cs_flags & RADEON_CS_USE_VM) == 0) return 0; @@ -587,7 +559,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, } if ((rdev->family >= CHIP_TAHITI) && - (parser->chunk_const_ib_idx != -1)) { + (parser->chunk_const_ib != NULL)) { r = radeon_ib_schedule(rdev, &parser->ib, &parser->const_ib, true); } else { r = radeon_ib_schedule(rdev, &parser->ib, NULL, true); @@ -614,7 +586,7 @@ static int radeon_cs_ib_fill(struct radeon_device *rdev, struct radeon_cs_parser struct radeon_vm *vm = NULL; int r; - if (parser->chunk_ib_idx == -1) + if (parser->chunk_ib == NULL) return 0; if (parser->cs_flags & RADEON_CS_USE_VM) { @@ -622,8 +594,8 @@ static int radeon_cs_ib_fill(struct radeon_device *rdev, struct radeon_cs_parser vm = &fpriv->vm; if ((rdev->family >= CHIP_TAHITI) && - (parser->chunk_const_ib_idx != -1)) { - ib_chunk = &parser->chunks[parser->chunk_const_ib_idx]; + (parser->chunk_const_ib != NULL)) { + ib_chunk = parser->chunk_const_ib; if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) { DRM_ERROR("cs IB CONST too big: %d\n", ib_chunk->length_dw); return -EINVAL; @@ -642,13 +614,13 @@ static int radeon_cs_ib_fill(struct radeon_device *rdev, struct radeon_cs_parser return -EFAULT; } - ib_chunk = &parser->chunks[parser->chunk_ib_idx]; + ib_chunk = parser->chunk_ib; if (ib_chunk->length_dw > RADEON_IB_VM_MAX_SIZE) { DRM_ERROR("cs IB too big: %d\n", ib_chunk->length_dw); return -EINVAL; } } - ib_chunk = &parser->chunks[parser->chunk_ib_idx]; + ib_chunk = parser->chunk_ib; r = radeon_ib_get(rdev, parser->ring, &parser->ib, vm, ib_chunk->length_dw * 4); @@ -740,7 +712,7 @@ int radeon_cs_packet_parse(struct radeon_cs_parser *p, struct radeon_cs_packet *pkt, unsigned idx) { - struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx]; + struct radeon_cs_chunk *ib_chunk = p->chunk_ib; struct radeon_device *rdev = p->rdev; uint32_t header; @@ -834,7 +806,7 @@ void radeon_cs_dump_packet(struct radeon_cs_parser *p, * GPU offset using the provided start. **/ int radeon_cs_packet_next_reloc(struct radeon_cs_parser *p, - struct radeon_cs_reloc **cs_reloc, + struct radeon_bo_list **cs_reloc, int nomm) { struct radeon_cs_chunk *relocs_chunk; @@ -842,12 +814,12 @@ int radeon_cs_packet_next_reloc(struct radeon_cs_parser *p, unsigned idx; int r; - if (p->chunk_relocs_idx == -1) { + if (p->chunk_relocs == NULL) { DRM_ERROR("No relocation chunk !\n"); return -EINVAL; } *cs_reloc = NULL; - relocs_chunk = &p->chunks[p->chunk_relocs_idx]; + relocs_chunk = p->chunk_relocs; r = radeon_cs_packet_parse(p, &p3reloc, p->idx); if (r) return r; @@ -873,6 +845,6 @@ int radeon_cs_packet_next_reloc(struct radeon_cs_parser *p, (u64)relocs_chunk->kdata[idx + 3] << 32; (*cs_reloc)->gpu_offset |= relocs_chunk->kdata[idx + 0]; } else - *cs_reloc = p->relocs_ptr[(idx / 4)]; + *cs_reloc = &p->relocs[(idx / 4)]; return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c index 85f38ee11888..45e54060ee97 100644 --- a/drivers/gpu/drm/radeon/radeon_cursor.c +++ b/drivers/gpu/drm/radeon/radeon_cursor.c @@ -227,11 +227,24 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc, return ret; } -static void radeon_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj, - uint64_t gpu_addr, int hot_x, int hot_y) +static int radeon_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj) { struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); struct radeon_device *rdev = crtc->dev->dev_private; + struct radeon_bo *robj = gem_to_radeon_bo(obj); + uint64_t gpu_addr; + int ret; + + ret = radeon_bo_reserve(robj, false); + if (unlikely(ret != 0)) + goto fail; + /* Only 27 bit offset for legacy cursor */ + ret = radeon_bo_pin_restricted(robj, RADEON_GEM_DOMAIN_VRAM, + ASIC_IS_AVIVO(rdev) ? 0 : 1 << 27, + &gpu_addr); + radeon_bo_unreserve(robj); + if (ret) + goto fail; if (ASIC_IS_DCE4(rdev)) { WREG32(EVERGREEN_CUR_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset, @@ -253,18 +266,12 @@ static void radeon_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj, WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset, radeon_crtc->legacy_cursor_offset); } - if (hot_x != radeon_crtc->cursor_hot_x || - hot_y != radeon_crtc->cursor_hot_y) { - int x, y; - - x = radeon_crtc->cursor_x + radeon_crtc->cursor_hot_x - hot_x; - y = radeon_crtc->cursor_y + radeon_crtc->cursor_hot_y - hot_y; + return 0; - radeon_cursor_move_locked(crtc, x, y); +fail: + drm_gem_object_unreference_unlocked(obj); - radeon_crtc->cursor_hot_x = hot_x; - radeon_crtc->cursor_hot_y = hot_y; - } + return ret; } int radeon_crtc_cursor_set2(struct drm_crtc *crtc, @@ -276,10 +283,7 @@ int radeon_crtc_cursor_set2(struct drm_crtc *crtc, int32_t hot_y) { struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); - struct radeon_device *rdev = crtc->dev->dev_private; struct drm_gem_object *obj; - struct radeon_bo *robj; - uint64_t gpu_addr; int ret; if (!handle) { @@ -301,41 +305,76 @@ int radeon_crtc_cursor_set2(struct drm_crtc *crtc, return -ENOENT; } - robj = gem_to_radeon_bo(obj); - ret = radeon_bo_reserve(robj, false); - if (unlikely(ret != 0)) - goto fail; - /* Only 27 bit offset for legacy cursor */ - ret = radeon_bo_pin_restricted(robj, RADEON_GEM_DOMAIN_VRAM, - ASIC_IS_AVIVO(rdev) ? 0 : 1 << 27, - &gpu_addr); - radeon_bo_unreserve(robj); - if (ret) - goto fail; - radeon_crtc->cursor_width = width; radeon_crtc->cursor_height = height; radeon_lock_cursor(crtc, true); - radeon_set_cursor(crtc, obj, gpu_addr, hot_x, hot_y); - radeon_show_cursor(crtc); + + if (hot_x != radeon_crtc->cursor_hot_x || + hot_y != radeon_crtc->cursor_hot_y) { + int x, y; + + x = radeon_crtc->cursor_x + radeon_crtc->cursor_hot_x - hot_x; + y = radeon_crtc->cursor_y + radeon_crtc->cursor_hot_y - hot_y; + + radeon_cursor_move_locked(crtc, x, y); + + radeon_crtc->cursor_hot_x = hot_x; + radeon_crtc->cursor_hot_y = hot_y; + } + + ret = radeon_set_cursor(crtc, obj); + + if (ret) + DRM_ERROR("radeon_set_cursor returned %d, not changing cursor\n", + ret); + else + radeon_show_cursor(crtc); + radeon_lock_cursor(crtc, false); unpin: if (radeon_crtc->cursor_bo) { - robj = gem_to_radeon_bo(radeon_crtc->cursor_bo); + struct radeon_bo *robj = gem_to_radeon_bo(radeon_crtc->cursor_bo); ret = radeon_bo_reserve(robj, false); if (likely(ret == 0)) { radeon_bo_unpin(robj); radeon_bo_unreserve(robj); } - drm_gem_object_unreference_unlocked(radeon_crtc->cursor_bo); + if (radeon_crtc->cursor_bo != obj) + drm_gem_object_unreference_unlocked(radeon_crtc->cursor_bo); } radeon_crtc->cursor_bo = obj; return 0; -fail: - drm_gem_object_unreference_unlocked(obj); +} - return ret; +/** + * radeon_cursor_reset - Re-set the current cursor, if any. + * + * @crtc: drm crtc + * + * If the CRTC passed in currently has a cursor assigned, this function + * makes sure it's visible. + */ +void radeon_cursor_reset(struct drm_crtc *crtc) +{ + struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc); + int ret; + + if (radeon_crtc->cursor_bo) { + radeon_lock_cursor(crtc, true); + + radeon_cursor_move_locked(crtc, radeon_crtc->cursor_x, + radeon_crtc->cursor_y); + + ret = radeon_set_cursor(crtc, radeon_crtc->cursor_bo); + if (ret) + DRM_ERROR("radeon_set_cursor returned %d, not showing " + "cursor\n", ret); + else + radeon_show_cursor(crtc); + + radeon_lock_cursor(crtc, false); + } } diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c index 0ea1db83d573..29b9220ec399 100644 --- a/drivers/gpu/drm/radeon/radeon_fb.c +++ b/drivers/gpu/drm/radeon/radeon_fb.c @@ -48,10 +48,40 @@ struct radeon_fbdev { struct radeon_device *rdev; }; +/** + * radeon_fb_helper_set_par - Hide cursor on CRTCs used by fbdev. + * + * @info: fbdev info + * + * This function hides the cursor on all CRTCs used by fbdev. + */ +static int radeon_fb_helper_set_par(struct fb_info *info) +{ + int ret; + + ret = drm_fb_helper_set_par(info); + + /* XXX: with universal plane support fbdev will automatically disable + * all non-primary planes (including the cursor) + */ + if (ret == 0) { + struct drm_fb_helper *fb_helper = info->par; + int i; + + for (i = 0; i < fb_helper->crtc_count; i++) { + struct drm_crtc *crtc = fb_helper->crtc_info[i].mode_set.crtc; + + radeon_crtc_cursor_set2(crtc, NULL, 0, 0, 0, 0, 0); + } + } + + return ret; +} + static struct fb_ops radeonfb_ops = { .owner = THIS_MODULE, .fb_check_var = drm_fb_helper_check_var, - .fb_set_par = drm_fb_helper_set_par, + .fb_set_par = radeon_fb_helper_set_par, .fb_fillrect = cfb_fillrect, .fb_copyarea = cfb_copyarea, .fb_imageblit = cfb_imageblit, diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 12cfaeac1205..fe48f229043e 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -548,7 +548,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, struct radeon_bo_va *bo_va) { struct ttm_validate_buffer tv, *entry; - struct radeon_cs_reloc *vm_bos; + struct radeon_bo_list *vm_bos; struct ww_acquire_ctx ticket; struct list_head list; unsigned domain; @@ -564,7 +564,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, if (!vm_bos) return; - r = ttm_eu_reserve_buffers(&ticket, &list, true); + r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL); if (r) goto error_free; diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index f4dd26ae33e5..3cf9c1fa6475 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -800,6 +800,8 @@ int radeon_get_vblank_timestamp_kms(struct drm_device *dev, int crtc, /* Get associated drm_crtc: */ drmcrtc = &rdev->mode_info.crtcs[crtc]->base; + if (!drmcrtc) + return -EINVAL; /* Helper routine in DRM core does all the work: */ return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc, max_error, diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c index cafb1ccf2ec3..678b4386540d 100644 --- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c +++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c @@ -1054,6 +1054,7 @@ static int radeon_crtc_mode_set(struct drm_crtc *crtc, DRM_ERROR("Mode need scaling but only first crtc can do that.\n"); } } + radeon_cursor_reset(crtc); return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index f3d87cdd5c9d..390db897f322 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -818,6 +818,7 @@ extern int radeon_crtc_cursor_set2(struct drm_crtc *crtc, int32_t hot_y); extern int radeon_crtc_cursor_move(struct drm_crtc *crtc, int x, int y); +extern void radeon_cursor_reset(struct drm_crtc *crtc); extern int radeon_get_crtc_scanoutpos(struct drm_device *dev, int crtc, unsigned int flags, diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 87b00d902bf7..7d68223eb469 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -233,6 +233,13 @@ int radeon_bo_create(struct radeon_device *rdev, if (!(rdev->flags & RADEON_IS_PCIE)) bo->flags &= ~(RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC); +#ifdef CONFIG_X86_32 + /* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit + * See https://bugs.freedesktop.org/show_bug.cgi?id=84627 + */ + bo->flags &= ~RADEON_GEM_GTT_WC; +#endif + radeon_ttm_placement_from_domain(bo, domain); /* Kernel allocation are uninterruptible */ down_read(&rdev->pm.mclk_lock); @@ -502,19 +509,20 @@ int radeon_bo_list_validate(struct radeon_device *rdev, struct ww_acquire_ctx *ticket, struct list_head *head, int ring) { - struct radeon_cs_reloc *lobj; - struct radeon_bo *bo; + struct radeon_bo_list *lobj; + struct list_head duplicates; int r; u64 bytes_moved = 0, initial_bytes_moved; u64 bytes_moved_threshold = radeon_bo_get_threshold_for_moves(rdev); - r = ttm_eu_reserve_buffers(ticket, head, true); + INIT_LIST_HEAD(&duplicates); + r = ttm_eu_reserve_buffers(ticket, head, true, &duplicates); if (unlikely(r != 0)) { return r; } list_for_each_entry(lobj, head, tv.head) { - bo = lobj->robj; + struct radeon_bo *bo = lobj->robj; if (!bo->pin_count) { u32 domain = lobj->prefered_domains; u32 allowed = lobj->allowed_domains; @@ -562,6 +570,12 @@ int radeon_bo_list_validate(struct radeon_device *rdev, lobj->gpu_offset = radeon_bo_gpu_offset(bo); lobj->tiling_flags = bo->tiling_flags; } + + list_for_each_entry(lobj, &duplicates, tv.head) { + lobj->gpu_offset = radeon_bo_gpu_offset(lobj->robj); + lobj->tiling_flags = lobj->robj->tiling_flags; + } + return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_trace.h b/drivers/gpu/drm/radeon/radeon_trace.h index 9db74a96ef61..ce075cb08cb2 100644 --- a/drivers/gpu/drm/radeon/radeon_trace.h +++ b/drivers/gpu/drm/radeon/radeon_trace.h @@ -38,7 +38,7 @@ TRACE_EVENT(radeon_cs, TP_fast_assign( __entry->ring = p->ring; - __entry->dw = p->chunks[p->chunk_ib_idx].length_dw; + __entry->dw = p->chunk_ib->length_dw; __entry->fences = radeon_fence_count_emitted( p->rdev, p->ring); ), diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index cbe7b32d181c..d02aa1d0f588 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -196,7 +196,7 @@ static void radeon_evict_flags(struct ttm_buffer_object *bo, rbo = container_of(bo, struct radeon_bo, tbo); switch (bo->mem.mem_type) { case TTM_PL_VRAM: - if (rbo->rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ready == false) + if (rbo->rdev->ring[radeon_copy_ring_index(rbo->rdev)].ready == false) radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_CPU); else if (rbo->rdev->mc.visible_vram_size < rbo->rdev->mc.real_vram_size && bo->mem.start < (rbo->rdev->mc.visible_vram_size >> PAGE_SHIFT)) { diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 11b662469253..c10b2aec6450 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -488,12 +488,12 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p, unsigned buf_sizes[], bool *has_msg_cmd) { struct radeon_cs_chunk *relocs_chunk; - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; unsigned idx, cmd, offset; uint64_t start, end; int r; - relocs_chunk = &p->chunks[p->chunk_relocs_idx]; + relocs_chunk = p->chunk_relocs; offset = radeon_get_ib_value(p, data0); idx = radeon_get_ib_value(p, data1); if (idx >= relocs_chunk->length_dw) { @@ -502,7 +502,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p, return -EINVAL; } - reloc = p->relocs_ptr[(idx / 4)]; + reloc = &p->relocs[(idx / 4)]; start = reloc->gpu_offset; end = start + radeon_bo_size(reloc->robj); start += offset; @@ -610,13 +610,13 @@ int radeon_uvd_cs_parse(struct radeon_cs_parser *p) [0x00000003] = 2048, }; - if (p->chunks[p->chunk_ib_idx].length_dw % 16) { + if (p->chunk_ib->length_dw % 16) { DRM_ERROR("UVD IB length (%d) not 16 dwords aligned!\n", - p->chunks[p->chunk_ib_idx].length_dw); + p->chunk_ib->length_dw); return -EINVAL; } - if (p->chunk_relocs_idx == -1) { + if (p->chunk_relocs == NULL) { DRM_ERROR("No relocation chunk !\n"); return -EINVAL; } @@ -640,7 +640,7 @@ int radeon_uvd_cs_parse(struct radeon_cs_parser *p) DRM_ERROR("Unknown packet type %d !\n", pkt.type); return -EINVAL; } - } while (p->idx < p->chunks[p->chunk_ib_idx].length_dw); + } while (p->idx < p->chunk_ib->length_dw); if (!has_msg_cmd) { DRM_ERROR("UVD-IBs need a msg command!\n"); diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c index 9e85757d5599..976fe432f4e2 100644 --- a/drivers/gpu/drm/radeon/radeon_vce.c +++ b/drivers/gpu/drm/radeon/radeon_vce.c @@ -453,11 +453,11 @@ int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi, unsigned size) { struct radeon_cs_chunk *relocs_chunk; - struct radeon_cs_reloc *reloc; + struct radeon_bo_list *reloc; uint64_t start, end, offset; unsigned idx; - relocs_chunk = &p->chunks[p->chunk_relocs_idx]; + relocs_chunk = p->chunk_relocs; offset = radeon_get_ib_value(p, lo); idx = radeon_get_ib_value(p, hi); @@ -467,7 +467,7 @@ int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi, return -EINVAL; } - reloc = p->relocs_ptr[(idx / 4)]; + reloc = &p->relocs[(idx / 4)]; start = reloc->gpu_offset; end = start + radeon_bo_size(reloc->robj); start += offset; @@ -534,7 +534,7 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p) uint32_t *size = &tmp; int i, r; - while (p->idx < p->chunks[p->chunk_ib_idx].length_dw) { + while (p->idx < p->chunk_ib->length_dw) { uint32_t len = radeon_get_ib_value(p, p->idx); uint32_t cmd = radeon_get_ib_value(p, p->idx + 1); diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index 0b10f3a03ce2..cde48c42b30a 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -125,41 +125,37 @@ void radeon_vm_manager_fini(struct radeon_device *rdev) * Add the page directory to the list of BOs to * validate for command submission (cayman+). */ -struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev, +struct radeon_bo_list *radeon_vm_get_bos(struct radeon_device *rdev, struct radeon_vm *vm, struct list_head *head) { - struct radeon_cs_reloc *list; + struct radeon_bo_list *list; unsigned i, idx; list = drm_malloc_ab(vm->max_pde_used + 2, - sizeof(struct radeon_cs_reloc)); + sizeof(struct radeon_bo_list)); if (!list) return NULL; /* add the vm page table to the list */ - list[0].gobj = NULL; list[0].robj = vm->page_directory; list[0].prefered_domains = RADEON_GEM_DOMAIN_VRAM; list[0].allowed_domains = RADEON_GEM_DOMAIN_VRAM; list[0].tv.bo = &vm->page_directory->tbo; list[0].tv.shared = true; list[0].tiling_flags = 0; - list[0].handle = 0; list_add(&list[0].tv.head, head); for (i = 0, idx = 1; i <= vm->max_pde_used; i++) { if (!vm->page_tables[i].bo) continue; - list[idx].gobj = NULL; list[idx].robj = vm->page_tables[i].bo; list[idx].prefered_domains = RADEON_GEM_DOMAIN_VRAM; list[idx].allowed_domains = RADEON_GEM_DOMAIN_VRAM; list[idx].tv.bo = &list[idx].robj->tbo; list[idx].tv.shared = true; list[idx].tiling_flags = 0; - list[idx].handle = 0; list_add(&list[idx++].tv.head, head); } @@ -491,7 +487,9 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev, tmp->vm = vm; tmp->addr = bo_va->addr; tmp->bo = radeon_bo_ref(bo_va->bo); + spin_lock(&vm->status_lock); list_add(&tmp->vm_status, &vm->freed); + spin_unlock(&vm->status_lock); } interval_tree_remove(&bo_va->it, &vm->va); @@ -802,11 +800,11 @@ static void radeon_vm_frag_ptes(struct radeon_device *rdev, * * Global and local mutex must be locked! */ -static void radeon_vm_update_ptes(struct radeon_device *rdev, - struct radeon_vm *vm, - struct radeon_ib *ib, - uint64_t start, uint64_t end, - uint64_t dst, uint32_t flags) +static int radeon_vm_update_ptes(struct radeon_device *rdev, + struct radeon_vm *vm, + struct radeon_ib *ib, + uint64_t start, uint64_t end, + uint64_t dst, uint32_t flags) { uint64_t mask = RADEON_VM_PTE_COUNT - 1; uint64_t last_pte = ~0, last_dst = ~0; @@ -819,8 +817,12 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev, struct radeon_bo *pt = vm->page_tables[pt_idx].bo; unsigned nptes; uint64_t pte; + int r; radeon_sync_resv(rdev, &ib->sync, pt->tbo.resv, true); + r = reservation_object_reserve_shared(pt->tbo.resv); + if (r) + return r; if ((addr & ~mask) == (end & ~mask)) nptes = end - addr; @@ -854,6 +856,8 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev, last_pte + 8 * count, last_dst, flags); } + + return 0; } /** @@ -878,7 +882,7 @@ static void radeon_vm_fence_pts(struct radeon_vm *vm, end >>= radeon_vm_block_size; for (i = start; i <= end; ++i) - radeon_bo_fence(vm->page_tables[i].bo, fence, false); + radeon_bo_fence(vm->page_tables[i].bo, fence, true); } /** @@ -911,7 +915,9 @@ int radeon_vm_bo_update(struct radeon_device *rdev, return -EINVAL; } + spin_lock(&vm->status_lock); list_del_init(&bo_va->vm_status); + spin_unlock(&vm->status_lock); bo_va->flags &= ~RADEON_VM_PAGE_VALID; bo_va->flags &= ~RADEON_VM_PAGE_SYSTEM; @@ -987,9 +993,13 @@ int radeon_vm_bo_update(struct radeon_device *rdev, radeon_sync_fence(&ib.sync, vm->ids[i].last_id_use); } - radeon_vm_update_ptes(rdev, vm, &ib, bo_va->it.start, - bo_va->it.last + 1, addr, - radeon_vm_page_flags(bo_va->flags)); + r = radeon_vm_update_ptes(rdev, vm, &ib, bo_va->it.start, + bo_va->it.last + 1, addr, + radeon_vm_page_flags(bo_va->flags)); + if (r) { + radeon_ib_free(rdev, &ib); + return r; + } radeon_asic_vm_pad_ib(rdev, &ib); WARN_ON(ib.length_dw > ndw); @@ -1022,17 +1032,25 @@ int radeon_vm_bo_update(struct radeon_device *rdev, int radeon_vm_clear_freed(struct radeon_device *rdev, struct radeon_vm *vm) { - struct radeon_bo_va *bo_va, *tmp; + struct radeon_bo_va *bo_va; int r; - list_for_each_entry_safe(bo_va, tmp, &vm->freed, vm_status) { + spin_lock(&vm->status_lock); + while (!list_empty(&vm->freed)) { + bo_va = list_first_entry(&vm->freed, + struct radeon_bo_va, vm_status); + spin_unlock(&vm->status_lock); + r = radeon_vm_bo_update(rdev, bo_va, NULL); radeon_bo_unref(&bo_va->bo); radeon_fence_unref(&bo_va->last_pt_update); kfree(bo_va); if (r) return r; + + spin_lock(&vm->status_lock); } + spin_unlock(&vm->status_lock); return 0; } @@ -1051,14 +1069,23 @@ int radeon_vm_clear_freed(struct radeon_device *rdev, int radeon_vm_clear_invalids(struct radeon_device *rdev, struct radeon_vm *vm) { - struct radeon_bo_va *bo_va, *tmp; + struct radeon_bo_va *bo_va; int r; - list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, vm_status) { + spin_lock(&vm->status_lock); + while (!list_empty(&vm->invalidated)) { + bo_va = list_first_entry(&vm->invalidated, + struct radeon_bo_va, vm_status); + spin_unlock(&vm->status_lock); + r = radeon_vm_bo_update(rdev, bo_va, NULL); if (r) return r; + + spin_lock(&vm->status_lock); } + spin_unlock(&vm->status_lock); + return 0; } @@ -1081,6 +1108,7 @@ void radeon_vm_bo_rmv(struct radeon_device *rdev, mutex_lock(&vm->mutex); interval_tree_remove(&bo_va->it, &vm->va); + spin_lock(&vm->status_lock); list_del(&bo_va->vm_status); if (bo_va->addr) { @@ -1090,6 +1118,7 @@ void radeon_vm_bo_rmv(struct radeon_device *rdev, radeon_fence_unref(&bo_va->last_pt_update); kfree(bo_va); } + spin_unlock(&vm->status_lock); mutex_unlock(&vm->mutex); } @@ -1110,10 +1139,10 @@ void radeon_vm_bo_invalidate(struct radeon_device *rdev, list_for_each_entry(bo_va, &bo->va, bo_list) { if (bo_va->addr) { - mutex_lock(&bo_va->vm->mutex); + spin_lock(&bo_va->vm->status_lock); list_del(&bo_va->vm_status); list_add(&bo_va->vm_status, &bo_va->vm->invalidated); - mutex_unlock(&bo_va->vm->mutex); + spin_unlock(&bo_va->vm->status_lock); } } } @@ -1141,6 +1170,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm) } mutex_init(&vm->mutex); vm->va = RB_ROOT; + spin_lock_init(&vm->status_lock); INIT_LIST_HEAD(&vm->invalidated); INIT_LIST_HEAD(&vm->freed); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index cf4c420b5572..32e354b8b0ab 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -5893,7 +5893,7 @@ static void si_fan_ctrl_set_static_mode(struct radeon_device *rdev, u32 mode) tmp |= TMIN(0); WREG32(CG_FDO_CTRL2, tmp); - tmp = RREG32(CG_FDO_CTRL2) & FDO_PWM_MODE_MASK; + tmp = RREG32(CG_FDO_CTRL2) & ~FDO_PWM_MODE_MASK; tmp |= FDO_PWM_MODE(mode); WREG32(CG_FDO_CTRL2, tmp); } @@ -6098,7 +6098,7 @@ static int si_fan_ctrl_set_fan_speed_rpm(struct radeon_device *rdev, tmp |= TARGET_PERIOD(tach_period); WREG32(CG_TACH_CTRL, tmp); - si_fan_ctrl_set_static_mode(rdev, FDO_PWM_MODE_STATIC); + si_fan_ctrl_set_static_mode(rdev, FDO_PWM_MODE_STATIC_RPM); return 0; } @@ -6114,7 +6114,7 @@ static void si_fan_ctrl_set_default_mode(struct radeon_device *rdev) tmp |= FDO_PWM_MODE(si_pi->fan_ctrl_default_mode); WREG32(CG_FDO_CTRL2, tmp); - tmp = RREG32(CG_FDO_CTRL2) & TMIN_MASK; + tmp = RREG32(CG_FDO_CTRL2) & ~TMIN_MASK; tmp |= TMIN(si_pi->t_min); WREG32(CG_FDO_CTRL2, tmp); si_pi->fan_ctrl_is_in_default_mode = true; diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h index c549c16a4fe4..4069be89e585 100644 --- a/drivers/gpu/drm/radeon/sid.h +++ b/drivers/gpu/drm/radeon/sid.h @@ -208,18 +208,18 @@ #define CG_FDO_CTRL0 0x754 #define FDO_STATIC_DUTY(x) ((x) << 0) -#define FDO_STATIC_DUTY_MASK 0x0000000F +#define FDO_STATIC_DUTY_MASK 0x000000FF #define FDO_STATIC_DUTY_SHIFT 0 #define CG_FDO_CTRL1 0x758 #define FMAX_DUTY100(x) ((x) << 0) -#define FMAX_DUTY100_MASK 0x0000000F +#define FMAX_DUTY100_MASK 0x000000FF #define FMAX_DUTY100_SHIFT 0 #define CG_FDO_CTRL2 0x75C #define TMIN(x) ((x) << 0) -#define TMIN_MASK 0x0000000F +#define TMIN_MASK 0x000000FF #define TMIN_SHIFT 0 #define FDO_PWM_MODE(x) ((x) << 11) -#define FDO_PWM_MODE_MASK (3 << 11) +#define FDO_PWM_MODE_MASK (7 << 11) #define FDO_PWM_MODE_SHIFT 11 #define TACH_PWM_RESP_RATE(x) ((x) << 25) #define TACH_PWM_RESP_RATE_MASK (0x7f << 25) diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig new file mode 100644 index 000000000000..ca9f085efa92 --- /dev/null +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -0,0 +1,17 @@ +config DRM_ROCKCHIP + tristate "DRM Support for Rockchip" + depends on DRM && ROCKCHIP_IOMMU + select DRM_KMS_HELPER + select DRM_KMS_FB_HELPER + select DRM_PANEL + select FB_CFB_FILLRECT + select FB_CFB_COPYAREA + select FB_CFB_IMAGEBLIT + select VT_HW_CONSOLE_BINDING if FRAMEBUFFER_CONSOLE + select VIDEOMODE_HELPERS + help + Choose this option if you have a Rockchip soc chipset. + This driver provides kernel mode setting and buffer + management to userspace. This driver does not provide + 2D or 3D acceleration; acceleration is performed by other + IP found on the SoC. diff --git a/drivers/gpu/drm/rockchip/Makefile b/drivers/gpu/drm/rockchip/Makefile new file mode 100644 index 000000000000..2cb0672f57ed --- /dev/null +++ b/drivers/gpu/drm/rockchip/Makefile @@ -0,0 +1,8 @@ +# +# Makefile for the drm device driver. This driver provides support for the +# Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. + +rockchipdrm-y := rockchip_drm_drv.o rockchip_drm_fb.o rockchip_drm_fbdev.o \ + rockchip_drm_gem.o + +obj-$(CONFIG_DRM_ROCKCHIP) += rockchipdrm.o rockchip_drm_vop.o diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c new file mode 100644 index 000000000000..a798c7c71f91 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -0,0 +1,551 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * based on exynos_drm_drv.c + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <asm/dma-iommu.h> + +#include <drm/drmP.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_fb_helper.h> +#include <linux/dma-mapping.h> +#include <linux/pm_runtime.h> +#include <linux/of_graph.h> +#include <linux/component.h> + +#include "rockchip_drm_drv.h" +#include "rockchip_drm_fb.h" +#include "rockchip_drm_fbdev.h" +#include "rockchip_drm_gem.h" + +#define DRIVER_NAME "rockchip" +#define DRIVER_DESC "RockChip Soc DRM" +#define DRIVER_DATE "20140818" +#define DRIVER_MAJOR 1 +#define DRIVER_MINOR 0 + +/* + * Attach a (component) device to the shared drm dma mapping from master drm + * device. This is used by the VOPs to map GEM buffers to a common DMA + * mapping. + */ +int rockchip_drm_dma_attach_device(struct drm_device *drm_dev, + struct device *dev) +{ + struct dma_iommu_mapping *mapping = drm_dev->dev->archdata.mapping; + int ret; + + ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); + if (ret) + return ret; + + dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); + + return arm_iommu_attach_device(dev, mapping); +} +EXPORT_SYMBOL_GPL(rockchip_drm_dma_attach_device); + +void rockchip_drm_dma_detach_device(struct drm_device *drm_dev, + struct device *dev) +{ + arm_iommu_detach_device(dev); +} +EXPORT_SYMBOL_GPL(rockchip_drm_dma_detach_device); + +int rockchip_register_crtc_funcs(struct drm_device *dev, + const struct rockchip_crtc_funcs *crtc_funcs, + int pipe) +{ + struct rockchip_drm_private *priv = dev->dev_private; + + if (pipe > ROCKCHIP_MAX_CRTC) + return -EINVAL; + + priv->crtc_funcs[pipe] = crtc_funcs; + + return 0; +} +EXPORT_SYMBOL_GPL(rockchip_register_crtc_funcs); + +void rockchip_unregister_crtc_funcs(struct drm_device *dev, int pipe) +{ + struct rockchip_drm_private *priv = dev->dev_private; + + if (pipe > ROCKCHIP_MAX_CRTC) + return; + + priv->crtc_funcs[pipe] = NULL; +} +EXPORT_SYMBOL_GPL(rockchip_unregister_crtc_funcs); + +static struct drm_crtc *rockchip_crtc_from_pipe(struct drm_device *drm, + int pipe) +{ + struct drm_crtc *crtc; + int i = 0; + + list_for_each_entry(crtc, &drm->mode_config.crtc_list, head) + if (i++ == pipe) + return crtc; + + return NULL; +} + +static int rockchip_drm_crtc_enable_vblank(struct drm_device *dev, int pipe) +{ + struct rockchip_drm_private *priv = dev->dev_private; + struct drm_crtc *crtc = rockchip_crtc_from_pipe(dev, pipe); + + if (crtc && priv->crtc_funcs[pipe] && + priv->crtc_funcs[pipe]->enable_vblank) + return priv->crtc_funcs[pipe]->enable_vblank(crtc); + + return 0; +} + +static void rockchip_drm_crtc_disable_vblank(struct drm_device *dev, int pipe) +{ + struct rockchip_drm_private *priv = dev->dev_private; + struct drm_crtc *crtc = rockchip_crtc_from_pipe(dev, pipe); + + if (crtc && priv->crtc_funcs[pipe] && + priv->crtc_funcs[pipe]->enable_vblank) + priv->crtc_funcs[pipe]->disable_vblank(crtc); +} + +static int rockchip_drm_load(struct drm_device *drm_dev, unsigned long flags) +{ + struct rockchip_drm_private *private; + struct dma_iommu_mapping *mapping; + struct device *dev = drm_dev->dev; + int ret; + + private = devm_kzalloc(drm_dev->dev, sizeof(*private), GFP_KERNEL); + if (!private) + return -ENOMEM; + + drm_dev->dev_private = private; + + drm_mode_config_init(drm_dev); + + rockchip_drm_mode_config_init(drm_dev); + + dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), + GFP_KERNEL); + if (!dev->dma_parms) { + ret = -ENOMEM; + goto err_config_cleanup; + } + + /* TODO(djkurtz): fetch the mapping start/size from somewhere */ + mapping = arm_iommu_create_mapping(&platform_bus_type, 0x00000000, + SZ_2G); + if (IS_ERR(mapping)) { + ret = PTR_ERR(mapping); + goto err_config_cleanup; + } + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); + if (ret) + goto err_release_mapping; + + dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); + + ret = arm_iommu_attach_device(dev, mapping); + if (ret) + goto err_release_mapping; + + /* Try to bind all sub drivers. */ + ret = component_bind_all(dev, drm_dev); + if (ret) + goto err_detach_device; + + /* init kms poll for handling hpd */ + drm_kms_helper_poll_init(drm_dev); + + /* + * enable drm irq mode. + * - with irq_enabled = true, we can use the vblank feature. + */ + drm_dev->irq_enabled = true; + + ret = drm_vblank_init(drm_dev, ROCKCHIP_MAX_CRTC); + if (ret) + goto err_kms_helper_poll_fini; + + /* + * with vblank_disable_allowed = true, vblank interrupt will be disabled + * by drm timer once a current process gives up ownership of + * vblank event.(after drm_vblank_put function is called) + */ + drm_dev->vblank_disable_allowed = true; + + ret = rockchip_drm_fbdev_init(drm_dev); + if (ret) + goto err_vblank_cleanup; + + return 0; +err_vblank_cleanup: + drm_vblank_cleanup(drm_dev); +err_kms_helper_poll_fini: + drm_kms_helper_poll_fini(drm_dev); + component_unbind_all(dev, drm_dev); +err_detach_device: + arm_iommu_detach_device(dev); +err_release_mapping: + arm_iommu_release_mapping(dev->archdata.mapping); +err_config_cleanup: + drm_mode_config_cleanup(drm_dev); + drm_dev->dev_private = NULL; + return ret; +} + +static int rockchip_drm_unload(struct drm_device *drm_dev) +{ + struct device *dev = drm_dev->dev; + + rockchip_drm_fbdev_fini(drm_dev); + drm_vblank_cleanup(drm_dev); + drm_kms_helper_poll_fini(drm_dev); + component_unbind_all(dev, drm_dev); + arm_iommu_detach_device(dev); + arm_iommu_release_mapping(dev->archdata.mapping); + drm_mode_config_cleanup(drm_dev); + drm_dev->dev_private = NULL; + + return 0; +} + +void rockchip_drm_lastclose(struct drm_device *dev) +{ + struct rockchip_drm_private *priv = dev->dev_private; + + drm_fb_helper_restore_fbdev_mode_unlocked(&priv->fbdev_helper); +} + +static const struct file_operations rockchip_drm_driver_fops = { + .owner = THIS_MODULE, + .open = drm_open, + .mmap = rockchip_gem_mmap, + .poll = drm_poll, + .read = drm_read, + .unlocked_ioctl = drm_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = drm_compat_ioctl, +#endif + .release = drm_release, +}; + +const struct vm_operations_struct rockchip_drm_vm_ops = { + .open = drm_gem_vm_open, + .close = drm_gem_vm_close, +}; + +static struct drm_driver rockchip_drm_driver = { + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME, + .load = rockchip_drm_load, + .unload = rockchip_drm_unload, + .lastclose = rockchip_drm_lastclose, + .get_vblank_counter = drm_vblank_count, + .enable_vblank = rockchip_drm_crtc_enable_vblank, + .disable_vblank = rockchip_drm_crtc_disable_vblank, + .gem_vm_ops = &rockchip_drm_vm_ops, + .gem_free_object = rockchip_gem_free_object, + .dumb_create = rockchip_gem_dumb_create, + .dumb_map_offset = rockchip_gem_dumb_map_offset, + .dumb_destroy = drm_gem_dumb_destroy, + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_import = drm_gem_prime_import, + .gem_prime_export = drm_gem_prime_export, + .gem_prime_get_sg_table = rockchip_gem_prime_get_sg_table, + .gem_prime_vmap = rockchip_gem_prime_vmap, + .gem_prime_vunmap = rockchip_gem_prime_vunmap, + .gem_prime_mmap = rockchip_gem_mmap_buf, + .fops = &rockchip_drm_driver_fops, + .name = DRIVER_NAME, + .desc = DRIVER_DESC, + .date = DRIVER_DATE, + .major = DRIVER_MAJOR, + .minor = DRIVER_MINOR, +}; + +#ifdef CONFIG_PM_SLEEP +static int rockchip_drm_sys_suspend(struct device *dev) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct drm_connector *connector; + + if (!drm) + return 0; + + drm_modeset_lock_all(drm); + list_for_each_entry(connector, &drm->mode_config.connector_list, head) { + int old_dpms = connector->dpms; + + if (connector->funcs->dpms) + connector->funcs->dpms(connector, DRM_MODE_DPMS_OFF); + + /* Set the old mode back to the connector for resume */ + connector->dpms = old_dpms; + } + drm_modeset_unlock_all(drm); + + return 0; +} + +static int rockchip_drm_sys_resume(struct device *dev) +{ + struct drm_device *drm = dev_get_drvdata(dev); + struct drm_connector *connector; + enum drm_connector_status status; + bool changed = false; + + if (!drm) + return 0; + + drm_modeset_lock_all(drm); + list_for_each_entry(connector, &drm->mode_config.connector_list, head) { + int desired_mode = connector->dpms; + + /* + * at suspend time, we save dpms to connector->dpms, + * restore the old_dpms, and at current time, the connector + * dpms status must be DRM_MODE_DPMS_OFF. + */ + connector->dpms = DRM_MODE_DPMS_OFF; + + /* + * If the connector has been disconnected during suspend, + * disconnect it from the encoder and leave it off. We'll notify + * userspace at the end. + */ + if (desired_mode == DRM_MODE_DPMS_ON) { + status = connector->funcs->detect(connector, true); + if (status == connector_status_disconnected) { + connector->encoder = NULL; + connector->status = status; + changed = true; + continue; + } + } + if (connector->funcs->dpms) + connector->funcs->dpms(connector, desired_mode); + } + drm_modeset_unlock_all(drm); + + drm_helper_resume_force_mode(drm); + + if (changed) + drm_kms_helper_hotplug_event(drm); + + return 0; +} +#endif + +static const struct dev_pm_ops rockchip_drm_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(rockchip_drm_sys_suspend, + rockchip_drm_sys_resume) +}; + +/* + * @node: device tree node containing encoder input ports + * @encoder: drm_encoder + */ +int rockchip_drm_encoder_get_mux_id(struct device_node *node, + struct drm_encoder *encoder) +{ + struct device_node *ep = NULL; + struct drm_crtc *crtc = encoder->crtc; + struct of_endpoint endpoint; + struct device_node *port; + int ret; + + if (!node || !crtc) + return -EINVAL; + + do { + ep = of_graph_get_next_endpoint(node, ep); + if (!ep) + break; + + port = of_graph_get_remote_port(ep); + of_node_put(port); + if (port == crtc->port) { + ret = of_graph_parse_endpoint(ep, &endpoint); + return ret ?: endpoint.id; + } + } while (ep); + + return -EINVAL; +} + +static int compare_of(struct device *dev, void *data) +{ + struct device_node *np = data; + + return dev->of_node == np; +} + +static void rockchip_add_endpoints(struct device *dev, + struct component_match **match, + struct device_node *port) +{ + struct device_node *ep, *remote; + + for_each_child_of_node(port, ep) { + remote = of_graph_get_remote_port_parent(ep); + if (!remote || !of_device_is_available(remote)) { + of_node_put(remote); + continue; + } else if (!of_device_is_available(remote->parent)) { + dev_warn(dev, "parent device of %s is not available\n", + remote->full_name); + of_node_put(remote); + continue; + } + + component_match_add(dev, match, compare_of, remote); + of_node_put(remote); + } +} + +static int rockchip_drm_bind(struct device *dev) +{ + struct drm_device *drm; + int ret; + + drm = drm_dev_alloc(&rockchip_drm_driver, dev); + if (!drm) + return -ENOMEM; + + ret = drm_dev_set_unique(drm, "%s", dev_name(dev)); + if (ret) + goto err_free; + + ret = drm_dev_register(drm, 0); + if (ret) + goto err_free; + + dev_set_drvdata(dev, drm); + + return 0; + +err_free: + drm_dev_unref(drm); + return ret; +} + +static void rockchip_drm_unbind(struct device *dev) +{ + struct drm_device *drm = dev_get_drvdata(dev); + + drm_dev_unregister(drm); + drm_dev_unref(drm); + dev_set_drvdata(dev, NULL); +} + +static const struct component_master_ops rockchip_drm_ops = { + .bind = rockchip_drm_bind, + .unbind = rockchip_drm_unbind, +}; + +static int rockchip_drm_platform_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct component_match *match = NULL; + struct device_node *np = dev->of_node; + struct device_node *port; + int i; + + if (!np) + return -ENODEV; + /* + * Bind the crtc ports first, so that + * drm_of_find_possible_crtcs called from encoder .bind callbacks + * works as expected. + */ + for (i = 0;; i++) { + port = of_parse_phandle(np, "ports", i); + if (!port) + break; + + if (!of_device_is_available(port->parent)) { + of_node_put(port); + continue; + } + + component_match_add(dev, &match, compare_of, port->parent); + of_node_put(port); + } + + if (i == 0) { + dev_err(dev, "missing 'ports' property\n"); + return -ENODEV; + } + + if (!match) { + dev_err(dev, "No available vop found for display-subsystem.