diff options
| author | Dave Airlie <airlied@redhat.com> | 2019-04-05 11:21:47 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2019-04-05 11:38:02 +1000 |
| commit | 14d2bd53a47a7e1cb3e03d00a6b952734cf90f3f (patch) | |
| tree | 616e11aacdf96d495bf6ef9c8163fb83cd5b712b | |
| parent | 5ebffda257731a11cf1db6c6142c82d5b30aec35 (diff) | |
| parent | f15a3ea80391e83f32d4a23f83b1f02415cd5889 (diff) | |
| download | linux-14d2bd53a47a7e1cb3e03d00a6b952734cf90f3f.tar.bz2 | |
Merge tag 'drm-misc-next-2019-04-04' of git://anongit.freedesktop.org/drm/drm-misc into drm-next
drm-misc-next for 5.2:
UAPI Changes:
-syncobj: Add TIMELINE_WAIT|QUERY|TRANSFER|TIMELINE_SIGNAL ioctls (Chunming)
-Clarify that 1.0 can be represented by drm_color_lut (Daniel)
Cross-subsystem Changes:
-dt-bindings: Add binding for rk3066 hdmi (Johan)
-dt-bindings: Add binding for Feiyang FY07024DI26A30-D panel (Jagan)
-dt-bindings: Add Rocktech vendor prefix and jh057n00900 panel bindings (Guido)
-MAINTAINERS: Add lima and ASPEED entries (Joel & Qiang)
Core Changes:
-memory: use dma_alloc_coherent when mem encryption is active (Christian)
-dma_buf: add support for a dma_fence chain (Christian)
-shmem_gem: fix off-by-one bug in new shmem gem helpers (Dan)
Driver Changes:
-rockchip: Add support for rk3066 hdmi (Johan)
-ASPEED: Add driver supporting ASPEED BMC display controller to drm (Joel)
-lima: Add driver supporting Arm Mali4xx gpus to drm (Qiang)
-vc4/v3d: Various cleanups and improved error handling (Eric)
-panel: Add support for Feiyang FY07024DI26A30-D MIPI-DSI panel (Jagan)
-panel: Add support for Rocktech jh057n00900 MIPI-DSI panel (Guido)
Cc: Johan Jonker <jbx6244@gmail.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Chunming Zhou <david1.zhou@amd.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Eric Anholt <eric@anholt.net>
Cc: Qiang Yu <yuq825@gmail.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Jagan Teki <jagan@amarulasolutions.com>
Cc: Guido Günther <agx@sigxcpu.org>
Cc: Joel Stanley <joel@jms.id.au>
[airlied: fixed XA limit build breakage, Rodrigo also submitted the same patch, but
I squashed it in the merge.]
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Sean Paul <sean@poorly.run>
Link: https://patchwork.freedesktop.org/patch/msgid/20190404201016.GA139524@art_vandelay
114 files changed, 8561 insertions, 742 deletions
diff --git a/Documentation/devicetree/bindings/display/panel/feiyang,fy07024di26a30d.txt b/Documentation/devicetree/bindings/display/panel/feiyang,fy07024di26a30d.txt new file mode 100644 index 000000000000..82caa7b65ae8 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/feiyang,fy07024di26a30d.txt @@ -0,0 +1,20 @@ +Feiyang FY07024DI26A30-D 7" MIPI-DSI LCD Panel + +Required properties: +- compatible: must be "feiyang,fy07024di26a30d" +- reg: DSI virtual channel used by that screen +- avdd-supply: analog regulator dc1 switch +- dvdd-supply: 3v3 digital regulator +- reset-gpios: a GPIO phandle for the reset pin + +Optional properties: +- backlight: phandle for the backlight control. + +panel@0 { + compatible = "feiyang,fy07024di26a30d"; + reg = <0>; + avdd-supply = <®_dc1sw>; + dvdd-supply = <®_dldo2>; + reset-gpios = <&pio 3 24 GPIO_ACTIVE_HIGH>; /* LCD-RST: PD24 */ + backlight = <&backlight>; +}; diff --git a/Documentation/devicetree/bindings/display/panel/innolux,p079zca.txt b/Documentation/devicetree/bindings/display/panel/innolux,p079zca.txt index d0f55161579a..3ab8c7412cf6 100644 --- a/Documentation/devicetree/bindings/display/panel/innolux,p079zca.txt +++ b/Documentation/devicetree/bindings/display/panel/innolux,p079zca.txt @@ -12,7 +12,7 @@ Optional properties: Example: &mipi_dsi { - panel { + panel@0 { compatible = "innolux,p079zca"; reg = <0>; power-supply = <...>; diff --git a/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt b/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt index 595d9dfeffd3..d1cab3a8f0fb 100644 --- a/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt +++ b/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt @@ -13,7 +13,7 @@ Optional properties: Example: &mipi_dsi { - panel { + panel@0 { compatible = "innolux,p079zca"; reg = <0>; avdd-supply = <...