mirror of
https://github.com/edk2-porting/linux-next.git
synced 2025-01-04 03:33:58 +08:00
7a53df2c08
When omapfb does ovl->get_overlay_info, ovl->set_overlay_info, the set function may fail even if the info has not been changed. This is because omapdss doesn't initialize the info, but expect the caller to set valid values. Normally that is the case, but there is at least one corner case: if omapfb has not allocated memory for the overlay yet, and the user uses ioctl to disable the overlay to make sure it's disabled. In this case get_overlay_info returns invalid data, but the user is only interested in setting the overlay to disabled, not configuring it, and set_overlay_info fails. The issue is made possible by the omapfb's setup_plane ioctl, which groups overlay configuration and overlay enable/disable bit into the same struct. Thus, when you are disabling an overlay, you are also configuring it. This is a bit counter intuitive, so I think it's better to initialize the info to some valid values. The fields requiring initialization are color_mode and rotation_type, and also we need to remove the check for (paddr == 0), as paddr is 0 for unallocated overlay (but it's still fine to disable the overlay). Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com> |
||
|---|---|---|
| .. | ||
| apply.c | ||
| core.c | ||
| dispc_coefs.c | ||
| dispc-compat.c | ||
| dispc-compat.h | ||
| dispc.c | ||
| dispc.h | ||
| display-sysfs.c | ||
| display.c | ||
| dpi.c | ||
| dsi.c | ||
| dss_features.c | ||
| dss_features.h | ||
| dss.c | ||
| dss.h | ||
| hdmi4_core.c | ||
| hdmi4_core.h | ||
| hdmi4.c | ||
| hdmi_common.c | ||
| hdmi_phy.c | ||
| hdmi_pll.c | ||
| hdmi_wp.c | ||
| hdmi.h | ||
| Kconfig | ||
| Makefile | ||
| manager-sysfs.c | ||
| manager.c | ||
| output.c | ||
| overlay-sysfs.c | ||
| overlay.c | ||
| rfbi.c | ||
| sdi.c | ||
| venc_panel.c | ||
| venc.c | ||