\n"); + return -ENODEV; + } + /* + * For each bound crtc, bind the encoders attached to its + * remote endpoint. + */ + for (i = 0;; i++) { + port = of_parse_phandle(np, "ports", i); + if (!port) + break; + + if (!of_device_is_available(port->parent)) { + of_node_put(port); + continue; + } + + rockchip_add_endpoints(dev, &match, port); + of_node_put(port); + } + + return component_master_add_with_match(dev, &rockchip_drm_ops, match); +} + +static int rockchip_drm_platform_remove(struct platform_device *pdev) +{ + component_master_del(&pdev->dev, &rockchip_drm_ops); + + return 0; +} + +static const struct of_device_id rockchip_drm_dt_ids[] = { + { .compatible = "rockchip,display-subsystem", }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, rockchip_drm_dt_ids); + +static struct platform_driver rockchip_drm_platform_driver = { + .probe = rockchip_drm_platform_probe, + .remove = rockchip_drm_platform_remove, + .driver = { + .owner = THIS_MODULE, + .name = "rockchip-drm", + .of_match_table = rockchip_drm_dt_ids, + .pm = &rockchip_drm_pm_ops, + }, +}; + +module_platform_driver(rockchip_drm_platform_driver); + +MODULE_AUTHOR("Mark Yao <mark.yao@rock-chips.com>"); +MODULE_DESCRIPTION("ROCKCHIP DRM Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h new file mode 100644 index 000000000000..dc4e5f03ac79 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h @@ -0,0 +1,68 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * based on exynos_drm_drv.h + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ROCKCHIP_DRM_DRV_H +#define _ROCKCHIP_DRM_DRV_H + +#include <drm/drm_fb_helper.h> +#include <drm/drm_gem.h> + +#include <linux/module.h> +#include <linux/component.h> + +#define ROCKCHIP_MAX_FB_BUFFER 3 +#define ROCKCHIP_MAX_CONNECTOR 2 +#define ROCKCHIP_MAX_CRTC 2 + +struct drm_device; +struct drm_connector; + +/* + * Rockchip drm private crtc funcs. + * @enable_vblank: enable crtc vblank irq. + * @disable_vblank: disable crtc vblank irq. + */ +struct rockchip_crtc_funcs { + int (*enable_vblank)(struct drm_crtc *crtc); + void (*disable_vblank)(struct drm_crtc *crtc); +}; + +/* + * Rockchip drm private structure. + * + * @crtc: array of enabled CRTCs, used to map from "pipe" to drm_crtc. + * @num_pipe: number of pipes for this device. + */ +struct rockchip_drm_private { + struct drm_fb_helper fbdev_helper; + struct drm_gem_object *fbdev_bo; + const struct rockchip_crtc_funcs *crtc_funcs[ROCKCHIP_MAX_CRTC]; +}; + +int rockchip_register_crtc_funcs(struct drm_device *dev, + const struct rockchip_crtc_funcs *crtc_funcs, + int pipe); +void rockchip_unregister_crtc_funcs(struct drm_device *dev, int pipe); +int rockchip_drm_encoder_get_mux_id(struct device_node *node, + struct drm_encoder *encoder); +int rockchip_drm_crtc_mode_config(struct drm_crtc *crtc, int connector_type, + int out_mode); +int rockchip_drm_dma_attach_device(struct drm_device *drm_dev, + struct device *dev); +void rockchip_drm_dma_detach_device(struct drm_device *drm_dev, + struct device *dev); + +#endif /* _ROCKCHIP_DRM_DRV_H_ */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c new file mode 100644 index 000000000000..77d52893d40f --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c @@ -0,0 +1,201 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/kernel.h> +#include <drm/drm.h> +#include <drm/drmP.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_crtc_helper.h> + +#include "rockchip_drm_drv.h" +#include "rockchip_drm_gem.h" + +#define to_rockchip_fb(x) container_of(x, struct rockchip_drm_fb, fb) + +struct rockchip_drm_fb { + struct drm_framebuffer fb; + struct drm_gem_object *obj[ROCKCHIP_MAX_FB_BUFFER]; +}; + +struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb, + unsigned int plane) +{ + struct rockchip_drm_fb *rk_fb = to_rockchip_fb(fb); + + if (plane >= ROCKCHIP_MAX_FB_BUFFER) + return NULL; + + return rk_fb->obj[plane]; +} +EXPORT_SYMBOL_GPL(rockchip_fb_get_gem_obj); + +static void rockchip_drm_fb_destroy(struct drm_framebuffer *fb) +{ + struct rockchip_drm_fb *rockchip_fb = to_rockchip_fb(fb); + struct drm_gem_object *obj; + int i; + + for (i = 0; i < ROCKCHIP_MAX_FB_BUFFER; i++) { + obj = rockchip_fb->obj[i]; + if (obj) + drm_gem_object_unreference_unlocked(obj); + } + + drm_framebuffer_cleanup(fb); + kfree(rockchip_fb); +} + +static int rockchip_drm_fb_create_handle(struct drm_framebuffer *fb, + struct drm_file *file_priv, + unsigned int *handle) +{ + struct rockchip_drm_fb *rockchip_fb = to_rockchip_fb(fb); + + return drm_gem_handle_create(file_priv, + rockchip_fb->obj[0], handle); +} + +static struct drm_framebuffer_funcs rockchip_drm_fb_funcs = { + .destroy = rockchip_drm_fb_destroy, + .create_handle = rockchip_drm_fb_create_handle, +}; + +static struct rockchip_drm_fb * +rockchip_fb_alloc(struct drm_device *dev, struct drm_mode_fb_cmd2 *mode_cmd, + struct drm_gem_object **obj, unsigned int num_planes) +{ + struct rockchip_drm_fb *rockchip_fb; + int ret; + int i; + + rockchip_fb = kzalloc(sizeof(*rockchip_fb), GFP_KERNEL); + if (!rockchip_fb) + return ERR_PTR(-ENOMEM); + + drm_helper_mode_fill_fb_struct(&rockchip_fb->fb, mode_cmd); + + for (i = 0; i < num_planes; i++) + rockchip_fb->obj[i] = obj[i]; + + ret = drm_framebuffer_init(dev, &rockchip_fb->fb, + &rockchip_drm_fb_funcs); + if (ret) { + dev_err(dev->dev, "Failed to initialize framebuffer: %d\n", + ret); + kfree(rockchip_fb); + return ERR_PTR(ret); + } + + return rockchip_fb; +} + +static struct drm_framebuffer * +rockchip_user_fb_create(struct drm_device *dev, struct drm_file *file_priv, + struct drm_mode_fb_cmd2 *mode_cmd) +{ + struct rockchip_drm_fb *rockchip_fb; + struct drm_gem_object *objs[ROCKCHIP_MAX_FB_BUFFER]; + struct drm_gem_object *obj; + unsigned int hsub; + unsigned int vsub; + int num_planes; + int ret; + int i; + + hsub = drm_format_horz_chroma_subsampling(mode_cmd->pixel_format); + vsub = drm_format_vert_chroma_subsampling(mode_cmd->pixel_format); + num_planes = min(drm_format_num_planes(mode_cmd->pixel_format), + ROCKCHIP_MAX_FB_BUFFER); + + for (i = 0; i < num_planes; i++) { + unsigned int width = mode_cmd->width / (i ? hsub : 1); + unsigned int height = mode_cmd->height / (i ? vsub : 1); + unsigned int min_size; + + obj = drm_gem_object_lookup(dev, file_priv, + mode_cmd->handles[i]); + if (!obj) { + dev_err(dev->dev, "Failed to lookup GEM object\n"); + ret = -ENXIO; + goto err_gem_object_unreference; + } + + min_size = (height - 1) * mode_cmd->pitches[i] + + mode_cmd->offsets[i] + + width * drm_format_plane_cpp(mode_cmd->pixel_format, i); + + if (obj->size < min_size) { + drm_gem_object_unreference_unlocked(obj); + ret = -EINVAL; + goto err_gem_object_unreference; + } + objs[i] = obj; + } + + rockchip_fb = rockchip_fb_alloc(dev, mode_cmd, objs, i); + if (IS_ERR(rockchip_fb)) { + ret = PTR_ERR(rockchip_fb); + goto err_gem_object_unreference; + } + + return &rockchip_fb->fb; + +err_gem_object_unreference: + for (i--; i >= 0; i--) + drm_gem_object_unreference_unlocked(objs[i]); + return ERR_PTR(ret); +} + +static void rockchip_drm_output_poll_changed(struct drm_device *dev) +{ + struct rockchip_drm_private *private = dev->dev_private; + struct drm_fb_helper *fb_helper = &private->fbdev_helper; + + drm_fb_helper_hotplug_event(fb_helper); +} + +static const struct drm_mode_config_funcs rockchip_drm_mode_config_funcs = { + .fb_create = rockchip_user_fb_create, + .output_poll_changed = rockchip_drm_output_poll_changed, +}; + +struct drm_framebuffer * +rockchip_drm_framebuffer_init(struct drm_device *dev, + struct drm_mode_fb_cmd2 *mode_cmd, + struct drm_gem_object *obj) +{ + struct rockchip_drm_fb *rockchip_fb; + + rockchip_fb = rockchip_fb_alloc(dev, mode_cmd, &obj, 1); + if (IS_ERR(rockchip_fb)) + return NULL; + + return &rockchip_fb->fb; +} + +void rockchip_drm_mode_config_init(struct drm_device *dev) +{ + dev->mode_config.min_width = 0; + dev->mode_config.min_height = 0; + + /* + * set max width and height as default value(4096x4096). + * this value would be used to check framebuffer size limitation + * at drm_mode_addfb(). + */ + dev->mode_config.max_width = 4096; + dev->mode_config.max_height = 4096; + + dev->mode_config.funcs = &rockchip_drm_mode_config_funcs; +} diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.h b/drivers/gpu/drm/rockchip/rockchip_drm_fb.h new file mode 100644 index 000000000000..09574d48226f --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.h @@ -0,0 +1,28 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ROCKCHIP_DRM_FB_H +#define _ROCKCHIP_DRM_FB_H + +struct drm_framebuffer * +rockchip_drm_framebuffer_init(struct drm_device *dev, + struct drm_mode_fb_cmd2 *mode_cmd, + struct drm_gem_object *obj); +void rockchip_drm_framebuffer_fini(struct drm_framebuffer *fb); + +void rockchip_drm_mode_config_init(struct drm_device *dev); + +struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb, + unsigned int plane); +#endif /* _ROCKCHIP_DRM_FB_H */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c new file mode 100644 index 000000000000..a5d889a8716b --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c @@ -0,0 +1,210 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <drm/drm.h> +#include <drm/drmP.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_crtc_helper.h> + +#include "rockchip_drm_drv.h" +#include "rockchip_drm_gem.h" +#include "rockchip_drm_fb.h" + +#define PREFERRED_BPP 32 +#define to_drm_private(x) \ + container_of(x, struct rockchip_drm_private, fbdev_helper) + +static int rockchip_fbdev_mmap(struct fb_info *info, + struct vm_area_struct *vma) +{ + struct drm_fb_helper *helper = info->par; + struct rockchip_drm_private *private = to_drm_private(helper); + + return rockchip_gem_mmap_buf(private->fbdev_bo, vma); +} + +static struct fb_ops rockchip_drm_fbdev_ops = { + .owner = THIS_MODULE, + .fb_mmap = rockchip_fbdev_mmap, + .fb_fillrect = cfb_fillrect, + .fb_copyarea = cfb_copyarea, + .fb_imageblit = cfb_imageblit, + .fb_check_var = drm_fb_helper_check_var, + .fb_set_par = drm_fb_helper_set_par, + .fb_blank = drm_fb_helper_blank, + .fb_pan_display = drm_fb_helper_pan_display, + .fb_setcmap = drm_fb_helper_setcmap, +}; + +static int rockchip_drm_fbdev_create(struct drm_fb_helper *helper, + struct drm_fb_helper_surface_size *sizes) +{ + struct rockchip_drm_private *private = to_drm_private(helper); + struct drm_mode_fb_cmd2 mode_cmd = { 0 }; + struct drm_device *dev = helper->dev; + struct rockchip_gem_object *rk_obj; + struct drm_framebuffer *fb; + unsigned int bytes_per_pixel; + unsigned long offset; + struct fb_info *fbi; + size_t size; + int ret; + + bytes_per_pixel = DIV_ROUND_UP(sizes->surface_bpp, 8); + + mode_cmd.width = sizes->surface_width; + mode_cmd.height = sizes->surface_height; + mode_cmd.pitches[0] = sizes->surface_width * bytes_per_pixel; + mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, + sizes->surface_depth); + + size = mode_cmd.pitches[0] * mode_cmd.height; + + rk_obj = rockchip_gem_create_object(dev, size); + if (IS_ERR(rk_obj)) + return -ENOMEM; + + private->fbdev_bo = &rk_obj->base; + + fbi = framebuffer_alloc(0, dev->dev); + if (!fbi) { + dev_err(dev->dev, "Failed to allocate framebuffer info.\n"); + ret = -ENOMEM; + goto err_rockchip_gem_free_object; + } + + helper->fb = rockchip_drm_framebuffer_init(dev, &mode_cmd, + private->fbdev_bo); + if (IS_ERR(helper->fb)) { + dev_err(dev->dev, "Failed to allocate DRM framebuffer.\n"); + ret = PTR_ERR(helper->fb); + goto err_framebuffer_release; + } + + helper->fbdev = fbi; + + fbi->par = helper; + fbi->flags = FBINFO_FLAG_DEFAULT; + fbi->fbops = &rockchip_drm_fbdev_ops; + + ret = fb_alloc_cmap(&fbi->cmap, 256, 0); + if (ret) { + dev_err(dev->dev, "Failed to allocate color map.\n"); + goto err_drm_framebuffer_unref; + } + + fb = helper->fb; + drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->depth); + drm_fb_helper_fill_var(fbi, helper, fb->width, fb->height); + + offset = fbi->var.xoffset * bytes_per_pixel; + offset += fbi->var.yoffset * fb->pitches[0]; + + dev->mode_config.fb_base = 0; + fbi->screen_base = rk_obj->kvaddr + offset; + fbi->screen_size = rk_obj->base.size; + fbi->fix.smem_len = rk_obj->base.size; + + DRM_DEBUG_KMS("FB [%dx%d]-%d kvaddr=%p offset=%ld size=%d\n", + fb->width, fb->height, fb->depth, rk_obj->kvaddr, + offset, size); + return 0; + +err_drm_framebuffer_unref: + drm_framebuffer_unreference(helper->fb); +err_framebuffer_release: + framebuffer_release(fbi); +err_rockchip_gem_free_object: + rockchip_gem_free_object(&rk_obj->base); + return ret; +} + +static const struct drm_fb_helper_funcs rockchip_drm_fb_helper_funcs = { + .fb_probe = rockchip_drm_fbdev_create, +}; + +int rockchip_drm_fbdev_init(struct drm_device *dev) +{ + struct rockchip_drm_private *private = dev->dev_private; + struct drm_fb_helper *helper; + unsigned int num_crtc; + int ret; + + if (!dev->mode_config.num_crtc || !dev->mode_config.num_connector) + return -EINVAL; + + num_crtc = dev->mode_config.num_crtc; + + helper = &private->fbdev_helper; + + drm_fb_helper_prepare(dev, helper, &rockchip_drm_fb_helper_funcs); + + ret = drm_fb_helper_init(dev, helper, num_crtc, ROCKCHIP_MAX_CONNECTOR); + if (ret < 0) { + dev_err(dev->dev, "Failed to initialize drm fb helper - %d.\n", + ret); + return ret; + } + + ret = drm_fb_helper_single_add_all_connectors(helper); + if (ret < 0) { + dev_err(dev->dev, "Failed to add connectors - %d.\n", ret); + goto err_drm_fb_helper_fini; + } + + /* disable all the possible outputs/crtcs before entering KMS mode */ + drm_helper_disable_unused_functions(dev); + + ret = drm_fb_helper_initial_config(helper, PREFERRED_BPP); + if (ret < 0) { + dev_err(dev->dev, "Failed to set initial hw config - %d.\n", + ret); + goto err_drm_fb_helper_fini; + } + + return 0; + +err_drm_fb_helper_fini: + drm_fb_helper_fini(helper); + return ret; +} + +void rockchip_drm_fbdev_fini(struct drm_device *dev) +{ + struct rockchip_drm_private *private = dev->dev_private; + struct drm_fb_helper *helper; + + helper = &private->fbdev_helper; + + if (helper->fbdev) { + struct fb_info *info; + int ret; + + info = helper->fbdev; + ret = unregister_framebuffer(info); + if (ret < 0) + DRM_DEBUG_KMS("failed unregister_framebuffer() - %d\n", + ret); + + if (info->cmap.len) + fb_dealloc_cmap(&info->cmap); + + framebuffer_release(info); + } + + if (helper->fb) + drm_framebuffer_unreference(helper->fb); + + drm_fb_helper_fini(helper); +} diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h new file mode 100644 index 000000000000..50432e9b5b37 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.h @@ -0,0 +1,21 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ROCKCHIP_DRM_FBDEV_H +#define _ROCKCHIP_DRM_FBDEV_H + +int rockchip_drm_fbdev_init(struct drm_device *dev); +void rockchip_drm_fbdev_fini(struct drm_device *dev); + +#endif /* _ROCKCHIP_DRM_FBDEV_H */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c new file mode 100644 index 000000000000..bc98a227dc76 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -0,0 +1,294 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <drm/drm.h> +#include <drm/drmP.h> +#include <drm/drm_gem.h> +#include <drm/drm_vma_manager.h> + +#include <linux/dma-attrs.h> + +#include "rockchip_drm_drv.h" +#include "rockchip_drm_gem.h" + +static int rockchip_gem_alloc_buf(struct rockchip_gem_object *rk_obj) +{ + struct drm_gem_object *obj = &rk_obj->base; + struct drm_device *drm = obj->dev; + + init_dma_attrs(&rk_obj->dma_attrs); + dma_set_attr(DMA_ATTR_WRITE_COMBINE, &rk_obj->dma_attrs); + + /* TODO(djkurtz): Use DMA_ATTR_NO_KERNEL_MAPPING except for fbdev */ + rk_obj->kvaddr = dma_alloc_attrs(drm->dev, obj->size, + &rk_obj->dma_addr, GFP_KERNEL, + &rk_obj->dma_attrs); + if (IS_ERR(rk_obj->kvaddr)) { + int ret = PTR_ERR(rk_obj->kvaddr); + + DRM_ERROR("failed to allocate %#x byte dma buffer, %d", + obj->size, ret); + return ret; + } + + return 0; +} + +static void rockchip_gem_free_buf(struct rockchip_gem_object *rk_obj) +{ + struct drm_gem_object *obj = &rk_obj->base; + struct drm_device *drm = obj->dev; + + dma_free_attrs(drm->dev, obj->size, rk_obj->kvaddr, rk_obj->dma_addr, + &rk_obj->dma_attrs); +} + +int rockchip_gem_mmap_buf(struct drm_gem_object *obj, + struct vm_area_struct *vma) +{ + struct rockchip_gem_object *rk_obj = to_rockchip_obj(obj); + struct drm_device *drm = obj->dev; + unsigned long vm_size; + + vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_size = vma->vm_end - vma->vm_start; + + if (vm_size > obj->size) + return -EINVAL; + + return dma_mmap_attrs(drm->dev, vma, rk_obj->kvaddr, rk_obj->dma_addr, + obj->size, &rk_obj->dma_attrs); +} + +/* drm driver mmap file operations */ +int rockchip_gem_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct drm_file *priv = filp->private_data; + struct drm_device *dev = priv->minor->dev; + struct drm_gem_object *obj; + struct drm_vma_offset_node *node; + int ret; + + if (drm_device_is_unplugged(dev)) + return -ENODEV; + + mutex_lock(&dev->struct_mutex); + + node = drm_vma_offset_exact_lookup(dev->vma_offset_manager, + vma->vm_pgoff, + vma_pages(vma)); + if (!node) { + mutex_unlock(&dev->struct_mutex); + DRM_ERROR("failed to find vma node.\n"); + return -EINVAL; + } else if (!drm_vma_node_is_allowed(node, filp)) { + mutex_unlock(&dev->struct_mutex); + return -EACCES; + } + + obj = container_of(node, struct drm_gem_object, vma_node); + ret = rockchip_gem_mmap_buf(obj, vma); + + mutex_unlock(&dev->struct_mutex); + + return ret; +} + +struct rockchip_gem_object * + rockchip_gem_create_object(struct drm_device *drm, unsigned int size) +{ + struct rockchip_gem_object *rk_obj; + struct drm_gem_object *obj; + int ret; + + size = round_up(size, PAGE_SIZE); + + rk_obj = kzalloc(sizeof(*rk_obj), GFP_KERNEL); + if (!rk_obj) + return ERR_PTR(-ENOMEM); + + obj = &rk_obj->base; + + drm_gem_private_object_init(drm, obj, size); + + ret = rockchip_gem_alloc_buf(rk_obj); + if (ret) + goto err_free_rk_obj; + + return rk_obj; + +err_free_rk_obj: + kfree(rk_obj); + return ERR_PTR(ret); +} + +/* + * rockchip_gem_free_object - (struct drm_driver)->gem_free_object callback + * function + */ +void rockchip_gem_free_object(struct drm_gem_object *obj) +{ + struct rockchip_gem_object *rk_obj; + + drm_gem_free_mmap_offset(obj); + + rk_obj = to_rockchip_obj(obj); + + rockchip_gem_free_buf(rk_obj); + + kfree(rk_obj); +} + +/* + * rockchip_gem_create_with_handle - allocate an object with the given + * size and create a gem handle on it + * + * returns a struct rockchip_gem_object* on success or ERR_PTR values + * on failure. + */ +static struct rockchip_gem_object * +rockchip_gem_create_with_handle(struct drm_file *file_priv, + struct drm_device *drm, unsigned int size, + unsigned int *handle) +{ + struct rockchip_gem_object *rk_obj; + struct drm_gem_object *obj; + int ret; + + rk_obj = rockchip_gem_create_object(drm, size); + if (IS_ERR(rk_obj)) + return ERR_CAST(rk_obj); + + obj = &rk_obj->base; + + /* + * allocate a id of idr table where the obj is registered + * and handle has the id what user can see. + */ + ret = drm_gem_handle_create(file_priv, obj, handle); + if (ret) + goto err_handle_create; + + /* drop reference from allocate - handle holds it now. */ + drm_gem_object_unreference_unlocked(obj); + + return rk_obj; + +err_handle_create: + rockchip_gem_free_object(obj); + + return ERR_PTR(ret); +} + +int rockchip_gem_dumb_map_offset(struct drm_file *file_priv, + struct drm_device *dev, uint32_t handle, + uint64_t *offset) +{ + struct drm_gem_object *obj; + int ret; + + mutex_lock(&dev->struct_mutex); + + obj = drm_gem_object_lookup(dev, file_priv, handle); + if (!obj) { + DRM_ERROR("failed to lookup gem object.