>; diff --git a/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt b/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt index 164a5fa236da..cfefff688614 100644 --- a/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt +++ b/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt @@ -12,7 +12,7 @@ Optional properties: Example: &mipi_dsi { - panel { + panel@0 { compatible = "kingdisplay,kd097d04"; reg = <0>; power-supply = <...>; diff --git a/Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.txt b/Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.txt new file mode 100644 index 000000000000..1b5763200cf6 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.txt @@ -0,0 +1,18 @@ +Rocktech jh057n00900 5.5" 720x1440 TFT LCD panel + +Required properties: +- compatible: should be "rocktech,jh057n00900" +- reg: DSI virtual channel of the peripheral +- reset-gpios: panel reset gpio +- backlight: phandle of the backlight device attached to the panel + +Example: + + &mipi_dsi { + panel@0 { + compatible = "rocktech,jh057n00900"; + reg = <0>; + backlight = <&backlight>; + reset-gpios = <&gpio3 13 GPIO_ACTIVE_LOW>; + }; + }; diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3066-hdmi.txt b/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3066-hdmi.txt new file mode 100644 index 000000000000..d1ad31bca8d9 --- /dev/null +++ b/Documentation/devicetree/bindings/display/rockchip/rockchip,rk3066-hdmi.txt @@ -0,0 +1,72 @@ +Rockchip specific extensions for rk3066 HDMI +============================================ + +Required properties: +- compatible: + "rockchip,rk3066-hdmi"; +- reg: + Physical base address and length of the controller's registers. +- clocks, clock-names: + Phandle to HDMI controller clock, name should be "hclk". +- interrupts: + HDMI interrupt number. +- power-domains: + Phandle to the RK3066_PD_VIO power domain. +- rockchip,grf: + This soc uses GRF regs to switch the HDMI TX input between vop0 and vop1. +- ports: + Contains one port node with two endpoints, numbered 0 and 1, + connected respectively to vop0 and vop1. + Contains one port node with one endpoint + connected to a hdmi-connector node. +- pinctrl-0, pinctrl-name: + Switch the iomux for the HPD/I2C pins to HDMI function. + +Example: + hdmi: hdmi@10116000 { + compatible = "rockchip,rk3066-hdmi"; + reg = <0x10116000 0x2000>; + interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&cru HCLK_HDMI>; + clock-names = "hclk"; + power-domains = <&power RK3066_PD_VIO>; + rockchip,grf = <&grf>; + pinctrl-names = "default"; + pinctrl-0 = <&hdmii2c_xfer>, <&hdmi_hpd>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + hdmi_in: port@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + hdmi_in_vop0: endpoint@0 { + reg = <0>; + remote-endpoint = <&vop0_out_hdmi>; + }; + hdmi_in_vop1: endpoint@1 { + reg = <1>; + remote-endpoint = <&vop1_out_hdmi>; + }; + }; + hdmi_out: port@1 { + reg = <1>; + hdmi_out_con: endpoint { + remote-endpoint = <&hdmi_con_in>; + }; + }; + }; + }; + +&pinctrl { + hdmi { + hdmi_hpd: hdmi-hpd { + rockchip,pins = <0 RK_PA0 1 &pcfg_pull_default>; + }; + hdmii2c_xfer: hdmii2c-xfer { + rockchip,pins = <0 RK_PA1 1 &pcfg_pull_none>, + <0 RK_PA2 1 &pcfg_pull_none>; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/gpu/aspeed-gfx.txt b/Documentation/devicetree/bindings/gpu/aspeed-gfx.txt new file mode 100644 index 000000000000..958bdf962339 --- /dev/null +++ b/Documentation/devicetree/bindings/gpu/aspeed-gfx.txt @@ -0,0 +1,41 @@ +Device tree configuration for the GFX display device on the ASPEED SoCs + +Required properties: + - compatible + * Must be one of the following: + + aspeed,ast2500-gfx + + aspeed,ast2400-gfx + * In addition, the ASPEED pinctrl bindings require the 'syscon' property to + be present + + - reg: Physical base address and length of the GFX registers + + - interrupts: interrupt number for the GFX device + + - clocks: clock number used to generate the pixel clock + + - resets: reset line that must be released to use the GFX device + + - memory-region: + Phandle to a memory region to allocate from, as defined in + Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt + + +Example: + +gfx: display@1e6e6000 { + compatible = "aspeed,ast2500-gfx", "syscon"; + reg = <0x1e6e6000 0x1000>; + reg-io-width = <4>; + clocks = <&syscon ASPEED_CLK_GATE_D1CLK>; + resets = <&syscon ASPEED_RESET_CRT1>; + interrupts = <0x19>; + memory-region = <&gfx_memory>; +}; + +gfx_memory: framebuffer { + size = <0x01000000>; + alignment = <0x01000000>; + compatible = "shared-dma-pool"; + reusable; +}; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 5e6ea1f991d8..9506140167d6 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -345,6 +345,7 @@ ricoh Ricoh Co. Ltd. rikomagic Rikomagic Tech Corp. Ltd riscv RISC-V Foundation rockchip Fuzhou Rockchip Electronics Co., Ltd +rocktech ROCKTECH DISPLAYS LIMITED rohm ROHM Semiconductor Co., Ltd ronbo Ronbo Electronics roofull Shenzhen Roofull Technology Co, Ltd diff --git a/MAINTAINERS b/MAINTAINERS index e6d476bf9e78..4b69b6b48b3b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4894,6 +4894,14 @@ M: Dave Airlie <airlied@redhat.com> S: Odd Fixes F: drivers/gpu/drm/ast/ +DRM DRIVER FOR ASPEED BMC GFX +M: Joel Stanley <joel@jms.id.au> +L: linux-aspeed@lists.ozlabs.org +T: git git://anongit.freedesktop.org/drm/drm-misc +S: Supported +F: drivers/gpu/drm/aspeed/ +F: Documentation/devicetree/bindings/gpu/aspeed-gfx.txt + DRM DRIVER FOR BOCHS VIRTUAL GPU M: Gerd Hoffmann <kraxel@redhat.com> L: virtualization@lists.linux-foundation.org @@ -4907,6 +4915,12 @@ T: git git://anongit.freedesktop.org/drm/drm-misc S: Maintained F: drivers/gpu/drm/tve200/ +DRM DRIVER FOR FEIYANG FY07024DI26A30-D MIPI-DSI LCD PANELS +M: Jagan Teki <jagan@amarulasolutions.com> +S: Maintained +F: drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c +F: Documentation/devicetree/bindings/display/panel/feiyang,fy07024di26a30d.txt + DRM DRIVER FOR ILITEK ILI9225 PANELS M: David Lechner <david@lechnology.com> S: Maintained @@ -4998,6 +5012,12 @@ S: Orphan / Obsolete F: drivers/gpu/drm/r128/ F: include/uapi/drm/r128_drm.h +DRM DRIVER FOR ROCKTECH JH057N00900 PANELS +M: Guido Günther <agx@sigxcpu.org> +S: Maintained +F: drivers/gpu/drm/panel/panel-rocktech-jh057n00900.c +F: Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.txt + DRM DRIVER FOR SAVAGE VIDEO CARDS S: Orphan / Obsolete F: drivers/gpu/drm/savage/ @@ -5186,6 +5206,15 @@ S: Maintained F: drivers/gpu/drm/hisilicon/ F: Documentation/devicetree/bindings/display/hisilicon/ +DRM DRIVERS FOR LIMA +M: Qiang Yu <yuq825@gmail.com> +L: dri-devel@lists.freedesktop.org +L: lima@lists.freedesktop.org +S: Maintained +F: drivers/gpu/drm/lima/ +F: include/uapi/drm/lima_drm.h +T: git git://anongit.freedesktop.org/drm/drm-misc + DRM DRIVERS FOR MEDIATEK M: CK Hu <ck.hu@mediatek.com> M: Philipp Zabel <p.zabel@pengutronix.de> diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 0913a6ccab5a..1f006e083eb9 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -1,4 +1,5 @@ -obj-y := dma-buf.o dma-fence.o dma-fence-array.o reservation.o seqno-fence.o +obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \ + reservation.o seqno-fence.o obj-$(CONFIG_SYNC_FILE) += sync_file.o obj-$(CONFIG_SW_SYNC) += sw_sync.o sync_debug.o obj-$(CONFIG_UDMABUF) += udmabuf.o diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c new file mode 100644 index 000000000000..c729f98a7bd3 --- /dev/null +++ b/drivers/dma-buf/dma-fence-chain.c @@ -0,0 +1,241 @@ +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2018 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + * + * 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. + * + * 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/dma-fence-chain.h> + +static bool dma_fence_chain_enable_signaling(struct dma_fence *fence); + +/** + * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence + * @chain: chain node to get the previous node from + * + * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the + * chain node. + */ +static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain) +{ + struct dma_fence *prev; + + rcu_read_lock(); + prev = dma_fence_get_rcu_safe(&chain->prev); + rcu_read_unlock(); + return prev; +} + +/** + * dma_fence_chain_walk - chain walking function + * @fence: current chain node + * + * Walk the chain to the next node. Returns the next fence or NULL if we are at + * the end of the chain. Garbage collects chain nodes which are already + * signaled. + */ +struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence) +{ + struct dma_fence_chain *chain, *prev_chain; + struct dma_fence *prev, *replacement, *tmp; + + chain = to_dma_fence_chain(fence); + if (!chain) { + dma_fence_put(fence); + return NULL; + } + + while ((prev = dma_fence_chain_get_prev(chain))) { + + prev_chain = to_dma_fence_chain(prev); + if (prev_chain) { + if (!dma_fence_is_signaled(prev_chain->fence)) + break; + + replacement = dma_fence_chain_get_prev(prev_chain); + } else { + if (!dma_fence_is_signaled(prev)) + break; + + replacement = NULL; + } + + tmp = cmpxchg((void **)&chain->prev, (void *)prev, (void *)replacement); + if (tmp == prev) + dma_fence_put(tmp); + else + dma_fence_put(replacement); + dma_fence_put(prev); + } + + dma_fence_put(fence); + return prev; +} +EXPORT_SYMBOL(dma_fence_chain_walk); + +/** + * dma_fence_chain_find_seqno - find fence chain node by seqno + * @pfence: pointer to the chain node where to start + * @seqno: the sequence number to search for + * + * Advance the fence pointer to the chain node which will signal this sequence + * number. If no sequence number is provided then this is a no-op. + * + * Returns EINVAL if the fence is not a chain node or the sequence number has + * not yet advanced far enough. + */ +int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno) +{ + struct dma_fence_chain *chain; + + if (!seqno) + return 0; + + chain = to_dma_fence_chain(*pfence); + if (!chain || chain->base.seqno < seqno) + return -EINVAL; + + dma_fence_chain_for_each(*pfence, &chain->base) { + if ((*pfence)->context != chain->base.context || + to_dma_fence_chain(*pfence)->prev_seqno < seqno) + break; + } + dma_fence_put(&chain->base); + + return 0; +} +EXPORT_SYMBOL(dma_fence_chain_find_seqno); + +static const char *dma_fence_chain_get_driver_name(struct dma_fence *fence) +{ + return "dma_fence_chain"; +} + +static const char *dma_fence_chain_get_timeline_name(struct dma_fence *fence) +{ + return "unbound"; +} + +static void dma_fence_chain_irq_work(struct irq_work *work) +{ + struct dma_fence_chain *chain; + + chain = container_of(work, typeof(*chain), work); + + /* Try to rearm the callback */ + if (!dma_fence_chain_enable_signaling(&chain->base)) + /* Ok, we are done. No more unsignaled fences left */ + dma_fence_signal(&chain->base); + dma_fence_put(&chain->base); +} + +static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb) +{ + struct dma_fence_chain *chain; + + chain = container_of(cb, typeof(*chain), cb); + irq_work_queue(&chain->work); + dma_fence_put(f); +} + +static bool dma_fence_chain_enable_signaling(struct dma_fence *fence) +{ + struct dma_fence_chain *head = to_dma_fence_chain(fence); + + dma_fence_get(&head->base); + dma_fence_chain_for_each(fence, &head->base) { + struct dma_fence_chain *chain = to_dma_fence_chain(fence); + struct dma_fence *f = chain ? chain->fence : fence; + + dma_fence_get(f); + if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) { + dma_fence_put(fence); + return true; + } + dma_fence_put(f); + } + dma_fence_put(&head->base); + return false; +} + +static bool dma_fence_chain_signaled(struct dma_fence *fence) +{ + dma_fence_chain_for_each(fence, fence) { + struct dma_fence_chain *chain = to_dma_fence_chain(fence); + struct dma_fence *f = chain ? chain->fence : fence; + + if (!dma_fence_is_signaled(f)) { + dma_fence_put(fence); + return false; + } + } + + return true; +} + +static void dma_fence_chain_release(struct dma_fence *fence) +{ + struct dma_fence_chain *chain = to_dma_fence_chain(fence); + + dma_fence_put(rcu_dereference_protected(chain->prev, true)); + dma_fence_put(chain->fence); + dma_fence_free(fence); +} + +const struct dma_fence_ops dma_fence_chain_ops = { + .get_driver_name = dma_fence_chain_get_driver_name, + .get_timeline_name = dma_fence_chain_get_timeline_name, + .enable_signaling = dma_fence_chain_enable_signaling, + .signaled = dma_fence_chain_signaled, + .release = dma_fence_chain_release, +}; +EXPORT_SYMBOL(dma_fence_chain_ops); + +/** + * dma_fence_chain_init - initialize a fence chain + * @chain: the chain node to initialize + * @prev: the previous fence + * @fence: the current fence + * + * Initialize a new chain node and either start a new chain or add the node to + * the existing chain of the previous fence. + */ +void dma_fence_chain_init(struct dma_fence_chain *chain, + struct dma_fence *prev, + struct dma_fence *fence, + uint64_t seqno) +{ + struct dma_fence_chain *prev_chain = to_dma_fence_chain(prev); + uint64_t context; + + spin_lock_init(&chain->lock); + rcu_assign_pointer(chain->prev, prev); + chain->fence = fence; + chain->prev_seqno = 0; + init_irq_work(&chain->work, dma_fence_chain_irq_work); + + /* Try to reuse the context of the previous chain node. */ + if (prev_chain && __dma_fence_is_later(seqno, prev->seqno)) { + context = prev->context; + chain->prev_seqno = prev->seqno; + } else { + context = dma_fence_context_alloc(1); + /* Make sure that we always have a valid sequence number. */ + if (prev_chain) + seqno = max(prev->seqno, seqno); + } + + dma_fence_init(&chain->base, &dma_fence_chain_ops, + &chain->lock, context, seqno); +} +EXPORT_SYMBOL(dma_fence_chain_init); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 82bb221ec94e..bcbc4234893a 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -335,6 +335,10 @@ source "drivers/gpu/drm/xen/Kconfig" source "drivers/gpu/drm/vboxvideo/Kconfig" +source "drivers/gpu/drm/lima/Kconfig" + +source "drivers/gpu/drm/aspeed/Kconfig" + # Keep legacy drivers last menuconfig DRM_LEGACY diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 0baf148e3687..d97c0a3a8cfc 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -110,3 +110,5 @@ obj-$(CONFIG_DRM_PL111) += pl111/ obj-$(CONFIG_DRM_TVE200) += tve200/ obj-$(CONFIG_DRM_XEN) += xen/ obj-$(CONFIG_DRM_VBOXVIDEO) += vboxvideo/ +obj-$(CONFIG_DRM_LIMA) += lima/ +obj-$(CONFIG_DRM_ASPEED_GFX) += aspeed/ diff --git a/drivers/gpu/drm/aspeed/Kconfig b/drivers/gpu/drm/aspeed/Kconfig new file mode 100644 index 000000000000..42b74d18a41b --- /dev/null +++ b/drivers/gpu/drm/aspeed/Kconfig @@ -0,0 +1,14 @@ +config DRM_ASPEED_GFX + tristate "ASPEED BMC Display Controller" + depends on DRM && OF + select DRM_KMS_HELPER + select DRM_KMS_CMA_HELPER + select DRM_PANEL + select DMA_CMA + select CMA + select MFD_SYSCON + help + Chose this option if you have an ASPEED AST2500 SOC Display + Controller (aka GFX). + + If M is selected this module will be called aspeed_gfx. diff --git a/drivers/gpu/drm/aspeed/Makefile b/drivers/gpu/drm/aspeed/Makefile new file mode 100644 index 000000000000..6e194cd790d8 --- /dev/null +++ b/drivers/gpu/drm/aspeed/Makefile @@ -0,0 +1,3 @@ +aspeed_gfx-y := aspeed_gfx_drv.o aspeed_gfx_crtc.o aspeed_gfx_out.o + +obj-$(CONFIG_DRM_ASPEED_GFX) += aspeed_gfx.o diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx.h b/drivers/gpu/drm/aspeed/aspeed_gfx.h new file mode 100644 index 000000000000..a10358bb61ec --- /dev/null +++ b/drivers/gpu/drm/aspeed/aspeed_gfx.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright 2018 IBM Corporation */ + +#include <drm/drm_device.h> +#include <drm/drm_simple_kms_helper.h> + +struct aspeed_gfx { + void __iomem *base; + struct clk *clk; + struct reset_control *rst; + struct regmap *scu; + + struct drm_simple_display_pipe pipe; + struct drm_connector connector; + struct drm_fbdev_cma *fbdev; +}; + +int aspeed_gfx_create_pipe(struct drm_device *drm); +int aspeed_gfx_create_output(struct drm_device *drm); + +#define CRT_CTRL1 0x60 /* CRT Control I */ +#define CRT_CTRL2 0x64 /* CRT Control II */ +#define CRT_STATUS 0x68 /* CRT Status */ +#define CRT_MISC 0x6c /* CRT Misc Setting */ +#define CRT_HORIZ0 0x70 /* CRT Horizontal Total & Display Enable End */ +#define CRT_HORIZ1 0x74 /* CRT Horizontal Retrace Start & End */ +#define CRT_VERT0 0x78 /* CRT Vertical Total & Display Enable End */ +#define CRT_VERT1 0x7C /* CRT Vertical Retrace Start & End */ +#define CRT_ADDR 0x80 /* CRT Display Starting Address */ +#define CRT_OFFSET 0x84 /* CRT Display Offset & Terminal Count */ +#define CRT_THROD 0x88 /* CRT Threshold */ +#define CRT_XSCALE 0x8C /* CRT Scaling-Up Factor */ +#define CRT_CURSOR0 0x90 /* CRT Hardware Cursor X & Y Offset */ +#define CRT_CURSOR1 0x94 /* CRT Hardware Cursor X & Y Position */ +#define CRT_CURSOR2 0x98 /* CRT Hardware Cursor Pattern Address */ +#define CRT_9C 0x9C +#define CRT_OSD_H 0xA0 /* CRT OSD Horizontal Start/End */ +#define CRT_OSD_V 0xA4 /* CRT OSD Vertical Start/End */ +#define CRT_OSD_ADDR 0xA8 /* CRT OSD Pattern Address */ +#define CRT_OSD_DISP 0xAC /* CRT OSD Offset */ +#define CRT_OSD_THRESH 0xB0 /* CRT OSD Threshold & Alpha */ +#define CRT_B4 0xB4 +#define CRT_STS_V 0xB8 /* CRT Status V */ +#define CRT_SCRATCH 0xBC /* Scratchpad */ +#define CRT_BB0_ADDR 0xD0 /* CRT Display BB0 Starting Address */ +#define CRT_BB1_ADDR 0xD4 /* CRT Display BB1 Starting Address */ +#define CRT_BB_COUNT 0xD8 /* CRT Display BB Terminal