\n"); + ret = -EINVAL; + goto unlock; + } + + ret = drm_gem_create_mmap_offset(obj); + if (ret) + goto out; + + *offset = drm_vma_node_offset_addr(&obj->vma_node); + DRM_DEBUG_KMS("offset = 0x%llx\n", *offset); + +out: + drm_gem_object_unreference(obj); +unlock: + mutex_unlock(&dev->struct_mutex); + return ret; +} + +/* + * rockchip_gem_dumb_create - (struct drm_driver)->dumb_create callback + * function + * + * This aligns the pitch and size arguments to the minimum required. wrap + * this into your own function if you need bigger alignment. + */ +int rockchip_gem_dumb_create(struct drm_file *file_priv, + struct drm_device *dev, + struct drm_mode_create_dumb *args) +{ + struct rockchip_gem_object *rk_obj; + int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8); + + /* + * align to 64 bytes since Mali requires it. + */ + min_pitch = ALIGN(min_pitch, 64); + + if (args->pitch < min_pitch) + args->pitch = min_pitch; + + if (args->size < args->pitch * args->height) + args->size = args->pitch * args->height; + + rk_obj = rockchip_gem_create_with_handle(file_priv, dev, args->size, + &args->handle); + + return PTR_ERR_OR_ZERO(rk_obj); +} + +/* + * Allocate a sg_table for this GEM object. + * Note: Both the table's contents, and the sg_table itself must be freed by + * the caller. + * Returns a pointer to the newly allocated sg_table, or an ERR_PTR() error. + */ +struct sg_table *rockchip_gem_prime_get_sg_table(struct drm_gem_object *obj) +{ + struct rockchip_gem_object *rk_obj = to_rockchip_obj(obj); + struct drm_device *drm = obj->dev; + struct sg_table *sgt; + int ret; + + sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); + if (!sgt) + return ERR_PTR(-ENOMEM); + + ret = dma_get_sgtable_attrs(drm->dev, sgt, rk_obj->kvaddr, + rk_obj->dma_addr, obj->size, + &rk_obj->dma_attrs); + if (ret) { + DRM_ERROR("failed to allocate sgt, %d\n", ret); + kfree(sgt); + return ERR_PTR(ret); + } + + return sgt; +} + +void *rockchip_gem_prime_vmap(struct drm_gem_object *obj) +{ + struct rockchip_gem_object *rk_obj = to_rockchip_obj(obj); + + return rk_obj->kvaddr; +} + +void rockchip_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr) +{ + /* Nothing to do */ +} diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.h b/drivers/gpu/drm/rockchip/rockchip_drm_gem.h new file mode 100644 index 000000000000..67bcebe90003 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.h @@ -0,0 +1,54 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ROCKCHIP_DRM_GEM_H +#define _ROCKCHIP_DRM_GEM_H + +#define to_rockchip_obj(x) container_of(x, struct rockchip_gem_object, base) + +struct rockchip_gem_object { + struct drm_gem_object base; + unsigned int flags; + + void *kvaddr; + dma_addr_t dma_addr; + struct dma_attrs dma_attrs; +}; + +struct sg_table *rockchip_gem_prime_get_sg_table(struct drm_gem_object *obj); +struct drm_gem_object * +rockchip_gem_prime_import_sg_table(struct drm_device *dev, size_t size, + struct sg_table *sgt); +void *rockchip_gem_prime_vmap(struct drm_gem_object *obj); +void rockchip_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); + +/* drm driver mmap file operations */ +int rockchip_gem_mmap(struct file *filp, struct vm_area_struct *vma); + +/* mmap a gem object to userspace. */ +int rockchip_gem_mmap_buf(struct drm_gem_object *obj, + struct vm_area_struct *vma); + +struct rockchip_gem_object * + rockchip_gem_create_object(struct drm_device *drm, unsigned int size); + +void rockchip_gem_free_object(struct drm_gem_object *obj); + +int rockchip_gem_dumb_create(struct drm_file *file_priv, + struct drm_device *dev, + struct drm_mode_create_dumb *args); +int rockchip_gem_dumb_map_offset(struct drm_file *file_priv, + struct drm_device *dev, uint32_t handle, + uint64_t *offset); +#endif /* _ROCKCHIP_DRM_GEM_H */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c new file mode 100644 index 000000000000..e7ca25b3fb38 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -0,0 +1,1455 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <drm/drm.h> +#include <drm/drmP.h> +#include <drm/drm_crtc.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_plane_helper.h> + +#include <linux/kernel.h> +#include <linux/platform_device.h> +#include <linux/clk.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/pm_runtime.h> +#include <linux/component.h> + +#include <linux/reset.h> +#include <linux/delay.h> + +#include "rockchip_drm_drv.h" +#include "rockchip_drm_gem.h" +#include "rockchip_drm_fb.h" +#include "rockchip_drm_vop.h" + +#define VOP_REG(off, _mask, s) \ + {.offset = off, \ + .mask = _mask, \ + .shift = s,} + +#define __REG_SET_RELAXED(x, off, mask, shift, v) \ + vop_mask_write_relaxed(x, off, (mask) << shift, (v) << shift) +#define __REG_SET_NORMAL(x, off, mask, shift, v) \ + vop_mask_write(x, off, (mask) << shift, (v) << shift) + +#define REG_SET(x, base, reg, v, mode) \ + __REG_SET_##mode(x, base + reg.offset, reg.mask, reg.shift, v) + +#define VOP_WIN_SET(x, win, name, v) \ + REG_SET(x, win->base, win->phy->name, v, RELAXED) +#define VOP_CTRL_SET(x, name, v) \ + REG_SET(x, 0, (x)->data->ctrl->name, v, NORMAL) + +#define VOP_WIN_GET(x, win, name) \ + vop_read_reg(x, win->base, &win->phy->name) + +#define VOP_WIN_GET_YRGBADDR(vop, win) \ + vop_readl(vop, win->base + win->phy->yrgb_mst.offset) + +#define to_vop(x) container_of(x, struct vop, crtc) +#define to_vop_win(x) container_of(x, struct vop_win, base) + +struct vop_win_state { + struct list_head head; + struct drm_framebuffer *fb; + dma_addr_t yrgb_mst; + struct drm_pending_vblank_event *event; +}; + +struct vop_win { + struct drm_plane base; + const struct vop_win_data *data; + struct vop *vop; + + struct list_head pending; + struct vop_win_state *active; +}; + +struct vop { + struct drm_crtc crtc; + struct device *dev; + struct drm_device *drm_dev; + unsigned int dpms; + + int connector_type; + int connector_out_mode; + + /* mutex vsync_ work */ + struct mutex vsync_mutex; + bool vsync_work_pending; + + const struct vop_data *data; + + uint32_t *regsbak; + void __iomem *regs; + + /* physical map length of vop register */ + uint32_t len; + + /* one time only one process allowed to config the register */ + spinlock_t reg_lock; + /* lock vop irq reg */ + spinlock_t irq_lock; + + unsigned int irq; + + /* vop AHP clk */ + struct clk *hclk; + /* vop dclk */ + struct clk *dclk; + /* vop share memory frequency */ + struct clk *aclk; + + /* vop dclk reset */ + struct reset_control *dclk_rst; + + int pipe; + + struct vop_win win[]; +}; + +enum vop_data_format { + VOP_FMT_ARGB8888 = 0, + VOP_FMT_RGB888, + VOP_FMT_RGB565, + VOP_FMT_YUV420SP = 4, + VOP_FMT_YUV422SP, + VOP_FMT_YUV444SP, +}; + +struct vop_reg_data { + uint32_t offset; + uint32_t value; +}; + +struct vop_reg { + uint32_t offset; + uint32_t shift; + uint32_t mask; +}; + +struct vop_ctrl { + struct vop_reg standby; + struct vop_reg data_blank; + struct vop_reg gate_en; + struct vop_reg mmu_en; + struct vop_reg rgb_en; + struct vop_reg edp_en; + struct vop_reg hdmi_en; + struct vop_reg mipi_en; + struct vop_reg out_mode; + struct vop_reg dither_down; + struct vop_reg dither_up; + struct vop_reg pin_pol; + + struct vop_reg htotal_pw; + struct vop_reg hact_st_end; + struct vop_reg vtotal_pw; + struct vop_reg vact_st_end; + struct vop_reg hpost_st_end; + struct vop_reg vpost_st_end; +}; + +struct vop_win_phy { + const uint32_t *data_formats; + uint32_t nformats; + + struct vop_reg enable; + struct vop_reg format; + struct vop_reg act_info; + struct vop_reg dsp_info; + struct vop_reg dsp_st; + struct vop_reg yrgb_mst; + struct vop_reg uv_mst; + struct vop_reg yrgb_vir; + struct vop_reg uv_vir; + + struct vop_reg dst_alpha_ctl; + struct vop_reg src_alpha_ctl; +}; + +struct vop_win_data { + uint32_t base; + const struct vop_win_phy *phy; + enum drm_plane_type type; +}; + +struct vop_data { + const struct vop_reg_data *init_table; + unsigned int table_size; + const struct vop_ctrl *ctrl; + const struct vop_win_data *win; + unsigned int win_size; +}; + +static const uint32_t formats_01[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGB888, + DRM_FORMAT_RGB565, + DRM_FORMAT_NV12, + DRM_FORMAT_NV16, + DRM_FORMAT_NV24, +}; + +static const uint32_t formats_234[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_RGB888, + DRM_FORMAT_RGB565, +}; + +static const struct vop_win_phy win01_data = { + .data_formats = formats_01, + .nformats = ARRAY_SIZE(formats_01), + .enable = VOP_REG(WIN0_CTRL0, 0x1, 0), + .format = VOP_REG(WIN0_CTRL0, 0x7, 1), + .act_info = VOP_REG(WIN0_ACT_INFO, 0x1fff1fff, 0), + .dsp_info = VOP_REG(WIN0_DSP_INFO, 0x0fff0fff, 0), + .dsp_st = VOP_REG(WIN0_DSP_ST, 0x1fff1fff, 0), + .yrgb_mst = VOP_REG(WIN0_YRGB_MST, 0xffffffff, 0), + .uv_mst = VOP_REG(WIN0_CBR_MST, 0xffffffff, 0), + .yrgb_vir = VOP_REG(WIN0_VIR, 0x3fff, 0), + .uv_vir = VOP_REG(WIN0_VIR, 0x3fff, 16), + .src_alpha_ctl = VOP_REG(WIN0_SRC_ALPHA_CTRL, 0xff, 0), + .dst_alpha_ctl = VOP_REG(WIN0_DST_ALPHA_CTRL, 0xff, 0), +}; + +static const struct vop_win_phy win23_data = { + .data_formats = formats_234, + .nformats = ARRAY_SIZE(formats_234), + .enable = VOP_REG(WIN2_CTRL0, 0x1, 0), + .format = VOP_REG(WIN2_CTRL0, 0x7, 1), + .dsp_info = VOP_REG(WIN2_DSP_INFO0, 0x0fff0fff, 0), + .dsp_st = VOP_REG(WIN2_DSP_ST0, 0x1fff1fff, 0), + .yrgb_mst = VOP_REG(WIN2_MST0, 0xffffffff, 0), + .yrgb_vir = VOP_REG(WIN2_VIR0_1, 0x1fff, 0), + .src_alpha_ctl = VOP_REG(WIN2_SRC_ALPHA_CTRL, 0xff, 0), + .dst_alpha_ctl = VOP_REG(WIN2_DST_ALPHA_CTRL, 0xff, 0), +}; + +static const struct vop_win_phy cursor_data = { + .data_formats = formats_234, + .nformats = ARRAY_SIZE(formats_234), + .enable = VOP_REG(HWC_CTRL0, 0x1, 0), + .format = VOP_REG(HWC_CTRL0, 0x7, 1), + .dsp_st = VOP_REG(HWC_DSP_ST, 0x1fff1fff, 0), + .yrgb_mst = VOP_REG(HWC_MST, 0xffffffff, 0), +}; + +static const struct vop_ctrl ctrl_data = { + .standby = VOP_REG(SYS_CTRL, 0x1, 22), + .gate_en = VOP_REG(SYS_CTRL, 0x1, 23), + .mmu_en = VOP_REG(SYS_CTRL, 0x1, 20), + .rgb_en = VOP_REG(SYS_CTRL, 0x1, 12), + .hdmi_en = VOP_REG(SYS_CTRL, 0x1, 13), + .edp_en = VOP_REG(SYS_CTRL, 0x1, 14), + .mipi_en = VOP_REG(SYS_CTRL, 0x1, 15), + .dither_down = VOP_REG(DSP_CTRL1, 0xf, 1), + .dither_up = VOP_REG(DSP_CTRL1, 0x1, 6), + .data_blank = VOP_REG(DSP_CTRL0, 0x1, 19), + .out_mode = VOP_REG(DSP_CTRL0, 0xf, 0), + .pin_pol = VOP_REG(DSP_CTRL0, 0xf, 4), + .htotal_pw = VOP_REG(DSP_HTOTAL_HS_END, 0x1fff1fff, 0), + .hact_st_end = VOP_REG(DSP_HACT_ST_END, 0x1fff1fff, 0), + .vtotal_pw = VOP_REG(DSP_VTOTAL_VS_END, 0x1fff1fff, 0), + .vact_st_end = VOP_REG(DSP_VACT_ST_END, 0x1fff1fff, 0), + .hpost_st_end = VOP_REG(POST_DSP_HACT_INFO, 0x1fff1fff, 0), + .vpost_st_end = VOP_REG(POST_DSP_VACT_INFO, 0x1fff1fff, 0), +}; + +static const struct vop_reg_data vop_init_reg_table[] = { + {SYS_CTRL, 0x00c00000}, + {DSP_CTRL0, 0x00000000}, + {WIN0_CTRL0, 0x00000080}, + {WIN1_CTRL0, 0x00000080}, +}; + +/* + * Note: rk3288 has a dedicated 'cursor' window, however, that window requires + * special support to get alpha blending working. For now, just use overlay + * window 1 for the drm cursor. + */ +static const struct vop_win_data rk3288_vop_win_data[] = { + { .base = 0x00, .phy = &win01_data, .type = DRM_PLANE_TYPE_PRIMARY }, + { .base = 0x40, .phy = &win01_data, .type = DRM_PLANE_TYPE_CURSOR }, + { .base = 0x00, .phy = &win23_data, .type = DRM_PLANE_TYPE_OVERLAY }, + { .base = 0x50, .phy = &win23_data, .type = DRM_PLANE_TYPE_OVERLAY }, + { .base = 0x00, .phy = &cursor_data, .type = DRM_PLANE_TYPE_OVERLAY }, +}; + +static const struct vop_data rk3288_vop = { + .init_table = vop_init_reg_table, + .table_size = ARRAY_SIZE(vop_init_reg_table), + .ctrl = &ctrl_data, + .win = rk3288_vop_win_data, + .win_size = ARRAY_SIZE(rk3288_vop_win_data), +}; + +static const struct of_device_id vop_driver_dt_match[] = { + { .compatible = "rockchip,rk3288-vop", + .data = &rk3288_vop }, + {}, +}; + +static inline void vop_writel(struct vop *vop, uint32_t offset, uint32_t v) +{ + writel(v, vop->regs + offset); + vop->regsbak[offset >> 2] = v; +} + +static inline uint32_t vop_readl(struct vop *vop, uint32_t offset) +{ + return readl(vop->regs + offset); +} + +static inline uint32_t vop_read_reg(struct vop *vop, uint32_t base, + const struct vop_reg *reg) +{ + return (vop_readl(vop, base + reg->offset) >> reg->shift) & reg->mask; +} + +static inline void vop_cfg_done(struct vop *vop) +{ + writel(0x01, vop->regs + REG_CFG_DONE); +} + +static inline void vop_mask_write(struct vop *vop, uint32_t offset, + uint32_t mask, uint32_t v) +{ + if (mask) { + uint32_t cached_val = vop->regsbak[offset >> 2]; + + cached_val = (cached_val & ~mask) | v; + writel(cached_val, vop->regs + offset); + vop->regsbak[offset >> 2] = cached_val; + } +} + +static inline void vop_mask_write_relaxed(struct vop *vop, uint32_t offset, + uint32_t mask, uint32_t v) +{ + if (mask) { + uint32_t cached_val = vop->regsbak[offset >> 2]; + + cached_val = (cached_val & ~mask) | v; + writel_relaxed(cached_val, vop->regs + offset); + vop->regsbak[offset >> 2] = cached_val; + } +} + +static enum vop_data_format vop_convert_format(uint32_t format) +{ + switch (format) { + case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_ARGB8888: + return VOP_FMT_ARGB8888; + case DRM_FORMAT_RGB888: + return VOP_FMT_RGB888; + case DRM_FORMAT_RGB565: + return VOP_FMT_RGB565; + case DRM_FORMAT_NV12: + return VOP_FMT_YUV420SP; + case DRM_FORMAT_NV16: + return VOP_FMT_YUV422SP; + case DRM_FORMAT_NV24: + return VOP_FMT_YUV444SP; + default: + DRM_ERROR("unsupport format[%08x]\n", format); + return -EINVAL; + } +} + +static bool is_alpha_support(uint32_t format) +{ + switch (format) { + case DRM_FORMAT_ARGB8888: + return true; + default: + return false; + } +} + +static void vop_enable(struct drm_crtc *crtc) +{ + struct vop *vop = to_vop(crtc); + int ret; + + ret = clk_enable(vop->hclk); + if (ret < 0) { + dev_err(vop->dev, "failed to enable hclk - %d\n", ret); + return; + } + + ret = clk_enable(vop->dclk); + if (ret < 0) { + dev_err(vop->dev, "failed to enable dclk - %d\n", ret); + goto err_disable_hclk; + } + + ret = clk_enable(vop->aclk); + if (ret < 0) { + dev_err(vop->dev, "failed to enable aclk - %d\n", ret); + goto err_disable_dclk; + } + + /* + * Slave iommu shares power, irq and clock with vop. It was associated + * automatically with this master device via common driver code. + * Now that we have enabled the clock we attach it to the shared drm + * mapping. + */ + ret = rockchip_drm_dma_attach_device(vop->drm_dev, vop->dev); + if (ret) { + dev_err(vop->dev, "failed to attach dma mapping, %d\n", ret); + goto err_disable_aclk; + } + + spin_lock(&vop->reg_lock); + + VOP_CTRL_SET(vop, standby, 0); + + spin_unlock(&vop->reg_lock); + + enable_irq(vop->irq); + + drm_vblank_on(vop->drm_dev, vop->pipe); + + return; + +err_disable_aclk: + clk_disable(vop->aclk); +err_disable_dclk: + clk_disable(vop->dclk); +err_disable_hclk: + clk_disable(vop->hclk); +} + +static void vop_disable(struct drm_crtc *crtc) +{ + struct vop *vop = to_vop(crtc); + + drm_vblank_off(crtc->dev, vop->pipe); + + disable_irq(vop->irq); + + /* + * TODO: Since standby doesn't take effect until the next vblank, + * when we turn off dclk below, the vop is probably still active. + */ + spin_lock(&vop->reg_lock); + + VOP_CTRL_SET(vop, standby, 1); + + spin_unlock(&vop->reg_lock); + /* + * disable dclk to stop frame scan, so we can safely detach iommu, + */ + clk_disable(vop->dclk); + + rockchip_drm_dma_detach_device(vop->drm_dev, vop->dev); + + clk_disable(vop->aclk); + clk_disable(vop->hclk); +} + +/* + * Caller must hold vsync_mutex. + */ +static struct drm_framebuffer *vop_win_last_pending_fb(struct vop_win *vop_win) +{ + struct vop_win_state *last; + struct vop_win_state *active = vop_win->active; + + if (list_empty(&vop_win->pending)) + return active ? active->fb : NULL; + + last = list_last_entry(&vop_win->pending, struct vop_win_state, head); + return last ? last->fb : NULL; +} + +/* + * Caller must hold vsync_mutex. + */ +static int vop_win_queue_fb(struct vop_win *vop_win, + struct drm_framebuffer *fb, dma_addr_t yrgb_mst, + struct drm_pending_vblank_event *event) +{ + struct vop_win_state *state; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + state->fb = fb; + state->yrgb_mst = yrgb_mst; + state->event = event; + + list_add_tail(&state->head, &vop_win->pending); + + return 0; +} + +static int vop_update_plane_event(struct drm_plane *plane, + struct drm_crtc *crtc, + struct drm_framebuffer *fb, int crtc_x, + int crtc_y, unsigned int crtc_w, + unsigned int crtc_h, uint32_t src_x, + uint32_t src_y, uint32_t src_w, + uint32_t src_h, + struct drm_pending_vblank_event *event) +{ + struct vop_win *vop_win = to_vop_win(plane); + const struct vop_win_data *win = vop_win->data; + struct vop *vop = to_vop(crtc); + struct drm_gem_object *obj; + struct rockchip_gem_object *rk_obj; + unsigned long offset; + unsigned int actual_w; + unsigned int actual_h; + unsigned int dsp_stx; + unsigned int dsp_sty; + unsigned int y_vir_stride; + dma_addr_t yrgb_mst; + enum vop_data_format format; + uint32_t val; + bool is_alpha; + bool visible; + int ret; + struct drm_rect dest = { + .x1 = crtc_x, + .y1 = crtc_y, + .x2 = crtc_x + crtc_w, + .y2 = crtc_y + crtc_h, + }; + struct drm_rect src = { + /* 16.16 fixed point */ + .x1 = src_x, + .y1 = src_y, + .x2 = src_x + src_w, + .y2 = src_y + src_h, + }; + const struct drm_rect clip = { + .x2 = crtc->mode.hdisplay, + .y2 = crtc->mode.vdisplay, + }; + bool can_position = plane->type != DRM_PLANE_TYPE_PRIMARY; + + ret = drm_plane_helper_check_update(plane, crtc, fb, + &src, &dest, &clip, + DRM_PLANE_HELPER_NO_SCALING, + DRM_PLANE_HELPER_NO_SCALING, + can_position, false, &visible); + if (ret) + return ret; + + if (!visible) + return 0; + + is_alpha = is_alpha_support(fb->pixel_format); + format = vop_convert_format(fb->pixel_format); + if (format < 0) + return format; + + obj = rockchip_fb_get_gem_obj(fb, 0); + if (!obj) { + DRM_ERROR("fail to get rockchip gem object from framebuffer\n"); + return -EINVAL; + } + + rk_obj = to_rockchip_obj(obj); + + actual_w = (src.x2 - src.x1) >> 16; + actual_h = (src.y2 - src.y1) >> 16; + crtc_x = max(0, crtc_x); + crtc_y = max(0, crtc_y); + + dsp_stx = crtc_x + crtc->mode.htotal - crtc->mode.hsync_start; + dsp_sty = crtc_y + crtc->mode.vtotal - crtc->mode.vsync_start; + + offset = (src.x1 >> 16) * (fb->bits_per_pixel >> 3); + offset += (src.y1 >> 16) * fb->pitches[0]; + yrgb_mst = rk_obj->dma_addr + offset; + + y_vir_stride = fb->pitches[0] / (fb->bits_per_pixel >> 3); + + /* + * If this plane update changes the plane's framebuffer, (or more + * precisely, if this update has a different framebuffer than the last + * update), enqueue it so we can track when it completes. + * + * Only when we discover that this update has completed, can we + * unreference any previous framebuffers. + */ + mutex_lock(&vop->vsync_mutex); + if (fb != vop_win_last_pending_fb(vop_win)) { + ret = drm_vblank_get(plane->dev, vop->pipe); + if (ret) { + DRM_ERROR("failed to get vblank, %d\n", ret); + mutex_unlock(&vop->vsync_mutex); + return ret; + } + + drm_framebuffer_reference(fb); + + ret = vop_win_queue_fb(vop_win, fb, yrgb_mst, event); + if (ret) { + drm_vblank_put(plane->dev, vop->pipe); + mutex_unlock(&vop->vsync_mutex); + return ret; + } + + vop->vsync_work_pending = true; + } + mutex_unlock(&vop->vsync_mutex); + + spin_lock(&vop->reg_lock); + + VOP_WIN_SET(vop, win, format, format); + VOP_WIN_SET(vop, win, yrgb_vir, y_vir_stride); + VOP_WIN_SET(vop, win, yrgb_mst, yrgb_mst); + val = (actual_h - 1) << 16; + val |= (actual_w - 1) & 0xffff; + VOP_WIN_SET(vop, win, act_info, val); + VOP_WIN_SET(vop, win, dsp_info, val); + val = (dsp_sty - 1) << 16; + val |= (dsp_stx - 1) & 0xffff; + VOP_WIN_SET(vop, win, dsp_st, val); + + if (is_alpha) { + VOP_WIN_SET(vop, win, dst_alpha_ctl, + DST_FACTOR_M0(ALPHA_SRC_INVERSE)); + val = SRC_ALPHA_EN(1) | SRC_COLOR_M0(ALPHA_SRC_PRE_MUL) | + SRC_ALPHA_M0(ALPHA_STRAIGHT) | + SRC_BLEND_M0(ALPHA_PER_PIX) | + SRC_ALPHA_CAL_M0(ALPHA_NO_SATURATION) | + SRC_FACTOR_M0(ALPHA_ONE); + VOP_WIN_SET(vop, win, src_alpha_ctl, val); + } else { + VOP_WIN_SET(vop, win, src_alpha_ctl, SRC_ALPHA_EN(0)); + } + + VOP_WIN_SET(vop, win, enable, 1); + + vop_cfg_done(vop); + spin_unlock(&vop->reg_lock); + + return 0; +} + +static int vop_update_plane(struct drm_plane *plane, struct drm_crtc *crtc, + struct drm_framebuffer *fb, int crtc_x, int crtc_y, + unsigned int crtc_w, unsigned int crtc_h, + uint32_t src_x, uint32_t src_y, uint32_t src_w, + uint32_t src_h) +{ + return vop_update_plane_event(plane, crtc, fb, crtc_x, crtc_y, crtc_w, + crtc_h, src_x, src_y, src_w, src_h, + NULL); +} + +static int vop_update_primary_plane(struct drm_crtc *crtc, + struct drm_pending_vblank_event *event) +{ + unsigned int crtc_w, crtc_h; + + crtc_w = crtc->primary->fb->width - crtc->x; + crtc_h = crtc->primary->fb->height - crtc->y; + + return vop_update_plane_event(crtc->primary, crtc, crtc->primary->fb, + 0, 0, crtc_w, crtc_h, crtc->x << 16, + crtc->y << 16, crtc_w << 16, + crtc_h << 16, event); +} + +static int vop_disable_plane(struct drm_plane *plane) +{ + struct vop_win *vop_win = to_vop_win(plane); + const struct vop_win_data *win = vop_win->data; + struct vop *vop; + int ret; + + if (!plane->crtc) + return 0; + + vop = to_vop(plane->crtc); + + ret = drm_vblank_get(plane->dev, vop->pipe); + if (ret) { + DRM_ERROR("failed to get vblank, %d\n", ret); + return ret; + } + + mutex_lock(&vop->vsync_mutex); + + ret = vop_win_queue_fb(vop_win, NULL, 0, NULL); + if (ret) { + drm_vblank_put(plane->dev, vop->pipe); + mutex_unlock(&vop->vsync_mutex); + return ret; + } + + vop->vsync_work_pending = true; + mutex_unlock(&vop->vsync_mutex); + + spin_lock(&vop->reg_lock); + VOP_WIN_SET(vop, win, enable, 0); + vop_cfg_done(vop); + spin_unlock(&vop->reg_lock); + + return 0; +} + +static void vop_plane_destroy(struct drm_plane *plane) +{ + vop_disable_plane(plane); + drm_plane_cleanup(plane); +} + +static const struct drm_plane_funcs vop_plane_funcs = { + .update_plane = vop_update_plane, + .disable_plane = vop_disable_plane, + .destroy = vop_plane_destroy, +}; + +int rockchip_drm_crtc_mode_config(struct drm_crtc *crtc, + int connector_type, + int out_mode) +{ + struct vop *vop = to_vop(crtc); + + vop->connector_type = connector_type; + vop->connector_out_mode = out_mode; + + return 0; +} + +static int vop_crtc_enable_vblank(struct drm_crtc *crtc) +{ + struct vop *vop = to_vop(crtc); + unsigned long flags; + + if (vop->dpms != DRM_MODE_DPMS_ON) + return -EPERM; + + spin_lock_irqsave(&vop->irq_lock, flags); + + vop_mask_write(vop, INTR_CTRL0, FS_INTR_MASK, FS_INTR_EN(1)); + + spin_unlock_irqrestore(&vop->irq_lock, flags); + + return 0; +} + +static void vop_crtc_disable_vblank(struct drm_crtc *crtc) +{ + struct vop *vop = to_vop(crtc); + unsigned long flags; + + if (vop->dpms != DRM_MODE_DPMS_ON) + return; + spin_lock_irqsave(&vop->irq_lock, flags); + vop_mask_write(vop, INTR_CTRL0, FS_INTR_MASK, FS_INTR_EN(0)); + spin_unlock_irqrestore(&vop->irq_lock, flags); +} + +static const struct rockchip_crtc_funcs private_crtc_funcs = { + .enable_vblank = vop_crtc_enable_vblank, + .disable_vblank = vop_crtc_disable_vblank, +}; + +static void vop_crtc_dpms(struct drm_crtc *crtc, int mode) +{ + struct vop *vop = to_vop(crtc); + + DRM_DEBUG_KMS("crtc[%d] mode[%d]\n", crtc->base.id, mode); + + if (vop->dpms == mode) { + DRM_DEBUG_KMS("desired dpms mode is same as previous one.\n"); + return; + } + + switch (mode) { + case DRM_MODE_DPMS_ON: + vop_enable(crtc); + break; + case DRM_MODE_DPMS_STANDBY: + case DRM_MODE_DPMS_SUSPEND: + case DRM_MODE_DPMS_OFF: + vop_disable(crtc); + break; + default: + DRM_DEBUG_KMS("unspecified mode %d\n", mode); + break; + } + + vop->dpms = mode; +} + +static void vop_crtc_prepare(struct drm_crtc *crtc) +{ + vop_crtc_dpms(crtc, DRM_MODE_DPMS_ON); +} + +static bool vop_crtc_mode_fixup(struct drm_crtc *crtc, + const struct drm_display_mode *mode, + struct drm_display_mode *adjusted_mode) +{ + if (adjusted_mode->htotal == 0 || adjusted_mode->vtotal == 0) + return false; + + return true; +} + +static int vop_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y, + struct drm_framebuffer *old_fb) +{ + int ret; + + crtc->x = x; + crtc->y = y; + + ret = vop_update_primary_plane(crtc, NULL); + if (ret < 0) { + DRM_ERROR("fail to update plane\n"); + return ret; + } + + return 0; +} + +static int vop_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 *fb) +{ + struct vop *vop = to_vop(crtc); + u16 hsync_len = adjusted_mode->hsync_end - adjusted_mode->hsync_start; + u16 hdisplay = adjusted_mode->hdisplay; + u16 htotal = adjusted_mode->htotal; + u16 hact_st = adjusted_mode->htotal - adjusted_mode->hsync_start; + u16 hact_end = hact_st + hdisplay; + u16 vdisplay = adjusted_mode->vdisplay; + u16 vtotal = adjusted_mode->vtotal; + u16 vsync_len = adjusted_mode->vsync_end - adjusted_mode->vsync_start; + u16 vact_st = adjusted_mode->vtotal - adjusted_mode->vsync_start; + u16 vact_end = vact_st + vdisplay; + int ret; + uint32_t val; + + /* + * disable dclk to stop frame scan, so that we can safe config mode and + * enable iommu. + */ + clk_disable(vop->dclk); + + switch (vop->connector_type) { + case DRM_MODE_CONNECTOR_LVDS: + VOP_CTRL_SET(vop, rgb_en, 1); + break; + case DRM_MODE_CONNECTOR_eDP: + VOP_CTRL_SET(vop, edp_en, 1); + break; + case DRM_MODE_CONNECTOR_HDMIA: + VOP_CTRL_SET(vop, hdmi_en, 1); + break; + default: + DRM_ERROR("unsupport connector_type[%d]\n", + vop->connector_type); + return -EINVAL; + }; + VOP_CTRL_SET(vop, out_mode, vop->connector_out_mode); + + val = 0x8; + val |= (adjusted_mode->flags & DRM_MODE_FLAG_NHSYNC) ? 1 : 0; + val |= (adjusted_mode->flags & DRM_MODE_FLAG_NVSYNC) ? (1 << 1) : 0; + VOP_CTRL_SET(vop, pin_pol, val); + + VOP_CTRL_SET(vop, htotal_pw, (htotal << 16) | hsync_len); + val = hact_st << 16; + val |= hact_end; + VOP_CTRL_SET(vop, hact_st_end, val); + VOP_CTRL_SET(vop, hpost_st_end, val); + + VOP_CTRL_SET(vop, vtotal_pw, (vtotal << 16) | vsync_len); + val = vact_st << 16; + val |= vact_end; + VOP_CTRL_SET(vop, vact_st_end, val); + VOP_CTRL_SET(vop, vpost_st_end, val); + + ret = vop_crtc_mode_set_base(crtc, x, y, fb); + if (ret) + return ret; + + /* + * reset dclk, take all mode config affect, so the clk would run in + * correct frame. + */ + reset_control_assert(vop->dclk_rst); + usleep_range(10, 20); + reset_control_deassert(vop->dclk_rst); + + clk_set_rate(vop->dclk, adjusted_mode->clock * 1000); + ret = clk_enable(vop->dclk); + if (ret < 0) { + dev_err(vop->dev, "failed to enable dclk - %d\n", ret); + return ret; + } + + return 0; +} + +static void vop_crtc_commit(struct drm_crtc *crtc) +{ +} + +static const struct drm_crtc_helper_funcs vop_crtc_helper_funcs = { + .dpms = vop_crtc_dpms, + .prepare = vop_crtc_prepare, + .mode_fixup = vop_crtc_mode_fixup, + .mode_set = vop_crtc_mode_set, + .mode_set_base = vop_crtc_mode_set_base, + .commit = vop_crtc_commit, +}; + +static int vop_crtc_page_flip(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_pending_vblank_event *event, + uint32_t page_flip_flags) +{ + struct vop *vop = to_vop(crtc); + struct drm_framebuffer *old_fb = crtc->primary->fb; + int ret; + + /* when the page flip is requested, crtc's dpms should be on */ + if (vop->dpms > DRM_MODE_DPMS_ON) { + DRM_DEBUG("failed page flip request at dpms[%d].\n", vop->dpms); + return 0; + } + + crtc->primary->fb = fb; + + ret = vop_update_primary_plane(crtc, event); + if (ret) + crtc->primary->fb = old_fb; + + return ret; +} + +static void vop_win_state_complete(struct vop_win *vop_win, + struct vop_win_state *state) +{ + struct vop *vop = vop_win->vop; + struct drm_crtc *crtc = &vop->crtc; + struct drm_device *drm = crtc->dev; + unsigned long flags; + + if (state->event) { + spin_lock_irqsave(&drm->event_lock, flags); + drm_send_vblank_event(drm, -1, state->event); + spin_unlock_irqrestore(&drm->event_lock, flags); + } + + list_del(&state->head); + drm_vblank_put(crtc->dev, vop->pipe); +} + +static void vop_crtc_destroy(struct drm_crtc *crtc) +{ + drm_crtc_cleanup(crtc); +} + +static const struct drm_crtc_funcs vop_crtc_funcs = { + .set_config = drm_crtc_helper_set_config, + .page_flip = vop_crtc_page_flip, + .destroy = vop_crtc_destroy, +}; + +static bool vop_win_state_is_active(struct vop_win *vop_win, + struct vop_win_state *state) +{ + bool active = false; + + if (state->fb) { + dma_addr_t yrgb_mst; + + /* check yrgb_mst to tell if pending_fb is now front */ + yrgb_mst = VOP_WIN_GET_YRGBADDR(vop_win->vop, vop_win->data); + + active = (yrgb_mst == state->yrgb_mst); + } else { + bool enabled; + + /* if enable bit is clear, plane is now disabled */ + enabled = VOP_WIN_GET(vop_win->vop, vop_win->data, enable); + + active = (enabled == 0); + } + + return active; +} + +static void vop_win_state_destroy(struct vop_win_state *state) +{ + struct drm_framebuffer *fb = state->fb; + + if (fb) + drm_framebuffer_unreference(fb); + + kfree(state); +} + +static void vop_win_update_state(struct vop_win *vop_win) +{ + struct vop_win_state *state, *n, *new_active = NULL; + + /* Check if any pending states are now active */ + list_for_each_entry(state, &vop_win->pending, head) + if (vop_win_state_is_active(vop_win, state)) { + new_active = state; + break; + } + + if (!new_active) + return; + + /* + * Destroy any 'skipped' pending states - states that were queued + * before the newly active state. + */ + list_for_each_entry_safe(state, n, &vop_win->pending, head) { + if (state == new_active) + break; + vop_win_state_complete(vop_win, state); + vop_win_state_destroy(state); + } + + vop_win_state_complete(vop_win, new_active); + + if (vop_win->active) + vop_win_state_destroy(vop_win->active); + vop_win->active = new_active; +} + +static bool vop_win_has_pending_state(struct vop_win *vop_win) +{ + return !list_empty(&vop_win->pending); +} + +static irqreturn_t vop_isr_thread(int irq, void *data) +{ + struct vop *vop = data; + const struct vop_data *vop_data = vop->data; + unsigned int i; + + mutex_lock(&vop->vsync_mutex); + + if (!vop->vsync_work_pending) + goto done; + + vop->vsync_work_pending = false; + + for (i = 0; i < vop_data->win_size; i++) { + struct vop_win *vop_win = &vop->win[i]; + + vop_win_update_state(vop_win); + if (vop_win_has_pending_state(vop_win)) + vop->vsync_work_pending = true; + } + +done: + mutex_unlock(&vop->vsync_mutex); + + return IRQ_HANDLED; +} + +static irqreturn_t vop_isr(int irq, void *data) +{ + struct vop *vop = data; + uint32_t intr0_reg, active_irqs; + unsigned long flags; + + /* + * INTR_CTRL0 register has interrupt status, enable and clear bits, we + * must hold irq_lock to avoid a race with enable/disable_vblank(). + */ + spin_lock_irqsave(&vop->irq_lock, flags); + intr0_reg = vop_readl(vop, INTR_CTRL0); + active_irqs = intr0_reg & INTR_MASK; + /* Clear all active interrupt sources */ + if (active_irqs) + vop_writel(vop, INTR_CTRL0, + intr0_reg | (active_irqs << INTR_CLR_SHIFT)); + spin_unlock_irqrestore(&vop->irq_lock, flags); + + /* This is expected for vop iommu irqs, since the irq is shared */ + if (!active_irqs) + return IRQ_NONE; + + /* Only Frame Start Interrupt is enabled; other irqs are spurious. */ + if (!(active_irqs & FS_INTR)) { + DRM_ERROR("Unknown VOP IRQs: %#02x\n", active_irqs); + return IRQ_NONE; + } + + drm_handle_vblank(vop->drm_dev, vop->pipe); + + return (vop->vsync_work_pending) ? IRQ_WAKE_THREAD : IRQ_HANDLED; +} + +static int vop_create_crtc(struct vop *vop) +{ + const struct vop_data *vop_data = vop->data; + struct device *dev = vop->dev; + struct drm_device *drm_dev = vop->drm_dev; + struct drm_plane *primary = NULL, *cursor = NULL, *plane; + struct drm_crtc *crtc = &vop->crtc; + struct device_node *port; + int ret; + int i; + + /* + * Create drm_plane for primary and cursor planes first, since we need + * to pass them to drm_crtc_init_with_planes, which sets the + * "possible_crtcs" to the newly initialized crtc. + */ + for (i = 0; i < vop_data->win_size; i++) { + struct vop_win *vop_win = &vop->win[i]; + const struct vop_win_data *win_data = vop_win->data; + + if (win_data->type != DRM_PLANE_TYPE_PRIMARY && + win_data->type != DRM_PLANE_TYPE_CURSOR) + continue; + + ret = drm_universal_plane_init(vop->drm_dev, &vop_win->base, + 0, &vop_plane_funcs, + win_data->phy->data_formats, + win_data->phy->nformats, + win_data->type); + if (ret) { + DRM_ERROR("failed to initialize plane\n"); + goto err_cleanup_planes; + } + + plane = &vop_win->base; + if (plane->type == DRM_PLANE_TYPE_PRIMARY) + primary = plane; + else if (plane->type == DRM_PLANE_TYPE_CURSOR) + cursor = plane; + } + + ret = drm_crtc_init_with_planes(drm_dev, crtc, primary, cursor, + &vop_crtc_funcs); + if (ret) + return ret; + + drm_crtc_helper_add(crtc, &vop_crtc_helper_funcs); + + /* + * Create drm_planes for overlay windows with possible_crtcs restricted + * to the newly created crtc. + */ + for (i = 0; i < vop_data->win_size; i++) { + struct vop_win *vop_win = &vop->win[i]; + const struct vop_win_data *win_data = vop_win->data; + unsigned long possible_crtcs = 1 << drm_crtc_index(crtc); + + if (win_data->type != DRM_PLANE_TYPE_OVERLAY) + continue; + + ret = drm_universal_plane_init(vop->drm_dev, &vop_win->base, + possible_crtcs, + &vop_plane_funcs, + win_data->phy->data_formats, + win_data->phy->nformats, + win_data->type); + if (ret) { + DRM_ERROR("failed to initialize overlay plane\n"); + goto err_cleanup_crtc; + } + } + + port = of_get_child_by_name(dev->of_node, "port"); + if (!port) { + DRM_ERROR("no port node found in %s\n", + dev->of_node->full_name); + goto err_cleanup_crtc; + } + + crtc->port = port; + vop->pipe = drm_crtc_index(crtc); + rockchip_register_crtc_funcs(drm_dev, &private_crtc_funcs, vop->pipe); + + return 0; + +err_cleanup_crtc: + drm_crtc_cleanup(crtc); +err_cleanup_planes: + list_for_each_entry(plane, &drm_dev->mode_config.plane_list, head) + drm_plane_cleanup(plane); + return ret; +} + +static void vop_destroy_crtc(struct vop *vop) +{ + struct drm_crtc *crtc = &vop->crtc; + + rockchip_unregister_crtc_funcs(vop->drm_dev, vop->pipe); + of_node_put(crtc->port); + drm_crtc_cleanup(crtc); +} + +static int vop_initial(struct vop *vop) +{ + const struct vop_data *vop_data = vop->data; + const struct vop_reg_data *init_table = vop_data->init_table; + struct reset_control *ahb_rst; + int i, ret; + + vop->hclk = devm_clk_get(vop->dev, "hclk_vop"); + if (IS_ERR(vop->hclk)) { + dev_err(vop->dev, "failed to get hclk source\n"); + return PTR_ERR(vop->hclk); + } + vop->aclk = devm_clk_get(vop->dev, "aclk_vop"); + if (IS_ERR(vop->aclk)) { + dev_err(vop->dev, "failed to get aclk source\n"); + return PTR_ERR(vop->aclk); + } + vop->dclk = devm_clk_get(vop->dev, "dclk_vop"); + if (IS_ERR(vop->dclk)) { + dev_err(vop->dev, "failed to get dclk source\n"); + return PTR_ERR(vop->dclk); + } + + ret = clk_prepare(vop->hclk); + if (ret < 0) { + dev_err(vop->dev, "failed to prepare hclk\n"); + return ret; + } + + ret = clk_prepare(vop->dclk); + if (ret < 0) { + dev_err(vop->dev, "failed to prepare dclk\n"); + goto err_unprepare_hclk; + } + + ret = clk_prepare(vop->aclk); + if (ret < 0) { + dev_err(vop->dev, "failed to prepare aclk\n"); + goto err_unprepare_dclk; + } + + /* + * enable hclk, so that we can config vop register. + */ + ret = clk_enable(vop->hclk); + if (ret < 0) { + dev_err(vop->dev, "failed to prepare aclk\n"); + goto err_unprepare_aclk; + } + /* + * do hclk_reset, reset all vop registers. + */ + ahb_rst = devm_reset_control_get(vop->dev, "ahb"); + if (IS_ERR(ahb_rst)) { + dev_err(vop->dev, "failed to get ahb reset\n"); + ret = PTR_ERR(ahb_rst); + goto err_disable_hclk; + } + reset_control_assert(ahb_rst); + usleep_range(10, 20); + reset_control_deassert(ahb_rst); + + memcpy(vop->regsbak, vop->regs, vop->len); + + for (i = 0; i < vop_data->table_size; i++) + vop_writel(vop, init_table[i].offset, init_table[i].value); + + for (i = 0; i < vop_data->win_size; i++) { + const struct vop_win_data *win = &vop_data->win[i]; + + VOP_WIN_SET(vop, win, enable, 0); + } + + vop_cfg_done(vop); + + /* + * do dclk_reset, let all config take affect. + */ + vop->dclk_rst = devm_reset_control_get(vop->dev, "dclk"); + if (IS_ERR(vop->dclk_rst)) { + dev_err(vop->dev, "failed to get dclk reset\n"); + ret = PTR_ERR(vop->dclk_rst); + goto err_unprepare_aclk; + } + reset_control_assert(vop->dclk_rst); + usleep_range(10, 20); + reset_control_deassert(vop->dclk_rst); + + clk_disable(vop->hclk); + + vop->dpms = DRM_MODE_DPMS_OFF; + + return 0; + +err_disable_hclk: + clk_disable(vop->hclk); +err_unprepare_aclk: + clk_unprepare(vop->aclk); +err_unprepare_dclk: + clk_unprepare(vop->dclk); +err_unprepare_hclk: + clk_unprepare(vop->hclk); + return ret; +} + +/* + * Initialize the vop->win array elements. + */ +static void vop_win_init(struct vop *vop) +{ + const struct vop_data *vop_data = vop->data; + unsigned int i; + + for (i = 0; i < vop_data->win_size; i++) { + struct vop_win *vop_win = &vop->win[i]; + const struct vop_win_data *win_data = &vop_data->win[i]; + + vop_win->data = win_data; + vop_win->vop = vop; + INIT_LIST_HEAD(&vop_win->pending); + } +} + +static int vop_bind(struct device *dev, struct device *master, void *data) +{ + struct platform_device *pdev = to_platform_device(dev); + const struct of_device_id *of_id; + const struct vop_data *vop_data; + struct drm_device *drm_dev = data; + struct vop *vop; + struct resource *res; + size_t alloc_size; + int ret; + + of_id = of_match_device(vop_driver_dt_match, dev); + vop_data = of_id->data; + if (!vop_data) + return -ENODEV; + + /* Allocate vop struct and its vop_win array */ + alloc_size = sizeof(*vop) + sizeof(*vop->win) * vop_data->win_size; + vop = devm_kzalloc(dev, alloc_size, GFP_KERNEL); + if (!vop) + return -ENOMEM; + + vop->dev = dev; + vop->data = vop_data; + vop->drm_dev = drm_dev; + dev_set_drvdata(dev, vop); + + vop_win_init(vop); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + vop->len = resource_size(res); + vop->regs = devm_ioremap_resource(dev, res); + if (IS_ERR(vop->regs)) + return PTR_ERR(vop->regs); + + vop->regsbak = devm_kzalloc(dev, vop->len, GFP_KERNEL); + if (!vop->regsbak) + return -ENOMEM; + + ret = vop_initial(vop); + if (ret < 0) { + dev_err(&pdev->dev, "cannot initial vop dev - err %d\n", ret); + return ret; + } + + vop->irq = platform_get_irq(pdev, 0); + if (vop->irq < 0) { + dev_err(dev, "cannot find irq for vop\n"); + return vop->irq; + } + + spin_lock_init(&vop->reg_lock); + spin_lock_init(&vop->irq_lock); + + mutex_init(&vop->vsync_mutex); + + ret = devm_request_threaded_irq(dev, vop->irq, vop_isr, vop_isr_thread, + IRQF_SHARED, dev_name(dev), vop); + if (ret) + return ret; + + /* IRQ is initially disabled; it gets enabled in power_on */ + disable_irq(vop->irq); + + ret = vop_create_crtc(vop); + if (ret) + return ret; + + pm_runtime_enable(&pdev->dev); + return 0; +} + +static void vop_unbind(struct device *dev, struct device *master, void *data) +{ + struct vop *vop = dev_get_drvdata(dev); + + pm_runtime_disable(dev); + vop_destroy_crtc(vop); +} + +static const struct component_ops vop_component_ops = { + .bind = vop_bind, + .unbind = vop_unbind, +}; + +static int vop_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + + if (!dev->of_node) { + dev_err(dev, "can't find vop devices\n"); + return -ENODEV; + } + + return component_add(dev, &vop_component_ops); +} + +static int vop_remove(struct platform_device *pdev) +{ + component_del(&pdev->dev, &vop_component_ops); + + return 0; +} + +struct platform_driver vop_platform_driver = { + .probe = vop_probe, + .remove = vop_remove, + .driver = { + .name = "rockchip-vop", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(vop_driver_dt_match), + }, +}; + +module_platform_driver(vop_platform_driver); + +MODULE_AUTHOR("Mark Yao <mark.yao@rock-chips.com>"); +MODULE_DESCRIPTION("ROCKCHIP VOP Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h new file mode 100644 index 000000000000..63e9b3a084c5 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h @@ -0,0 +1,201 @@ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Author:Mark Yao <mark.yao@rock-chips.