Count */ +#define OSD_COLOR1 0xE0 /* OSD Color Palette Index 1 & 0 */ +#define OSD_COLOR2 0xE4 /* OSD Color Palette Index 3 & 2 */ +#define OSD_COLOR3 0xE8 /* OSD Color Palette Index 5 & 4 */ +#define OSD_COLOR4 0xEC /* OSD Color Palette Index 7 & 6 */ +#define OSD_COLOR5 0xF0 /* OSD Color Palette Index 9 & 8 */ +#define OSD_COLOR6 0xF4 /* OSD Color Palette Index 11 & 10 */ +#define OSD_COLOR7 0xF8 /* OSD Color Palette Index 13 & 12 */ +#define OSD_COLOR8 0xFC /* OSD Color Palette Index 15 & 14 */ + +/* CTRL1 */ +#define CRT_CTRL_EN BIT(0) +#define CRT_CTRL_HW_CURSOR_EN BIT(1) +#define CRT_CTRL_OSD_EN BIT(2) +#define CRT_CTRL_INTERLACED BIT(3) +#define CRT_CTRL_COLOR_RGB565 (0 << 7) +#define CRT_CTRL_COLOR_YUV444 (1 << 7) +#define CRT_CTRL_COLOR_XRGB8888 (2 << 7) +#define CRT_CTRL_COLOR_RGB888 (3 << 7) +#define CRT_CTRL_COLOR_YUV444_2RGB (5 << 7) +#define CRT_CTRL_COLOR_YUV422 (7 << 7) +#define CRT_CTRL_COLOR_MASK GENMASK(9, 7) +#define CRT_CTRL_HSYNC_NEGATIVE BIT(16) +#define CRT_CTRL_VSYNC_NEGATIVE BIT(17) +#define CRT_CTRL_VERTICAL_INTR_EN BIT(30) +#define CRT_CTRL_VERTICAL_INTR_STS BIT(31) + +/* CTRL2 */ +#define CRT_CTRL_DAC_EN BIT(0) +#define CRT_CTRL_VBLANK_LINE(x) (((x) << 20) & CRT_CTRL_VBLANK_LINE_MASK) +#define CRT_CTRL_VBLANK_LINE_MASK GENMASK(20, 31) + +/* CRT_HORIZ0 */ +#define CRT_H_TOTAL(x) (x) +#define CRT_H_DE(x) ((x) << 16) + +/* CRT_HORIZ1 */ +#define CRT_H_RS_START(x) (x) +#define CRT_H_RS_END(x) ((x) << 16) + +/* CRT_VIRT0 */ +#define CRT_V_TOTAL(x) (x) +#define CRT_V_DE(x) ((x) << 16) + +/* CRT_VIRT1 */ +#define CRT_V_RS_START(x) (x) +#define CRT_V_RS_END(x) ((x) << 16) + +/* CRT_OFFSET */ +#define CRT_DISP_OFFSET(x) (x) +#define CRT_TERM_COUNT(x) ((x) << 16) + +/* CRT_THROD */ +#define CRT_THROD_LOW(x) (x) +#define CRT_THROD_HIGH(x) ((x) << 8) + +/* Default Threshold Seting */ +#define G5_CRT_THROD_VAL (CRT_THROD_LOW(0x24) | CRT_THROD_HIGH(0x3C)) diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c b/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c new file mode 100644 index 000000000000..15db9e426ec4 --- /dev/null +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c @@ -0,0 +1,241 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright 2018 IBM Corporation + +#include <linux/clk.h> +#include <linux/reset.h> +#include <linux/regmap.h> + +#include <drm/drm_crtc_helper.h> +#include <drm/drm_device.h> +#include <drm/drm_fb_cma_helper.h> +#include <drm/drm_fourcc.h> +#include <drm/drm_gem_cma_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_panel.h> +#include <drm/drm_simple_kms_helper.h> +#include <drm/drm_vblank.h> + +#include "aspeed_gfx.h" + +static struct aspeed_gfx * +drm_pipe_to_aspeed_gfx(struct drm_simple_display_pipe *pipe) +{ + return container_of(pipe, struct aspeed_gfx, pipe); +} + +static int aspeed_gfx_set_pixel_fmt(struct aspeed_gfx *priv, u32 *bpp) +{ + struct drm_crtc *crtc = &priv->pipe.crtc; + struct drm_device *drm = crtc->dev; + const u32 format = crtc->primary->state->fb->format->format; + u32 ctrl1; + + ctrl1 = readl(priv->base + CRT_CTRL1); + ctrl1 &= ~CRT_CTRL_COLOR_MASK; + + switch (format) { + case DRM_FORMAT_RGB565: + dev_dbg(drm->dev, "Setting up RGB565 mode\n"); + ctrl1 |= CRT_CTRL_COLOR_RGB565; + *bpp = 16; + break; + case DRM_FORMAT_XRGB8888: + dev_dbg(drm->dev, "Setting up XRGB8888 mode\n"); + ctrl1 |= CRT_CTRL_COLOR_XRGB8888; + *bpp = 32; + break; + default: + dev_err(drm->dev, "Unhandled pixel format %08x\n", format); + return -EINVAL; + } + + writel(ctrl1, priv->base + CRT_CTRL1); + + return 0; +} + +static void aspeed_gfx_enable_controller(struct aspeed_gfx *priv) +{ + u32 ctrl1 = readl(priv->base + CRT_CTRL1); + u32 ctrl2 = readl(priv->base + CRT_CTRL2); + + /* SCU2C: set DAC source for display output to Graphics CRT (GFX) */ + regmap_update_bits(priv->scu, 0x2c, BIT(16), BIT(16)); + + writel(ctrl1 | CRT_CTRL_EN, priv->base + CRT_CTRL1); + writel(ctrl2 | CRT_CTRL_DAC_EN, priv->base + CRT_CTRL2); +} + +static void aspeed_gfx_disable_controller(struct aspeed_gfx *priv) +{ + u32 ctrl1 = readl(priv->base + CRT_CTRL1); + u32 ctrl2 = readl(priv->base + CRT_CTRL2); + + writel(ctrl1 & ~CRT_CTRL_EN, priv->base + CRT_CTRL1); + writel(ctrl2 & ~CRT_CTRL_DAC_EN, priv->base + CRT_CTRL2); + + regmap_update_bits(priv->scu, 0x2c, BIT(16), 0); +} + +static void aspeed_gfx_crtc_mode_set_nofb(struct aspeed_gfx *priv) +{ + struct drm_display_mode *m = &priv->pipe.crtc.state->adjusted_mode; + u32 ctrl1, d_offset, t_count, bpp; + int err; + + err = aspeed_gfx_set_pixel_fmt(priv, &bpp); + if (err) + return; + +#if 0 + /* TODO: we have only been able to test with the 40MHz USB clock. The + * clock is fixed, so we cannot adjust it here. */ + clk_set_rate(priv->pixel_clk, m->crtc_clock * 1000); +#endif + + ctrl1 = readl(priv->base + CRT_CTRL1); + ctrl1 &= ~(CRT_CTRL_INTERLACED | + CRT_CTRL_HSYNC_NEGATIVE | + CRT_CTRL_VSYNC_NEGATIVE); + + if (m->flags & DRM_MODE_FLAG_INTERLACE) + ctrl1 |= CRT_CTRL_INTERLACED; + + if (!