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ROCKCHIP_DRM_VOP_H +#define _ROCKCHIP_DRM_VOP_H + +/* register definition */ +#define REG_CFG_DONE 0x0000 +#define VERSION_INFO 0x0004 +#define SYS_CTRL 0x0008 +#define SYS_CTRL1 0x000c +#define DSP_CTRL0 0x0010 +#define DSP_CTRL1 0x0014 +#define DSP_BG 0x0018 +#define MCU_CTRL 0x001c +#define INTR_CTRL0 0x0020 +#define INTR_CTRL1 0x0024 +#define WIN0_CTRL0 0x0030 +#define WIN0_CTRL1 0x0034 +#define WIN0_COLOR_KEY 0x0038 +#define WIN0_VIR 0x003c +#define WIN0_YRGB_MST 0x0040 +#define WIN0_CBR_MST 0x0044 +#define WIN0_ACT_INFO 0x0048 +#define WIN0_DSP_INFO 0x004c +#define WIN0_DSP_ST 0x0050 +#define WIN0_SCL_FACTOR_YRGB 0x0054 +#define WIN0_SCL_FACTOR_CBR 0x0058 +#define WIN0_SCL_OFFSET 0x005c +#define WIN0_SRC_ALPHA_CTRL 0x0060 +#define WIN0_DST_ALPHA_CTRL 0x0064 +#define WIN0_FADING_CTRL 0x0068 +/* win1 register */ +#define WIN1_CTRL0 0x0070 +#define WIN1_CTRL1 0x0074 +#define WIN1_COLOR_KEY 0x0078 +#define WIN1_VIR 0x007c +#define WIN1_YRGB_MST 0x0080 +#define WIN1_CBR_MST 0x0084 +#define WIN1_ACT_INFO 0x0088 +#define WIN1_DSP_INFO 0x008c +#define WIN1_DSP_ST 0x0090 +#define WIN1_SCL_FACTOR_YRGB 0x0094 +#define WIN1_SCL_FACTOR_CBR 0x0098 +#define WIN1_SCL_OFFSET 0x009c +#define WIN1_SRC_ALPHA_CTRL 0x00a0 +#define WIN1_DST_ALPHA_CTRL 0x00a4 +#define WIN1_FADING_CTRL 0x00a8 +/* win2 register */ +#define WIN2_CTRL0 0x00b0 +#define WIN2_CTRL1 0x00b4 +#define WIN2_VIR0_1 0x00b8 +#define WIN2_VIR2_3 0x00bc +#define WIN2_MST0 0x00c0 +#define WIN2_DSP_INFO0 0x00c4 +#define WIN2_DSP_ST0 0x00c8 +#define WIN2_COLOR_KEY 0x00cc +#define WIN2_MST1 0x00d0 +#define WIN2_DSP_INFO1 0x00d4 +#define WIN2_DSP_ST1 0x00d8 +#define WIN2_SRC_ALPHA_CTRL 0x00dc +#define WIN2_MST2 0x00e0 +#define WIN2_DSP_INFO2 0x00e4 +#define WIN2_DSP_ST2 0x00e8 +#define WIN2_DST_ALPHA_CTRL 0x00ec +#define WIN2_MST3 0x00f0 +#define WIN2_DSP_INFO3 0x00f4 +#define WIN2_DSP_ST3 0x00f8 +#define WIN2_FADING_CTRL 0x00fc +/* win3 register */ +#define WIN3_CTRL0 0x0100 +#define WIN3_CTRL1 0x0104 +#define WIN3_VIR0_1 0x0108 +#define WIN3_VIR2_3 0x010c +#define WIN3_MST0 0x0110 +#define WIN3_DSP_INFO0 0x0114 +#define WIN3_DSP_ST0 0x0118 +#define WIN3_COLOR_KEY 0x011c +#define WIN3_MST1 0x0120 +#define WIN3_DSP_INFO1 0x0124 +#define WIN3_DSP_ST1 0x0128 +#define WIN3_SRC_ALPHA_CTRL 0x012c +#define WIN3_MST2 0x0130 +#define WIN3_DSP_INFO2 0x0134 +#define WIN3_DSP_ST2 0x0138 +#define WIN3_DST_ALPHA_CTRL 0x013c +#define WIN3_MST3 0x0140 +#define WIN3_DSP_INFO3 0x0144 +#define WIN3_DSP_ST3 0x0148 +#define WIN3_FADING_CTRL 0x014c +/* hwc register */ +#define HWC_CTRL0 0x0150 +#define HWC_CTRL1 0x0154 +#define HWC_MST 0x0158 +#define HWC_DSP_ST 0x015c +#define HWC_SRC_ALPHA_CTRL 0x0160 +#define HWC_DST_ALPHA_CTRL 0x0164 +#define HWC_FADING_CTRL 0x0168 +/* post process register */ +#define POST_DSP_HACT_INFO 0x0170 +#define POST_DSP_VACT_INFO 0x0174 +#define POST_SCL_FACTOR_YRGB 0x0178 +#define POST_SCL_CTRL 0x0180 +#define POST_DSP_VACT_INFO_F1 0x0184 +#define DSP_HTOTAL_HS_END 0x0188 +#define DSP_HACT_ST_END 0x018c +#define DSP_VTOTAL_VS_END 0x0190 +#define DSP_VACT_ST_END 0x0194 +#define DSP_VS_ST_END_F1 0x0198 +#define DSP_VACT_ST_END_F1 0x019c +/* register definition end */ + +/* interrupt define */ +#define DSP_HOLD_VALID_INTR (1 << 0) +#define FS_INTR (1 << 1) +#define LINE_FLAG_INTR (1 << 2) +#define BUS_ERROR_INTR (1 << 3) + +#define INTR_MASK (DSP_HOLD_VALID_INTR | FS_INTR | \ + LINE_FLAG_INTR | BUS_ERROR_INTR) + +#define DSP_HOLD_VALID_INTR_EN(x) ((x) << 4) +#define FS_INTR_EN(x) ((x) << 5) +#define LINE_FLAG_INTR_EN(x) ((x) << 6) +#define BUS_ERROR_INTR_EN(x) ((x) << 7) +#define DSP_HOLD_VALID_INTR_MASK (1 << 4) +#define FS_INTR_MASK (1 << 5) +#define LINE_FLAG_INTR_MASK (1 << 6) +#define BUS_ERROR_INTR_MASK (1 << 7) + +#define INTR_CLR_SHIFT 8 +#define DSP_HOLD_VALID_INTR_CLR (1 << (INTR_CLR_SHIFT + 0)) +#define FS_INTR_CLR (1 << (INTR_CLR_SHIFT + 1)) +#define LINE_FLAG_INTR_CLR (1 << (INTR_CLR_SHIFT + 2)) +#define BUS_ERROR_INTR_CLR (1 << (INTR_CLR_SHIFT + 3)) + +#define DSP_LINE_NUM(x) (((x) & 0x1fff) << 12) +#define DSP_LINE_NUM_MASK (0x1fff << 12) + +/* src alpha ctrl define */ +#define SRC_FADING_VALUE(x) (((x) & 0xff) << 24) +#define SRC_GLOBAL_ALPHA(x) (((x) & 0xff) << 16) +#define SRC_FACTOR_M0(x) (((x) & 0x7) << 6) +#define SRC_ALPHA_CAL_M0(x) (((x) & 0x1) << 5) +#define SRC_BLEND_M0(x) (((x) & 0x3) << 3) +#define SRC_ALPHA_M0(x) (((x) & 0x1) << 2) +#define SRC_COLOR_M0(x) (((x) & 0x1) << 1) +#define SRC_ALPHA_EN(x) (((x) & 0x1) << 0) +/* dst alpha ctrl define */ +#define DST_FACTOR_M0(x) (((x) & 0x7) << 6) + +/* + * display output interface supported by rockchip lcdc + */ +#define ROCKCHIP_OUT_MODE_P888 0 +#define ROCKCHIP_OUT_MODE_P666 1 +#define ROCKCHIP_OUT_MODE_P565 2 +/* for use special outface */ +#define ROCKCHIP_OUT_MODE_AAAA 15 + +enum alpha_mode { + ALPHA_STRAIGHT, + ALPHA_INVERSE, +}; + +enum global_blend_mode { + ALPHA_GLOBAL, + ALPHA_PER_PIX, + ALPHA_PER_PIX_GLOBAL, +}; + +enum alpha_cal_mode { + ALPHA_SATURATION, + ALPHA_NO_SATURATION, +}; + +enum color_mode { + ALPHA_SRC_PRE_MUL, + ALPHA_SRC_NO_PRE_MUL, +}; + +enum factor_mode { + ALPHA_ZERO, + ALPHA_ONE, + ALPHA_SRC, + ALPHA_SRC_INVERSE, + ALPHA_SRC_GLOBAL, +}; + +#endif /* _ROCKCHIP_DRM_VOP_H */ diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c index 8ce508e76208..3820ae97a030 100644 --- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c +++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c @@ -93,7 +93,8 @@ EXPORT_SYMBOL(ttm_eu_backoff_reservation); */ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, - struct list_head *list, bool intr) + struct list_head *list, bool intr, + struct list_head *dups) { struct ttm_bo_global *glob; struct ttm_validate_buffer *entry; @@ -117,6 +118,13 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, __ttm_bo_unreserve(bo); ret = -EBUSY; + + } else if (ret == -EALREADY && dups) { + struct ttm_validate_buffer *safe = entry; + entry = list_prev_entry(entry, head); + list_del(&safe->head); + list_add(&safe->head, dups); + continue; } if (!ret) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index db7621828bc7..7b5d22110f25 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1062,8 +1062,12 @@ static long vmw_generic_ioctl(struct file *filp, unsigned int cmd, vmaster = vmw_master_check(dev, file_priv, flags); if (unlikely(IS_ERR(vmaster))) { - DRM_INFO("IOCTL ERROR %d\n", nr); - return PTR_ERR(vmaster); + ret = PTR_ERR(vmaster); + + if (ret != -ERESTARTSYS) + DRM_INFO("IOCTL ERROR Command %d, Error %ld.\n", + nr, ret); + return ret; } ret = ioctl_func(filp, cmd, arg); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 596cd6dafd33..33176d05db35 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -2487,7 +2487,8 @@ int vmw_execbuf_process(struct drm_file *file_priv, if (unlikely(ret != 0)) goto out_err_nores; - ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes, true); + ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes, + true, NULL); if (unlikely(ret != 0)) goto out_err; @@ -2677,7 +2678,8 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv, query_val.shared = false; list_add_tail(&query_val.head, &validate_list); - ret = ttm_eu_reserve_buffers(&ticket, &validate_list, false); + ret = ttm_eu_reserve_buffers(&ticket, &validate_list, + false, NULL); if (unlikely(ret != 0)) { vmw_execbuf_unpin_panic(dev_priv); goto out_no_reserve; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 197164fd7803..b7594cb758af 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -545,35 +545,19 @@ void vmw_fence_obj_flush(struct vmw_fence_obj *fence) static void vmw_fence_destroy(struct vmw_fence_obj *fence) { - struct vmw_fence_manager *fman = fman_from_fence(fence); - fence_free(&fence->base); - - /* - * Free kernel space accounting. - */ - ttm_mem_global_free(vmw_mem_glob(fman->dev_priv), - fman->fence_size); } int vmw_fence_create(struct vmw_fence_manager *fman, uint32_t seqno, struct vmw_fence_obj **p_fence) { - struct ttm_mem_global *mem_glob = vmw_mem_glob(fman->dev_priv); struct vmw_fence_obj *fence; int ret; - ret = ttm_mem_global_alloc(mem_glob, fman->fence_size, - false, false); - if (unlikely(ret != 0)) - return ret; - fence = kzalloc(sizeof(*fence), GFP_KERNEL); - if (unlikely(fence == NULL)) { - ret = -ENOMEM; - goto out_no_object; - } + if (unlikely(fence == NULL)) + return -ENOMEM; ret = vmw_fence_obj_init(fman, fence, seqno, vmw_fence_destroy); @@ -585,8 +569,6 @@ int vmw_fence_create(struct vmw_fence_manager *fman, out_err_init: kfree(fence); -out_no_object: - ttm_mem_global_free(mem_glob, fman->fence_size); return ret; } @@ -1105,6 +1087,8 @@ static int vmw_event_fence_action_create(struct drm_file *file_priv, if (ret != 0) goto out_no_queue; + return 0; + out_no_queue: event->base.destroy(&event->base); out_no_event: @@ -1180,17 +1164,10 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data, BUG_ON(fence == NULL); - if (arg->flags & DRM_VMW_FE_FLAG_REQ_TIME) - ret = vmw_event_fence_action_create(file_priv, fence, - arg->flags, - arg->user_data, - true); - else - ret = vmw_event_fence_action_create(file_priv, fence, - arg->flags, - arg->user_data, - true); - + ret = vmw_event_fence_action_create(file_priv, fence, + arg->flags, + arg->user_data, + true); if (unlikely(ret != 0)) { if (ret != -ERESTARTSYS) DRM_ERROR("Failed to attach event to fence.\n"); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 026de7cea0f6..210ef15b1d09 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -1222,7 +1222,7 @@ vmw_resource_check_buffer(struct vmw_resource *res, val_buf->bo = ttm_bo_reference(&res->backup->base); val_buf->shared = false; list_add_tail(&val_buf->head, &val_list); - ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible); + ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible, NULL); if (unlikely(ret != 0)) goto out_no_reserve; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 8719fb3cccc9..6a4584a43aa6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -198,7 +198,7 @@ static int vmw_gb_shader_bind(struct vmw_resource *res, cmd->header.size = sizeof(cmd->body); cmd->body.shid = res->id; cmd->body.mobid = bo->mem.start; - cmd->body.offsetInBytes = 0; + cmd->body.offsetInBytes = res->backup_offset; res->backup_dirty = false; vmw_fifo_commit(dev_priv, sizeof(*cmd)); diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index 63f3f03ecc9b..c604f4c3ac0d 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -111,6 +111,8 @@ #define CDNS_I2C_DIVA_MAX 4 #define CDNS_I2C_DIVB_MAX 64 +#define CDNS_I2C_TIMEOUT_MAX 0xFF + #define cdns_i2c_readreg(offset) readl_relaxed(id->membase + offset) #define cdns_i2c_writereg(val, offset) writel_relaxed(val, id->membase + offset) @@ -852,6 +854,15 @@ static int cdns_i2c_probe(struct platform_device *pdev) goto err_clk_dis; } + /* + * Cadence I2C controller has a bug wherein it generates + * invalid read transaction after HW timeout in master receiver mode. + * HW timeout is not used by this driver and the interrupt is disabled. + * But the feature itself cannot be disabled. Hence maximum value + * is written to this register to reduce the chances of error. + */ + cdns_i2c_writereg(CDNS_I2C_TIMEOUT_MAX, CDNS_I2C_TIME_OUT_OFFSET); + dev_info(&pdev->dev, "%u kHz mmio %08lx irq %d\n", id->i2c_clk / 1000, (unsigned long)r_mem->start, id->irq); diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index d15b7c9b9219..01f0cd87a4a5 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -407,11 +407,9 @@ i2c_davinci_xfer_msg(struct i2c_adapter *adap, struct i2c_msg *msg, int stop) if (dev->cmd_err & DAVINCI_I2C_STR_NACK) { if (msg->flags & I2C_M_IGNORE_NAK) return msg->len; - if (stop) { - w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG); - w |= DAVINCI_I2C_MDR_STP; - davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w); - } + w = davinci_i2c_read_reg(dev, DAVINCI_I2C_MDR_REG); + w |= DAVINCI_I2C_MDR_STP; + davinci_i2c_write_reg(dev, DAVINCI_I2C_MDR_REG, w); return -EREMOTEIO; } return -EIO; diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index edca99dbba23..23628b7bfb8d 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -359,7 +359,7 @@ int i2c_dw_init(struct dw_i2c_dev *dev) } /* Configure Tx/Rx FIFO threshold levels */ - dw_writel(dev, dev->tx_fifo_depth - 1, DW_IC_TX_TL); + dw_writel(dev, dev->tx_fifo_depth / 2, DW_IC_TX_TL); dw_writel(dev, 0, DW_IC_RX_TL); /* configure the i2c master */ diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 26942c159de1..277a2288d4a8 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -922,14 +922,12 @@ omap_i2c_isr_thread(int this_irq, void *dev_id) if (stat & OMAP_I2C_STAT_NACK) { err |= OMAP_I2C_STAT_NACK; omap_i2c_ack_stat(dev, OMAP_I2C_STAT_NACK); - break; } if (stat & OMAP_I2C_STAT_AL) { dev_err(dev->dev, "Arbitration lost\n"); err |= OMAP_I2C_STAT_AL; omap_i2c_ack_stat(dev, OMAP_I2C_STAT_AL); - break; } /* @@ -954,11 +952,13 @@ omap_i2c_isr_thread(int this_irq, void *dev_id) if (dev->fifo_size) num_bytes = dev->buf_len; - omap_i2c_receive_data(dev, num_bytes, true); - - if (dev->errata & I2C_OMAP_ERRATA_I207) + if (dev->errata & I2C_OMAP_ERRATA_I207) { i2c_omap_errata_i207(dev, stat); + num_bytes = (omap_i2c_read_reg(dev, + OMAP_I2C_BUFSTAT_REG) >> 8) & 0x3F; + } + omap_i2c_receive_data(dev, num_bytes, true); omap_i2c_ack_stat(dev, OMAP_I2C_STAT_RDR); continue; } diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index bc203485716d..8afa28e4570e 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -421,7 +421,7 @@ static int evdev_open(struct inode *inode, struct file *file) err_free_client: evdev_detach_client(evdev, client); - kfree(client); + kvfree(client); return error; } diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index dd5112265cc9..d0a1261eb1ba 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -152,6 +152,18 @@ config OMAP_IOMMU_DEBUG Say N unless you know you need this. +config ROCKCHIP_IOMMU + bool "Rockchip IOMMU Support" + depends on ARCH_ROCKCHIP + select IOMMU_API + select ARM_DMA_USE_IOMMU + help + Support for IOMMUs found on Rockchip rk32xx SOCs. + These IOMMUs allow virtualization of the address space used by most + cores within the multimedia subsystem. + Say Y here if you are using a Rockchip SoC that includes an IOMMU + device. + config TEGRA_IOMMU_GART bool "Tegra GART IOMMU Support" depends on ARCH_TEGRA_2x_SOC diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 16edef74b8ee..3e47ef35a35f 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -13,6 +13,7 @@ obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o obj-$(CONFIG_OMAP_IOMMU) += omap-iommu2.o obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o +obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c new file mode 100644 index 000000000000..b2023af384b9 --- /dev/null +++ b/drivers/iommu/rockchip-iommu.c @@ -0,0 +1,1038 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <asm/cacheflush.h> +#include <asm/pgtable.h> +#include <linux/compiler.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/iommu.h> +#include <linux/jiffies.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +/** MMU register offsets */ +#define RK_MMU_DTE_ADDR 0x00 /* Directory table address */ +#define RK_MMU_STATUS 0x04 +#define RK_MMU_COMMAND 0x08 +#define RK_MMU_PAGE_FAULT_ADDR 0x0C /* IOVA of last page fault */ +#define RK_MMU_ZAP_ONE_LINE 0x10 /* Shootdown one IOTLB entry */ +#define RK_MMU_INT_RAWSTAT 0x14 /* IRQ status ignoring mask */ +#define RK_MMU_INT_CLEAR 0x18 /* Acknowledge and re-arm irq */ +#define RK_MMU_INT_MASK 0x1C /* IRQ enable */ +#define RK_MMU_INT_STATUS 0x20 /* IRQ status after masking */ +#define RK_MMU_AUTO_GATING 0x24 + +#define DTE_ADDR_DUMMY 0xCAFEBABE +#define FORCE_RESET_TIMEOUT 100 /* ms */ + +/* RK_MMU_STATUS fields */ +#define RK_MMU_STATUS_PAGING_ENABLED BIT(0) +#define RK_MMU_STATUS_PAGE_FAULT_ACTIVE BIT(1) +#define RK_MMU_STATUS_STALL_ACTIVE BIT(2) +#define RK_MMU_STATUS_IDLE BIT(3) +#define RK_MMU_STATUS_REPLAY_BUFFER_EMPTY BIT(4) +#define RK_MMU_STATUS_PAGE_FAULT_IS_WRITE BIT(5) +#define RK_MMU_STATUS_STALL_NOT_ACTIVE BIT(31) + +/* RK_MMU_COMMAND command values */ +#define RK_MMU_CMD_ENABLE_PAGING 0 /* Enable memory translation */ +#define RK_MMU_CMD_DISABLE_PAGING 1 /* Disable memory translation */ +#define RK_MMU_CMD_ENABLE_STALL 2 /* Stall paging to allow other cmds */ +#define RK_MMU_CMD_DISABLE_STALL 3 /* Stop stall re-enables paging */ +#define RK_MMU_CMD_ZAP_CACHE 4 /* Shoot down entire IOTLB */ +#define RK_MMU_CMD_PAGE_FAULT_DONE 5 /* Clear page fault */ +#define RK_MMU_CMD_FORCE_RESET 6 /* Reset all registers */ + +/* RK_MMU_INT_* register fields */ +#define RK_MMU_IRQ_PAGE_FAULT 0x01 /* page fault */ +#define RK_MMU_IRQ_BUS_ERROR 0x02 /* bus read error */ +#define RK_MMU_IRQ_MASK (RK_MMU_IRQ_PAGE_FAULT | RK_MMU_IRQ_BUS_ERROR) + +#define NUM_DT_ENTRIES 1024 +#define NUM_PT_ENTRIES 1024 + +#define SPAGE_ORDER 12 +#define SPAGE_SIZE (1 << SPAGE_ORDER) + + /* + * Support mapping any size that fits in one page table: + * 4 KiB to 4 MiB + */ +#define RK_IOMMU_PGSIZE_BITMAP 0x007ff000 + +#define IOMMU_REG_POLL_COUNT_FAST 1000 + +struct rk_iommu_domain { + struct list_head iommus; + u32 *dt; /* page directory table */ + spinlock_t iommus_lock; /* lock for iommus list */ + spinlock_t dt_lock; /* lock for modifying page directory table */ +}; + +struct rk_iommu { + struct device *dev; + void __iomem *base; + int irq; + struct list_head node; /* entry in rk_iommu_domain.iommus */ + struct iommu_domain *domain; /* domain to which iommu is attached */ +}; + +static inline void rk_table_flush(u32 *va, unsigned int count) +{ + phys_addr_t pa_start = virt_to_phys(va); + phys_addr_t pa_end = virt_to_phys(va + count); + size_t size = pa_end - pa_start; + + __cpuc_flush_dcache_area(va, size); + outer_flush_range(pa_start, pa_end); +} + +/** + * Inspired by _wait_for in intel_drv.h + * This is NOT safe for use in interrupt context. + * + * Note that it's important that we check the condition again after having + * timed out, since the timeout could be due to preemption or similar and + * we've never had a chance to check the condition before the timeout. + */ +#define rk_wait_for(COND, MS) ({ \ + unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1; \ + int ret__ = 0; \ + while (!(COND)) { \ + if (time_after(jiffies, timeout__)) { \ + ret__ = (COND) ? 