(m->flags & DRM_MODE_FLAG_PHSYNC)) + ctrl1 |= CRT_CTRL_HSYNC_NEGATIVE; + + if (!(m->flags & DRM_MODE_FLAG_PVSYNC)) + ctrl1 |= CRT_CTRL_VSYNC_NEGATIVE; + + writel(ctrl1, priv->base + CRT_CTRL1); + + /* Horizontal timing */ + writel(CRT_H_TOTAL(m->htotal - 1) | CRT_H_DE(m->hdisplay - 1), + priv->base + CRT_HORIZ0); + writel(CRT_H_RS_START(m->hsync_start - 1) | CRT_H_RS_END(m->hsync_end), + priv->base + CRT_HORIZ1); + + + /* Vertical timing */ + writel(CRT_V_TOTAL(m->vtotal - 1) | CRT_V_DE(m->vdisplay - 1), + priv->base + CRT_VERT0); + writel(CRT_V_RS_START(m->vsync_start) | CRT_V_RS_END(m->vsync_end), + priv->base + CRT_VERT1); + + /* + * Display Offset: address difference between consecutive scan lines + * Terminal Count: memory size of one scan line + */ + d_offset = m->hdisplay * bpp / 8; + t_count = (m->hdisplay * bpp + 127) / 128; + writel(CRT_DISP_OFFSET(d_offset) | CRT_TERM_COUNT(t_count), + priv->base + CRT_OFFSET); + + /* + * Threshold: FIFO thresholds of refill and stop (16 byte chunks + * per line, rounded up) + */ + writel(G5_CRT_THROD_VAL, priv->base + CRT_THROD); +} + +static void aspeed_gfx_pipe_enable(struct drm_simple_display_pipe *pipe, + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) +{ + struct aspeed_gfx *priv = drm_pipe_to_aspeed_gfx(pipe); + struct drm_crtc *crtc = &pipe->crtc; + + aspeed_gfx_crtc_mode_set_nofb(priv); + aspeed_gfx_enable_controller(priv); + drm_crtc_vblank_on(crtc); +} + +static void aspeed_gfx_pipe_disable(struct drm_simple_display_pipe *pipe) +{ + struct aspeed_gfx *priv = drm_pipe_to_aspeed_gfx(pipe); + struct drm_crtc *crtc = &pipe->crtc; + + drm_crtc_vblank_off(crtc); + aspeed_gfx_disable_controller(priv); +} + +static void aspeed_gfx_pipe_update(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *plane_state) +{ + struct aspeed_gfx *priv = drm_pipe_to_aspeed_gfx(pipe); + struct drm_crtc *crtc = &pipe->crtc; + struct drm_framebuffer *fb = pipe->plane.state->fb; + struct drm_pending_vblank_event *event; + struct drm_gem_cma_object *gem; + + spin_lock_irq(&crtc->dev->event_lock); + event = crtc->state->event; + if (event) { + crtc->state->event = NULL; + + if (drm_crtc_vblank_get(crtc) == 0) + drm_crtc_arm_vblank_event(crtc, event); + else + drm_crtc_send_vblank_event(crtc, event); + } + spin_unlock_irq(&crtc->dev->event_lock); + + if (!fb) + return; + + gem = drm_fb_cma_get_gem_obj(fb, 0); + if (!gem) + return; + writel(gem->paddr, priv->base + CRT_ADDR); +} + +static int aspeed_gfx_enable_vblank(struct drm_simple_display_pipe *pipe) +{ + struct aspeed_gfx *priv = drm_pipe_to_aspeed_gfx(pipe); + u32 reg = readl(priv->base + CRT_CTRL1); + + /* Clear pending VBLANK IRQ */ + writel(reg | CRT_CTRL_VERTICAL_INTR_STS, priv->base + CRT_CTRL1); + + reg |= CRT_CTRL_VERTICAL_INTR_EN; + writel(reg, priv->base + CRT_CTRL1); + + return 0; +} + +static void aspeed_gfx_disable_vblank(struct drm_simple_display_pipe *pipe) +{ + struct aspeed_gfx *priv = drm_pipe_to_aspeed_gfx(pipe); + u32 reg = readl(priv->base + CRT_CTRL1); + + reg &= ~CRT_CTRL_VERTICAL_INTR_EN; + writel(reg, priv->base + CRT_CTRL1); + + /* Clear pending VBLANK IRQ */ + writel(reg | CRT_CTRL_VERTICAL_INTR_STS, priv->base + CRT_CTRL1); +} + +static struct drm_simple_display_pipe_funcs aspeed_gfx_funcs = { + .enable = aspeed_gfx_pipe_enable, + .disable = aspeed_gfx_pipe_disable, + .update = aspeed_gfx_pipe_update, + .prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb, + .enable_vblank = aspeed_gfx_enable_vblank, + .disable_vblank = aspeed_gfx_disable_vblank, +}; + +static const uint32_t aspeed_gfx_formats[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_RGB565, +}; + +int aspeed_gfx_create_pipe(struct drm_device *drm) +{ + struct aspeed_gfx *priv = drm->dev_private; + + return drm_simple_display_pipe_init(drm, &priv->pipe, &aspeed_gfx_funcs, + aspeed_gfx_formats, + ARRAY_SIZE(aspeed_gfx_formats), + NULL, + &priv->connector); +} diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c new file mode 100644 index 000000000000..eeb22eccd1fc --- /dev/null +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright 2018 IBM Corporation + +#include <linux/clk.h> +#include <linux/dma-mapping.h> +#include <linux/irq.