0 : -ETIMEDOUT; \ + break; \ + } \ + usleep_range(50, 100); \ + } \ + ret__; \ +}) + +/* + * The Rockchip rk3288 iommu uses a 2-level page table. + * The first level is the "Directory Table" (DT). + * The DT consists of 1024 4-byte Directory Table Entries (DTEs), each pointing + * to a "Page Table". + * The second level is the 1024 Page Tables (PT). + * Each PT consists of 1024 4-byte Page Table Entries (PTEs), each pointing to + * a 4 KB page of physical memory. + * + * The DT and each PT fits in a single 4 KB page (4-bytes * 1024 entries). + * Each iommu device has a MMU_DTE_ADDR register that contains the physical + * address of the start of the DT page. + * + * The structure of the page table is as follows: + * + * DT + * MMU_DTE_ADDR -> +-----+ + * | | + * +-----+ PT + * | DTE | -> +-----+ + * +-----+ | | Memory + * | | +-----+ Page + * | | | PTE | -> +-----+ + * +-----+ +-----+ | | + * | | | | + * | | | | + * +-----+ | | + * | | + * | | + * +-----+ + */ + +/* + * Each DTE has a PT address and a valid bit: + * +---------------------+-----------+-+ + * | PT address | Reserved |V| + * +---------------------+-----------+-+ + * 31:12 - PT address (PTs always starts on a 4 KB boundary) + * 11: 1 - Reserved + * 0 - 1 if PT @ PT address is valid + */ +#define RK_DTE_PT_ADDRESS_MASK 0xfffff000 +#define RK_DTE_PT_VALID BIT(0) + +static inline phys_addr_t rk_dte_pt_address(u32 dte) +{ + return (phys_addr_t)dte & RK_DTE_PT_ADDRESS_MASK; +} + +static inline bool rk_dte_is_pt_valid(u32 dte) +{ + return dte & RK_DTE_PT_VALID; +} + +static u32 rk_mk_dte(u32 *pt) +{ + phys_addr_t pt_phys = virt_to_phys(pt); + return (pt_phys & RK_DTE_PT_ADDRESS_MASK) | RK_DTE_PT_VALID; +} + +/* + * Each PTE has a Page address, some flags and a valid bit: + * +---------------------+---+-------+-+ + * | Page address |Rsv| Flags |V| + * +---------------------+---+-------+-+ + * 31:12 - Page address (Pages always start on a 4 KB boundary) + * 11: 9 - Reserved + * 8: 1 - Flags + * 8 - Read allocate - allocate cache space on read misses + * 7 - Read cache - enable cache & prefetch of data + * 6 - Write buffer - enable delaying writes on their way to memory + * 5 - Write allocate - allocate cache space on write misses + * 4 - Write cache - different writes can be merged together + * 3 - Override cache attributes + * if 1, bits 4-8 control cache attributes + * if 0, the system bus defaults are used + * 2 - Writable + * 1 - Readable + * 0 - 1 if Page @ Page address is valid + */ +#define RK_PTE_PAGE_ADDRESS_MASK 0xfffff000 +#define RK_PTE_PAGE_FLAGS_MASK 0x000001fe +#define RK_PTE_PAGE_WRITABLE BIT(2) +#define RK_PTE_PAGE_READABLE BIT(1) +#define RK_PTE_PAGE_VALID BIT(0) + +static inline phys_addr_t rk_pte_page_address(u32 pte) +{ + return (phys_addr_t)pte & RK_PTE_PAGE_ADDRESS_MASK; +} + +static inline bool rk_pte_is_page_valid(u32 pte) +{ + return pte & RK_PTE_PAGE_VALID; +} + +/* TODO: set cache flags per prot IOMMU_CACHE */ +static u32 rk_mk_pte(phys_addr_t page, int prot) +{ + u32 flags = 0; + flags |= (prot & IOMMU_READ) ? RK_PTE_PAGE_READABLE : 0; + flags |= (prot & IOMMU_WRITE) ? RK_PTE_PAGE_WRITABLE : 0; + page &= RK_PTE_PAGE_ADDRESS_MASK; + return page | flags | RK_PTE_PAGE_VALID; +} + +static u32 rk_mk_pte_invalid(u32 pte) +{ + return pte & ~RK_PTE_PAGE_VALID; +} + +/* + * rk3288 iova (IOMMU Virtual Address) format + * 31 22.21 12.11 0 + * +-----------+-----------+-------------+ + * | DTE index | PTE index | Page offset | + * +-----------+-----------+-------------+ + * 31:22 - DTE index - index of DTE in DT + * 21:12 - PTE index - index of PTE in PT @ DTE.pt_address + * 11: 0 - Page offset - offset into page @ PTE.page_address + */ +#define RK_IOVA_DTE_MASK 0xffc00000 +#define RK_IOVA_DTE_SHIFT 22 +#define RK_IOVA_PTE_MASK 0x003ff000 +#define RK_IOVA_PTE_SHIFT 12 +#define RK_IOVA_PAGE_MASK 0x00000fff +#define RK_IOVA_PAGE_SHIFT 0 + +static u32 rk_iova_dte_index(dma_addr_t iova) +{ + return (u32)(iova & RK_IOVA_DTE_MASK) >> RK_IOVA_DTE_SHIFT; +} + +static u32 rk_iova_pte_index(dma_addr_t iova) +{ + return (u32)(iova & RK_IOVA_PTE_MASK) >> RK_IOVA_PTE_SHIFT; +} + +static u32 rk_iova_page_offset(dma_addr_t iova) +{ + return (u32)(iova & RK_IOVA_PAGE_MASK) >> RK_IOVA_PAGE_SHIFT; +} + +static u32 rk_iommu_read(struct rk_iommu *iommu, u32 offset) +{ + return readl(iommu->base + offset); +} + +static void rk_iommu_write(struct rk_iommu *iommu, u32 offset, u32 value) +{ + writel(value, iommu->base + offset); +} + +static void rk_iommu_command(struct rk_iommu *iommu, u32 command) +{ + writel(command, iommu->base + RK_MMU_COMMAND); +} + +static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova, + size_t size) +{ + dma_addr_t iova_end = iova + size; + /* + * TODO(djkurtz): Figure out when it is more efficient to shootdown the + * entire iotlb rather than iterate over individual iovas. + */ + for (; iova < iova_end; iova += SPAGE_SIZE) + rk_iommu_write(iommu, RK_MMU_ZAP_ONE_LINE, iova); +} + +static bool rk_iommu_is_stall_active(struct rk_iommu *iommu) +{ + return rk_iommu_read(iommu, RK_MMU_STATUS) & RK_MMU_STATUS_STALL_ACTIVE; +} + +static bool rk_iommu_is_paging_enabled(struct rk_iommu *iommu) +{ + return rk_iommu_read(iommu, RK_MMU_STATUS) & + RK_MMU_STATUS_PAGING_ENABLED; +} + +static int rk_iommu_enable_stall(struct rk_iommu *iommu) +{ + int ret; + + if (rk_iommu_is_stall_active(iommu)) + return 0; + + /* Stall can only be enabled if paging is enabled */ + if (!rk_iommu_is_paging_enabled(iommu)) + return 0; + + rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_STALL); + + ret = rk_wait_for(rk_iommu_is_stall_active(iommu), 1); + if (ret) + dev_err(iommu->dev, "Enable stall request timed out, status: %#08x\n", + rk_iommu_read(iommu, RK_MMU_STATUS)); + + return ret; +} + +static int rk_iommu_disable_stall(struct rk_iommu *iommu) +{ + int ret; + + if (!rk_iommu_is_stall_active(iommu)) + return 0; + + rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_STALL); + + ret = rk_wait_for(!rk_iommu_is_stall_active(iommu), 1); + if (ret) + dev_err(iommu->dev, "Disable stall request timed out, status: %#08x\n", + rk_iommu_read(iommu, RK_MMU_STATUS)); + + return ret; +} + +static int rk_iommu_enable_paging(struct rk_iommu *iommu) +{ + int ret; + + if (rk_iommu_is_paging_enabled(iommu)) + return 0; + + rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_PAGING); + + ret = rk_wait_for(rk_iommu_is_paging_enabled(iommu), 1); + if (ret) + dev_err(iommu->dev, "Enable paging request timed out, status: %#08x\n", + rk_iommu_read(iommu, RK_MMU_STATUS)); + + return ret; +} + +static int rk_iommu_disable_paging(struct rk_iommu *iommu) +{ + int ret; + + if (!rk_iommu_is_paging_enabled(iommu)) + return 0; + + rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_PAGING); + + ret = rk_wait_for(!rk_iommu_is_paging_enabled(iommu), 1); + if (ret) + dev_err(iommu->dev, "Disable paging request timed out, status: %#08x\n", + rk_iommu_read(iommu, RK_MMU_STATUS)); + + return ret; +} + +static int rk_iommu_force_reset(struct rk_iommu *iommu) +{ + int ret; + u32 dte_addr; + + /* + * Check if register DTE_ADDR is working by writing DTE_ADDR_DUMMY + * and verifying that upper 5 nybbles are read back. + */ + rk_iommu_write(iommu, RK_MMU_DTE_ADDR, DTE_ADDR_DUMMY); + + dte_addr = rk_iommu_read(iommu, RK_MMU_DTE_ADDR); + if (dte_addr != (DTE_ADDR_DUMMY & RK_DTE_PT_ADDRESS_MASK)) { + dev_err(iommu->dev, "Error during raw reset. MMU_DTE_ADDR is not functioning\n"); + return -EFAULT; + } + + rk_iommu_command(iommu, RK_MMU_CMD_FORCE_RESET); + + ret = rk_wait_for(rk_iommu_read(iommu, RK_MMU_DTE_ADDR) == 0x00000000, + FORCE_RESET_TIMEOUT); + if (ret) + dev_err(iommu->dev, "FORCE_RESET command timed out\n"); + + return ret; +} + +static void log_iova(struct rk_iommu *iommu, dma_addr_t iova) +{ + u32 dte_index, pte_index, page_offset; + u32 mmu_dte_addr; + phys_addr_t mmu_dte_addr_phys, dte_addr_phys; + u32 *dte_addr; + u32 dte; + phys_addr_t pte_addr_phys = 0; + u32 *pte_addr = NULL; + u32 pte = 0; + phys_addr_t page_addr_phys = 0; + u32 page_flags = 0; + + dte_index = rk_iova_dte_index(iova); + pte_index = rk_iova_pte_index(iova); + page_offset = rk_iova_page_offset(iova); + + mmu_dte_addr = rk_iommu_read(iommu, RK_MMU_DTE_ADDR); + mmu_dte_addr_phys = (phys_addr_t)mmu_dte_addr; + + dte_addr_phys = mmu_dte_addr_phys + (4 * dte_index); + dte_addr = phys_to_virt(dte_addr_phys); + dte = *dte_addr; + + if (!rk_dte_is_pt_valid(dte)) + goto print_it; + + pte_addr_phys = rk_dte_pt_address(dte) + (pte_index * 4); + pte_addr = phys_to_virt(pte_addr_phys); + pte = *pte_addr; + + if (!rk_pte_is_page_valid(pte)) + goto print_it; + + page_addr_phys = rk_pte_page_address(pte) + page_offset; + page_flags = pte & RK_PTE_PAGE_FLAGS_MASK; + +print_it: + dev_err(iommu->dev, "iova = %pad: dte_index: %#03x pte_index: %#03x page_offset: %#03x\n", + &iova, dte_index, pte_index, page_offset); + dev_err(iommu->dev, "mmu_dte_addr: %pa dte@%pa: %#08x valid: %u pte@%pa: %#08x valid: %u page@%pa flags: %#03x\n", + &mmu_dte_addr_phys, &dte_addr_phys, dte, + rk_dte_is_pt_valid(dte), &pte_addr_phys, pte, + rk_pte_is_page_valid(pte), &page_addr_phys, page_flags); +} + +static irqreturn_t rk_iommu_irq(int irq, void *dev_id) +{ + struct rk_iommu *iommu = dev_id; + u32 status; + u32 int_status; + dma_addr_t iova; + + int_status = rk_iommu_read(iommu, RK_MMU_INT_STATUS); + if (int_status == 0) + return IRQ_NONE; + + iova = rk_iommu_read(iommu, RK_MMU_PAGE_FAULT_ADDR); + + if (int_status & RK_MMU_IRQ_PAGE_FAULT) { + int flags; + + status = rk_iommu_read(iommu, RK_MMU_STATUS); + flags = (status & RK_MMU_STATUS_PAGE_FAULT_IS_WRITE) ? + IOMMU_FAULT_WRITE : IOMMU_FAULT_READ; + + dev_err(iommu->dev, "Page fault at %pad of type %s\n", + &iova, + (flags == IOMMU_FAULT_WRITE) ? "write" : "read"); + + log_iova(iommu, iova); + + /* + * Report page fault to any installed handlers. + * Ignore the return code, though, since we always zap cache + * and clear the page fault anyway. + */ + if (iommu->domain) + report_iommu_fault(iommu->domain, iommu->dev, iova, + flags); + else + dev_err(iommu->dev, "Page fault while iommu not attached to domain?\n"); + + rk_iommu_command(iommu, RK_MMU_CMD_ZAP_CACHE); + rk_iommu_command(iommu, RK_MMU_CMD_PAGE_FAULT_DONE); + } + + if (int_status & RK_MMU_IRQ_BUS_ERROR) + dev_err(iommu->dev, "BUS_ERROR occurred at %pad\n", &iova); + + if (int_status & ~RK_MMU_IRQ_MASK) + dev_err(iommu->dev, "unexpected int_status: %#08x\n", + int_status); + + rk_iommu_write(iommu, RK_MMU_INT_CLEAR, int_status); + + return IRQ_HANDLED; +} + +static phys_addr_t rk_iommu_iova_to_phys(struct iommu_domain *domain, + dma_addr_t iova) +{ + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + phys_addr_t pt_phys, phys = 0; + u32 dte, pte; + u32 *page_table; + + spin_lock_irqsave(&rk_domain->dt_lock, flags); + + dte = rk_domain->dt[rk_iova_dte_index(iova)]; + if (!rk_dte_is_pt_valid(dte)) + goto out; + + pt_phys = rk_dte_pt_address(dte); + page_table = (u32 *)phys_to_virt(pt_phys); + pte = page_table[rk_iova_pte_index(iova)]; + if (!rk_pte_is_page_valid(pte)) + goto out; + + phys = rk_pte_page_address(pte) + rk_iova_page_offset(iova); +out: + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + + return phys; +} + +static void rk_iommu_zap_iova(struct rk_iommu_domain *rk_domain, + dma_addr_t iova, size_t size) +{ + struct list_head *pos; + unsigned long flags; + + /* shootdown these iova from all iommus using this domain */ + spin_lock_irqsave(&rk_domain->iommus_lock, flags); + list_for_each(pos, &rk_domain->iommus) { + struct rk_iommu *iommu; + iommu = list_entry(pos, struct rk_iommu, node); + rk_iommu_zap_lines(iommu, iova, size); + } + spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); +} + +static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain, + dma_addr_t iova) +{ + u32 *page_table, *dte_addr; + u32 dte; + phys_addr_t pt_phys; + + assert_spin_locked(&rk_domain->dt_lock); + + dte_addr = &rk_domain->dt[rk_iova_dte_index(iova)]; + dte = *dte_addr; + if (rk_dte_is_pt_valid(dte)) + goto done; + + page_table = (u32 *)get_zeroed_page(GFP_ATOMIC | GFP_DMA32); + if (!page_table) + return ERR_PTR(-ENOMEM); + + dte = rk_mk_dte(page_table); + *dte_addr = dte; + + rk_table_flush(page_table, NUM_PT_ENTRIES); + rk_table_flush(dte_addr, 1); + + /* + * Zap the first iova of newly allocated page table so iommu evicts + * old cached value of new dte from the iotlb. + */ + rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE); + +done: + pt_phys = rk_dte_pt_address(dte); + return (u32 *)phys_to_virt(pt_phys); +} + +static size_t rk_iommu_unmap_iova(struct rk_iommu_domain *rk_domain, + u32 *pte_addr, dma_addr_t iova, size_t size) +{ + unsigned int pte_count; + unsigned int pte_total = size / SPAGE_SIZE; + + assert_spin_locked(&rk_domain->dt_lock); + + for (pte_count = 0; pte_count < pte_total; pte_count++) { + u32 pte = pte_addr[pte_count]; + if (!rk_pte_is_page_valid(pte)) + break; + + pte_addr[pte_count] = rk_mk_pte_invalid(pte); + } + + rk_table_flush(pte_addr, pte_count); + + return pte_count * SPAGE_SIZE; +} + +static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr, + dma_addr_t iova, phys_addr_t paddr, size_t size, + int prot) +{ + unsigned int pte_count; + unsigned int pte_total = size / SPAGE_SIZE; + phys_addr_t page_phys; + + assert_spin_locked(&rk_domain->dt_lock); + + for (pte_count = 0; pte_count < pte_total; pte_count++) { + u32 pte = pte_addr[pte_count]; + + if (rk_pte_is_page_valid(pte)) + goto unwind; + + pte_addr[pte_count] = rk_mk_pte(paddr, prot); + + paddr += SPAGE_SIZE; + } + + rk_table_flush(pte_addr, pte_count); + + return 0; +unwind: + /* Unmap the range of iovas that we just mapped */ + rk_iommu_unmap_iova(rk_domain, pte_addr, iova, pte_count * SPAGE_SIZE); + + iova += pte_count * SPAGE_SIZE; + page_phys = rk_pte_page_address(pte_addr[pte_count]); + pr_err("iova: %pad already mapped to %pa cannot remap to phys: %pa prot: %#x\n", + &iova, &page_phys, &paddr, prot); + + return -EADDRINUSE; +} + +static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova, + phys_addr_t paddr, size_t size, int prot) +{ + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + dma_addr_t iova = (dma_addr_t)_iova; + u32 *page_table, *pte_addr; + int ret; + + spin_lock_irqsave(&rk_domain->dt_lock, flags); + + /* + * pgsize_bitmap specifies iova sizes that fit in one page table + * (1024 4-KiB pages = 4 MiB). + * So, size will always be 4096 <= size <= 4194304. + * Since iommu_map() guarantees that both iova and size will be + * aligned, we will always only be mapping from a single dte here. + */ + page_table = rk_dte_get_page_table(rk_domain, iova); + if (IS_ERR(page_table)) { + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + return PTR_ERR(page_table); + } + + pte_addr = &page_table[rk_iova_pte_index(iova)]; + ret = rk_iommu_map_iova(rk_domain, pte_addr, iova, paddr, size, prot); + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + + return ret; +} + +static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova, + size_t size) +{ + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + dma_addr_t iova = (dma_addr_t)_iova; + phys_addr_t pt_phys; + u32 dte; + u32 *pte_addr; + size_t unmap_size; + + spin_lock_irqsave(&rk_domain->dt_lock, flags); + + /* + * pgsize_bitmap specifies iova sizes that fit in one page table + * (1024 4-KiB pages = 4 MiB). + * So, size will always be 4096 <= size <= 4194304. + * Since iommu_unmap() guarantees that both iova and size will be + * aligned, we will always only be unmapping from a single dte here. + */ + dte = rk_domain->dt[rk_iova_dte_index(iova)]; + /* Just return 0 if iova is unmapped */ + if (!rk_dte_is_pt_valid(dte)) { + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + return 0; + } + + pt_phys = rk_dte_pt_address(dte); + pte_addr = (u32 *)phys_to_virt(pt_phys) + rk_iova_pte_index(iova); + unmap_size = rk_iommu_unmap_iova(rk_domain, pte_addr, iova, size); + + spin_unlock_irqrestore(&rk_domain->dt_lock, flags); + + /* Shootdown iotlb entries for iova range that was just unmapped */ + rk_iommu_zap_iova(rk_domain, iova, unmap_size); + + return unmap_size; +} + +static struct rk_iommu *rk_iommu_from_dev(struct device *dev) +{ + struct iommu_group *group; + struct device *iommu_dev; + struct rk_iommu *rk_iommu; + + group = iommu_group_get(dev); + if (!group) + return NULL; + iommu_dev = iommu_group_get_iommudata(group); + rk_iommu = dev_get_drvdata(iommu_dev); + iommu_group_put(group); + + return rk_iommu; +} + +static int rk_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct rk_iommu *iommu; + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + int ret; + phys_addr_t dte_addr; + + /* + * Allow 'virtual devices' (e.g., drm) to attach to domain. + * Such a device does not belong to an iommu group. + */ + iommu = rk_iommu_from_dev(dev); + if (!iommu) + return 0; + + ret = rk_iommu_enable_stall(iommu); + if (ret) + return ret; + + ret = rk_iommu_force_reset(iommu); + if (ret) + return ret; + + iommu->domain = domain; + + ret = devm_request_irq(dev, iommu->irq, rk_iommu_irq, + IRQF_SHARED, dev_name(dev), iommu); + if (ret) + return ret; + + dte_addr = virt_to_phys(rk_domain->dt); + rk_iommu_write(iommu, RK_MMU_DTE_ADDR, dte_addr); + rk_iommu_command(iommu, RK_MMU_CMD_ZAP_CACHE); + rk_iommu_write(iommu, RK_MMU_INT_MASK, RK_MMU_IRQ_MASK); + + ret = rk_iommu_enable_paging(iommu); + if (ret) + return ret; + + spin_lock_irqsave(&rk_domain->iommus_lock, flags); + list_add_tail(&iommu->node, &rk_domain->iommus); + spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); + + dev_info(dev, "Attached to iommu domain\n"); + + rk_iommu_disable_stall(iommu); + + return 0; +} + +static void rk_iommu_detach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct rk_iommu *iommu; + struct rk_iommu_domain *rk_domain = domain->priv; + unsigned long flags; + + /* Allow 'virtual devices' (eg drm) to detach from domain */ + iommu = rk_iommu_from_dev(dev); + if (!iommu) + return; + + spin_lock_irqsave(&rk_domain->iommus_lock, flags); + list_del_init(&iommu->node); + spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); + + /* Ignore error while disabling, just keep going */ + rk_iommu_enable_stall(iommu); + rk_iommu_disable_paging(iommu); + rk_iommu_write(iommu, RK_MMU_INT_MASK, 0); + rk_iommu_write(iommu, RK_MMU_DTE_ADDR, 0); + rk_iommu_disable_stall(iommu); + + devm_free_irq(dev, iommu->irq, iommu); + + iommu->domain = NULL; + + dev_info(dev, "Detached from iommu domain\n"); +} + +static int rk_iommu_domain_init(struct iommu_domain *domain) +{ + struct rk_iommu_domain *rk_domain; + + rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL); + if (!rk_domain) + return -ENOMEM; + + /* + * rk32xx iommus use a 2 level pagetable. + * Each level1 (dt) and level2 (pt) table has 1024 4-byte entries. + * Allocate one 4 KiB page for each table. + */ + rk_domain->dt = (u32 *)get_zeroed_page(GFP_KERNEL | GFP_DMA32); + if (!rk_domain->dt) + goto err_dt; + + rk_table_flush(rk_domain->dt, NUM_DT_ENTRIES); + + spin_lock_init(&rk_domain->iommus_lock); + spin_lock_init(&rk_domain->dt_lock); + INIT_LIST_HEAD(&rk_domain->iommus); + + domain->priv = rk_domain; + + return 0; +err_dt: + kfree(rk_domain); + return -ENOMEM; +} + +static void rk_iommu_domain_destroy(struct iommu_domain *domain) +{ + struct rk_iommu_domain *rk_domain = domain->priv; + int i; + + WARN_ON(!list_empty(&rk_domain->iommus)); + + for (i = 0; i < NUM_DT_ENTRIES; i++) { + u32 dte = rk_domain->dt[i]; + if (rk_dte_is_pt_valid(dte)) { + phys_addr_t pt_phys = rk_dte_pt_address(dte); + u32 *page_table = phys_to_virt(pt_phys); + free_page((unsigned long)page_table); + } + } + + free_page((unsigned long)rk_domain->dt); + kfree(domain->priv); + domain->priv = NULL; +} + +static bool rk_iommu_is_dev_iommu_master(struct device *dev) +{ + struct device_node *np = dev->of_node; + int ret; + + /* + * An iommu master has an iommus property containing a list of phandles + * to iommu nodes, each with an #iommu-cells property with value 0. + */ + ret = of_count_phandle_with_args(np, "iommus", "#iommu-cells"); + return (ret > 0); +} + +static int rk_iommu_group_set_iommudata(struct iommu_group *group, + struct device *dev) +{ + struct device_node *np = dev->of_node; + struct platform_device *pd; + int ret; + struct of_phandle_args args; + + /* + * An iommu master has an iommus property containing a list of phandles + * to iommu nodes, each with an #iommu-cells property with value 0. + */ + ret = of_parse_phandle_with_args(np, "iommus", "#iommu-cells", 0, + &args); + if (ret) { + dev_err(dev, "of_parse_phandle_with_args(%s) => %d\n", + np->full_name, ret); + return ret; + } + if (args.args_count != 0) { + dev_err(dev, "incorrect number of iommu params found for %s (found %d, expected 0)\n", + args.np->full_name, args.args_count); + return -EINVAL; + } + + pd = of_find_device_by_node(args.np); + of_node_put(args.np); + if (!pd) { + dev_err(dev, "iommu %s not found\n", args.np->full_name); + return -EPROBE_DEFER; + } + + /* TODO(djkurtz): handle multiple slave iommus for a single master */ + iommu_group_set_iommudata(group, &pd->dev, NULL); + + return 0; +} + +static int rk_iommu_add_device(struct device *dev) +{ + struct iommu_group *group; + int ret; + + if (!rk_iommu_is_dev_iommu_master(dev)) + return -ENODEV; + + group = iommu_group_get(dev); + if (!group) { + group = iommu_group_alloc(); + if (IS_ERR(group)) { + dev_err(dev, "Failed to allocate IOMMU group\n"); + return PTR_ERR(group); + } + } + + ret = iommu_group_add_device(group, dev); + if (ret) + goto err_put_group; + + ret = rk_iommu_group_set_iommudata(group, dev); + if (ret) + goto err_remove_device; + + iommu_group_put(group); + + return 0; + +err_remove_device: + iommu_group_remove_device(dev); +err_put_group: + iommu_group_put(group); + return ret; +} + +static void rk_iommu_remove_device(struct device *dev) +{ + if (!rk_iommu_is_dev_iommu_master(dev)) + return; + + iommu_group_remove_device(dev); +} + +static const struct iommu_ops rk_iommu_ops = { + .domain_init = rk_iommu_domain_init, + .domain_destroy = rk_iommu_domain_destroy, + .attach_dev = rk_iommu_attach_device, + .detach_dev = rk_iommu_detach_device, + .map = rk_iommu_map, + .unmap = rk_iommu_unmap, + .add_device = rk_iommu_add_device, + .remove_device = rk_iommu_remove_device, + .iova_to_phys = rk_iommu_iova_to_phys, + .pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP, +}; + +static int rk_iommu_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rk_iommu *iommu; + struct resource *res; + + iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL); + if (!iommu) + return -ENOMEM; + + platform_set_drvdata(pdev, iommu); + iommu->dev = dev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + iommu->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(iommu->base)) + return PTR_ERR(iommu->base); + + iommu->irq = platform_get_irq(pdev, 0); + if (iommu->irq < 0) { + dev_err(dev, "Failed to get IRQ, %d\n", iommu->irq); + return -ENXIO; + } + + return 0; +} + +static int rk_iommu_remove(struct platform_device *pdev) +{ + return 0; +} + +#ifdef CONFIG_OF +static const struct of_device_id rk_iommu_dt_ids[] = { + { .compatible = "rockchip,iommu" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, rk_iommu_dt_ids); +#endif + +static struct platform_driver rk_iommu_driver = { + .probe = rk_iommu_probe, + .remove = rk_iommu_remove, + .driver = { + .name = "rk_iommu", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(rk_iommu_dt_ids), + }, +}; + +static int __init rk_iommu_init(void) +{ + int ret; + + ret = bus_set_iommu(&platform_bus_type, &rk_iommu_ops); + if (ret) + return ret; + + return platform_driver_register(&rk_iommu_driver); +} +static void __exit rk_iommu_exit(void) +{ + platform_driver_unregister(&rk_iommu_driver); +} + +subsys_initcall(rk_iommu_init); +module_exit(rk_iommu_exit); + +MODULE_DESCRIPTION("IOMMU API for Rockchip"); +MODULE_AUTHOR("Simon Xue <xxm@rock-chips.com> and Daniel Kurtz <djkurtz@chromium.org>"); +MODULE_ALIAS("platform:rockchip-iommu"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c index 932ed9be9ff3..b10aaeda2bb4 100644 --- a/drivers/media/i2c/smiapp/smiapp-core.c +++ b/drivers/media/i2c/smiapp/smiapp-core.c @@ -2190,7 +2190,7 @@ static int smiapp_set_selection(struct v4l2_subdev *subdev, ret = smiapp_set_compose(subdev, fh, sel); break; default: - BUG(); + ret = -EINVAL; } mutex_unlock(&sensor->mutex); diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c index 331eddac7222..3bd386c371f7 100644 --- a/drivers/media/pci/cx23885/cx23885-core.c +++ b/drivers/media/pci/cx23885/cx23885-core.c @@ -1078,7 +1078,7 @@ static __le32 *cx23885_risc_field(__le32 *rp, struct scatterlist *sglist, for (line = 0; line < lines; line++) { while (offset && offset >= sg_dma_len(sg)) { offset -= sg_dma_len(sg); - sg++; + sg = sg_next(sg); } if (lpi && line > 0 && !(line % lpi)) @@ -1101,14 +1101,14 @@ static __le32 *cx23885_risc_field(__le32 *rp, struct scatterlist *sglist, *(rp++) = cpu_to_le32(0); /* bits 63-32 */ todo -= (sg_dma_len(sg)-offset); offset = 0; - sg++; + sg = sg_next(sg); while (todo > sg_dma_len(sg)) { *(rp++) = cpu_to_le32(RISC_WRITE| sg_dma_len(sg)); *(rp++) = cpu_to_le32(sg_dma_address(sg)); *(rp++) = cpu_to_le32(0); /* bits 63-32 */ todo -= sg_dma_len(sg); - sg++; + sg = sg_next(sg); } *(rp++) = cpu_to_le32(RISC_WRITE|RISC_EOL|todo); *(rp++) = cpu_to_le32(sg_dma_address(sg)); diff --git a/drivers/media/pci/solo6x10/solo6x10-core.c b/drivers/media/pci/solo6x10/solo6x10-core.c index 172583d736fe..8cbe6b49f4c2 100644 --- a/drivers/media/pci/solo6x10/solo6x10-core.c +++ b/drivers/media/pci/solo6x10/solo6x10-core.c @@ -105,11 +105,8 @@ static irqreturn_t solo_isr(int irq, void *data) if (!status) return IRQ_NONE; - if (status & ~solo_dev->irq_mask) { - solo_reg_write(solo_dev, SOLO_IRQ_STAT, - status & ~solo_dev->irq_mask); - status &= solo_dev->irq_mask; - } + /* Acknowledge all interrupts immediately */ + solo_reg_write(solo_dev, SOLO_IRQ_STAT, status); if (status & SOLO_IRQ_PCI_ERR) solo_p2m_error_isr(solo_dev); @@ -132,9 +129,6 @@ static irqreturn_t solo_isr(int irq, void *data) if (status & SOLO_IRQ_G723) solo_g723_isr(solo_dev); - /* Clear all interrupts handled */ - solo_reg_write(solo_dev, SOLO_IRQ_STAT, status); - return IRQ_HANDLED; } diff --git a/drivers/media/rc/ir-rc6-decoder.c b/drivers/media/rc/ir-rc6-decoder.c index f1f098e22f7e..d16bc67af732 100644 --- a/drivers/media/rc/ir-rc6-decoder.c +++ b/drivers/media/rc/ir-rc6-decoder.c @@ -259,8 +259,8 @@ again: case 32: if ((scancode & RC6_6A_LCC_MASK) == RC6_6A_MCE_CC) { protocol = RC_TYPE_RC6_MCE; - scancode &= ~RC6_6A_MCE_TOGGLE_MASK; toggle = !!(scancode & RC6_6A_MCE_TOGGLE_MASK); + scancode &= ~RC6_6A_MCE_TOGGLE_MASK; } else { protocol = RC_BIT_RC6_6A_32; toggle = 0; diff --git a/drivers/media/usb/s2255/s2255drv.c b/drivers/media/usb/s2255/s2255drv.c index ccc00099b261..1c0dbf428a3a 100644 --- a/drivers/media/usb/s2255/s2255drv.c +++ b/drivers/media/usb/s2255/s2255drv.c @@ -632,7 +632,7 @@ static void s2255_fillbuff(struct s2255_vc *vc, break; case V4L2_PIX_FMT_JPEG: case V4L2_PIX_FMT_MJPEG: - buf->vb.v4l2_buf.length = jpgsize; + vb2_set_plane_payload(&buf->vb, 0, jpgsize); memcpy(vbuf, tmpbuf, jpgsize); break; case V4L2_PIX_FMT_YUV422P: diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index c13d83e15ace..45f09a66e6c9 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -225,7 +225,12 @@ static int bond_changelink(struct net_device *bond_dev, bond_option_arp_ip_targets_clear(bond); nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) { - __be32 target = nla_get_be32(attr); + __be32 target; + + if (nla_len(attr) < sizeof(target)) + return -EINVAL; + + target = nla_get_be32(attr); bond_opt_initval(&newval, (__force u64)target); err = __bond_opt_set(bond, BOND_OPT_ARP_TARGETS, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 8520d5529df8..279873cb6e3a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2442,9 +2442,13 @@ static unsigned int from_fw_linkcaps(unsigned int type, unsigned int caps) SUPPORTED_10000baseKR_Full | SUPPORTED_1000baseKX_Full | SUPPORTED_10000baseKX4_Full; else if (type == FW_PORT_TYPE_FIBER_XFI || - type == FW_PORT_TYPE_FIBER_XAUI || type == FW_PORT_TYPE_SFP) + type == FW_PORT_TYPE_FIBER_XAUI || type == FW_PORT_TYPE_SFP) { v |= SUPPORTED_FIBRE; - else if (type == FW_PORT_TYPE_BP40_BA) + if (caps & FW_PORT_CAP_SPEED_1G) + v |= SUPPORTED_1000baseT_Full; + if (caps & FW_PORT_CAP_SPEED_10G) + v |= SUPPORTED_10000baseT_Full; + } else if (type == FW_PORT_TYPE_BP40_BA) v |= SUPPORTED_40000baseSR4_Full; if (caps & FW_PORT_CAP_ANEG) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 60e9c2cd051e..b5db6b3f939f 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -917,21 +917,13 @@ static int sh_eth_reset(struct net_device *ndev) return ret; } -#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE) static void sh_eth_set_receive_align(struct sk_buff *skb) { - int reserve; + uintptr_t reserve = (uintptr_t)skb->data & (SH_ETH_RX_ALIGN - 1); - reserve = SH4_SKB_RX_ALIGN - ((u32)skb->data & (SH4_SKB_RX_ALIGN - 1)); if (reserve) - skb_reserve(skb, reserve); + skb_reserve(skb, SH_ETH_RX_ALIGN - reserve); } -#else -static void sh_eth_set_receive_align(struct sk_buff *skb) -{ - skb_reserve(skb, SH2_SH3_SKB_RX_ALIGN); -} -#endif /* CPU <-> EDMAC endian convert */ @@ -1119,6 +1111,7 @@ static void sh_eth_ring_format(struct net_device *ndev) struct sh_eth_txdesc *txdesc = NULL; int rx_ringsize = sizeof(*rxdesc) * mdp->num_rx_ring; int tx_ringsize = sizeof(*txdesc) * mdp->num_tx_ring; + int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1; mdp->cur_rx = 0; mdp->cur_tx = 0; @@ -1131,21 +1124,21 @@ static void sh_eth_ring_format(struct net_device *ndev) for (i = 0; i < mdp->num_rx_ring; i++) { /* skb */ mdp->rx_skbuff[i] = NULL; - skb = netdev_alloc_skb(ndev, mdp->rx_buf_sz); + skb = netdev_alloc_skb(ndev, skbuff_size); mdp->rx_skbuff[i] = skb; if (skb == NULL) break; - dma_map_single(&ndev->dev, skb->data, mdp->rx_buf_sz, - DMA_FROM_DEVICE); sh_eth_set_receive_align(skb); /* RX descriptor */ rxdesc = &mdp->rx_ring[i]; + /* The size of the buffer is a multiple of 16 bytes. */ + rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16); + dma_map_single(&ndev->dev, skb->data, rxdesc->buffer_length, + DMA_FROM_DEVICE); rxdesc->addr = virt_to_phys(PTR_ALIGN(skb->data, 4)); rxdesc->status = cpu_to_edmac(mdp, RD_RACT | RD_RFP); - /* The size of the buffer is 16 byte boundary. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16); /* Rx descriptor address set */ if (i == 0) { sh_eth_write(ndev, mdp->rx_desc_dma, RDLAR); @@ -1397,6 +1390,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) struct sk_buff *skb; u16 pkt_len = 0; u32 desc_status; + int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1; rxdesc = &mdp->rx_ring[entry]; while (!(rxdesc->status & cpu_to_edmac(mdp, RD_RACT))) { @@ -1448,7 +1442,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) if (mdp->cd->rpadir) skb_reserve(skb, NET_IP_ALIGN); dma_sync_single_for_cpu(&ndev->dev, rxdesc->addr, - mdp->rx_buf_sz, + ALIGN(mdp->rx_buf_sz, 16), DMA_FROM_DEVICE); skb_put(skb, pkt_len); skb->protocol = eth_type_trans(skb, ndev); @@ -1468,13 +1462,13 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16); if (mdp->rx_skbuff[entry] == NULL) { - skb = netdev_alloc_skb(ndev, mdp->rx_buf_sz); + skb = netdev_alloc_skb(ndev, skbuff_size); mdp->rx_skbuff[entry] = skb; if (skb == NULL) break; /* Better luck next round. */ - dma_map_single(&ndev->dev, skb->data, mdp->rx_buf_sz, - DMA_FROM_DEVICE); sh_eth_set_receive_align(skb); + dma_map_single(&ndev->dev, skb->data, + rxdesc->buffer_length, DMA_FROM_DEVICE); skb_checksum_none_assert(skb); rxdesc->addr = virt_to_phys(PTR_ALIGN(skb->data, 4)); @@ -2042,6 +2036,8 @@ static int sh_eth_open(struct net_device *ndev) if (ret) goto out_free_irq; + mdp->is_opened = 1; + return ret; out_free_irq: @@ -2131,6 +2127,36 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +static struct net_device_stats *sh_eth_get_stats(struct net_device *ndev) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + + if (sh_eth_is_rz_fast_ether(mdp)) + return &ndev->stats; + + if (!mdp->is_opened) + return &ndev->stats; + + ndev->stats.tx_dropped += sh_eth_read(ndev, TROCR); + sh_eth_write(ndev, 0, TROCR); /* (write clear) */ + ndev->stats.collisions += sh_eth_read(ndev, CDCR); + sh_eth_write(ndev, 0, CDCR); /* (write clear) */ + ndev->stats.tx_carrier_errors += sh_eth_read(ndev, LCCR); + sh_eth_write(ndev, 0, LCCR); /* (write clear) */ + + if (sh_eth_is_gether(mdp)) { + ndev->stats.tx_carrier_errors += sh_eth_read(ndev, CERCR); + sh_eth_write(ndev, 0, CERCR); /* (write clear) */ + ndev->stats.tx_carrier_errors += sh_eth_read(ndev, CEECR); + sh_eth_write(ndev, 0, CEECR); /* (write clear) */ + } else { + ndev->stats.tx_carrier_errors += sh_eth_read(ndev, CNDCR); + sh_eth_write(ndev, 0, CNDCR); /* (write clear) */ + } + + return &ndev->stats; +} + /* device close function */ static int sh_eth_close(struct net_device *ndev) { @@ -2145,6 +2171,7 @@ static int sh_eth_close(struct net_device *ndev) sh_eth_write(ndev, 0, EDTRR); sh_eth_write(ndev, 0, EDRRR); + sh_eth_get_stats(ndev); /* PHY Disconnect */ if (mdp->phydev) { phy_stop(mdp->phydev); @@ -2163,36 +2190,9 @@ static int sh_eth_close(struct net_device *ndev) pm_runtime_put_sync(&mdp->pdev->dev); - return 0; -} - -static struct net_device_stats *sh_eth_get_stats(struct net_device *ndev) -{ - struct sh_eth_private *mdp = netdev_priv(ndev); - - if (sh_eth_is_rz_fast_ether(mdp)) - return &ndev->stats; + mdp->is_opened = 0; - pm_runtime_get_sync(&mdp->pdev->dev); - - ndev->stats.tx_dropped += sh_eth_read(ndev, TROCR); - sh_eth_write(ndev, 0, TROCR); /* (write clear) */ - ndev->stats.collisions += sh_eth_read(ndev, CDCR); - sh_eth_write(ndev, 0, CDCR); /* (write clear) */ - ndev->stats.tx_carrier_errors += sh_eth_read(ndev, LCCR); - sh_eth_write(ndev, 0, LCCR); /* (write clear) */ - if (sh_eth_is_gether(mdp)) { - ndev->stats.tx_carrier_errors += sh_eth_read(ndev, CERCR); - sh_eth_write(ndev, 0, CERCR); /* (write clear) */ - ndev->stats.tx_carrier_errors += sh_eth_read(ndev, CEECR); - sh_eth_write(ndev, 0, CEECR); /* (write clear) */ - } else { - ndev->stats.tx_carrier_errors += sh_eth_read(ndev, CNDCR); - sh_eth_write(ndev, 0, CNDCR); /* (write clear) */ - } - pm_runtime_put_sync(&mdp->pdev->dev); - - return &ndev->stats; + return 0; } /* ioctl to device function */ diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index b37c427144ee..22301bf9c21d 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -162,9 +162,9 @@ enum { /* Driver's parameters */ #if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE) -#define SH4_SKB_RX_ALIGN 32 +#define SH_ETH_RX_ALIGN 32 #else -#define SH2_SH3_SKB_RX_ALIGN 2 +#define SH_ETH_RX_ALIGN 2 #endif /* Register's bits @@ -522,6 +522,7 @@ struct sh_eth_private { unsigned no_ether_link:1; unsigned ether_link_active_low:1; + unsigned is_opened:1; }; static inline void sh_eth_soft_swap(char *src, int len) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5b0da3986216..58a1a0a423d4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -265,6 +265,15 @@ static int stmmac_pltfr_probe(struct platform_device *pdev) plat_dat = dev_get_platdata(&pdev->dev); + if (!plat_dat) + plat_dat = devm_kzalloc(&pdev->dev, + sizeof(struct plat_stmmacenet_data), + GFP_KERNEL); + if (!plat_dat) { + pr_err("%s: ERROR: no memory", __func__); + return -ENOMEM; + } + /* Set default value for multicast hash bins */ plat_dat->multicast_filter_bins = HASH_TABLE_SIZE; @@ -272,15 +281,6 @@ static int stmmac_pltfr_probe(struct platform_device *pdev) plat_dat->unicast_filter_entries = 1; if (pdev->dev.of_node) { - if (!plat_dat) - plat_dat = devm_kzalloc(&pdev->dev, - sizeof(struct plat_stmmacenet_data), - GFP_KERNEL); - if (!plat_dat) { - pr_err("%s: ERROR: no memory", __func__); - return -ENOMEM; - } - ret = stmmac_probe_config_dt(pdev, plat_dat, &mac); if (ret) { pr_err("%s: main dt probe failed", __func__); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index cca871346a0f..ece8d1804d13 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -496,9 +496,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct netfront_queue *queue, len = skb_frag_size(frag); offset = frag->page_offset; - /* Data must not cross a page boundary. */ - BUG_ON(len + offset > PAGE_SIZE<<compound_order(page)); - /* Skip unused frames from start of page */ page += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; @@ -506,8 +503,6 @@ static void xennet_make_frags(struct sk_buff *skb, struct netfront_queue *queue, while (len > 0) { unsigned long bytes; - BUG_ON(offset >= PAGE_SIZE); - bytes = PAGE_SIZE - offset; if (bytes > len) bytes = len; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 30e97bcc4f88..d134710de96d 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -964,8 +964,6 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size) int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, bool nomap) { - if (memblock_is_region_reserved(base, size)) - return -EBUSY; if (nomap) return memblock_remove(base, size); return memblock_reserve(base, size); diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c index 3d43874319be..19bb19c7db4a 100644 --- a/drivers/pci/host/pci-tegra.c +++ b/drivers/pci/host/pci-tegra.c @@ -276,6 +276,7 @@ struct tegra_pcie { struct resource all; struct resource io; + struct resource pio; struct resource mem; struct resource prefetch; struct resource busn; @@ -658,7 +659,6 @@ static int tegra_pcie_setup(int nr, struct pci_sys_data *sys) { struct tegra_pcie *pcie = sys_to_pcie(sys); int err; - phys_addr_t io_start; err = devm_request_resource(pcie->dev, &pcie->all, &pcie->mem); if (err < 0) @@ -668,14 +668,12 @@ static int tegra_pcie_setup(int nr, struct pci_sys_data *sys) if (err) return err; - io_start = pci_pio_to_address(pcie->io.start); - pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset); pci_add_resource_offset(&sys->resources, &pcie->prefetch, sys->mem_offset); pci_add_resource(&sys->resources, &pcie->busn); - pci_ioremap_io(nr * SZ_64K, io_start); + pci_ioremap_io(pcie->pio.start, pcie->io.start); return 1; } @@ -786,7 +784,6 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg) static void tegra_pcie_setup_translations(struct tegra_pcie *pcie) { u32 fpci_bar, size, axi_address; - phys_addr_t io_start = pci_pio_to_address(pcie->io.start); /* Bar 0: type 1 extended configuration space */ fpci_bar = 0xfe100000; @@ -799,7 +796,7 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie) /* Bar 1: downstream IO bar */ fpci_bar = 0xfdfc0000; size = resource_size(&pcie->io); - axi_address = io_start; + axi_address = pcie->io.start; afi_writel(pcie, axi_address, AFI_AXI_BAR1_START); afi_writel(pcie, size >> 12, AFI_AXI_BAR1_SZ); afi_writel(pcie, fpci_bar, AFI_FPCI_BAR1); @@ -1690,8 +1687,23 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie) switch (res.flags & IORESOURCE_TYPE_BITS) { case IORESOURCE_IO: - memcpy(&pcie->io, &res, sizeof(res)); - pcie->io.name = np->full_name; + memcpy(&pcie->pio, &res, sizeof(res)); + pcie->pio.name = np->full_name; + + /* + * The Tegra PCIe host bridge uses this to program the + * mapping of the I/O space to the physical address, + * so we override the .start and .end fields here that + * of_pci_range_to_resource() converted to I/O space. + * We also set the IORESOURCE_MEM type to clarify that + * the resource is in the physical memory space. + */ + pcie->io.start = range.cpu_addr; + pcie->io.end = range.cpu_addr + range.size - 1; + pcie->io.flags = IORESOURCE_MEM; + pcie->io.name = "I/O"; + + memcpy(&res, &pcie->io, sizeof(res)); break; case IORESOURCE_MEM: diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c index 8532c3e2aea7..1626dc66e763 100644 --- a/drivers/watchdog/s3c2410_wdt.c +++ b/drivers/watchdog/s3c2410_wdt.c @@ -161,7 +161,7 @@ static const struct s3c2410_wdt_variant drv_data_exynos5420 = { static const struct s3c2410_wdt_variant drv_data_exynos7 = { .disable_reg = EXYNOS5_WDT_DISABLE_REG_OFFSET, .mask_reset_reg = EXYNOS5_WDT_MASK_RESET_REG_OFFSET, - .mask_bit = 0, + .mask_bit = 23, .rst_stat_reg = EXYNOS5_RST_STAT_REG_OFFSET, .rst_stat_bit = 23, /* A57 WDTRESET */ .quirks = QUIRK_HAS_PMU_CONFIG | QUIRK_HAS_RST_STAT, |