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_reserved_mem.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_device.h> +#include <drm/drm_fb_cma_helper.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_gem_cma_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_simple_kms_helper.h> +#include <drm/drm_vblank.h> +#include <drm/drm_drv.h> + +#include "aspeed_gfx.h" + +/** + * DOC: ASPEED GFX Driver + * + * This driver is for the ASPEED BMC SoC's 'GFX' display hardware, also called + * the 'SOC Display Controller' in the datasheet. This driver runs on the ARM + * based BMC systems, unlike the ast driver which runs on a host CPU and is for + * a PCIe graphics device. + * + * The AST2500 supports a total of 3 output paths: + * + * 1. VGA output, the output target can choose either or both to the DAC + * or DVO interface. + * + * 2. Graphics CRT output, the output target can choose either or both to + * the DAC or DVO interface. + * + * 3. Video input from DVO, the video input can be used for video engine + * capture or DAC display output. + * + * Output options are selected in SCU2C. + * + * The "VGA mode" device is the PCI attached controller. The "Graphics CRT" + * is the ARM's internal display controller. + * + * The driver only supports a simple configuration consisting of a 40MHz + * pixel clock, fixed by hardware limitations, and the VGA output path. + * + * The driver was written with the 'AST2500 Software Programming Guide' v17, + * which is available under NDA from ASPEED. + */ + +static const struct drm_mode_config_funcs aspeed_gfx_mode_config_funcs = { + .fb_create = drm_gem_fb_create, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static void aspeed_gfx_setup_mode_config(struct drm_device *drm) +{ + drm_mode_config_init(drm); + + drm->mode_config.min_width = 0; + drm->mode_config.min_height = 0; + drm->mode_config.max_width = 800; + drm->mode_config.max_height = 600; + drm->mode_config.funcs = &aspeed_gfx_mode_config_funcs; +} + +static irqreturn_t aspeed_gfx_irq_handler(int irq, void *data) +{ + struct drm_device *drm = data; + struct aspeed_gfx *priv = drm->dev_private; + u32 reg; + + reg = readl(priv->base + CRT_CTRL1); + + if (reg & CRT_CTRL_VERTICAL_INTR_STS) { + drm_crtc_handle_vblank(&priv->pipe.crtc); + writel(reg, priv->base + CRT_CTRL1); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + + + +static int aspeed_gfx_load(struct drm_device *drm) +{ + struct platform_device *pdev = to_platform_device(drm->dev); + struct aspeed_gfx *priv; + struct resource *res; + int ret; + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + drm->dev_private = priv; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + priv->base = devm_ioremap_resource(drm->dev, res); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); + + priv->scu = syscon_regmap_lookup_by_compatible("aspeed,ast2500-scu"); + if (IS_ERR(priv->scu)) { + dev_err(&pdev->dev, "failed to find SCU regmap\n"); + return PTR_ERR(priv->scu); + } + + ret = of_reserved_mem_device_init(drm->dev); + if (ret) { + dev_err(&pdev->dev, + "failed to initialize reserved mem: %d\n", ret); + return ret; + } + + ret = dma_set_mask_and_coherent(drm->dev, DMA_BIT_MASK(32)); + if (ret) { + dev_err(&pdev->dev, "failed to set DMA mask: %d\n", ret); + return ret; + } + + priv->rst = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (IS_ERR(priv->rst)) { + dev_err(&pdev->dev, + "missing or invalid reset controller device tree entry"); + return PTR_ERR(priv->rst); + } + reset_control_deassert(priv->rst); + + priv->clk = devm_clk_get(drm->dev, NULL); + if (IS_ERR(priv->clk)) { + dev_err(&pdev->dev, + "missing or invalid clk device tree entry"); + return PTR_ERR(priv->clk); + } + clk_prepare_enable(priv->clk); + + /* Sanitize control registers */ + writel(0, priv->base + CRT_CTRL1); + writel(0, priv->base + CRT_CTRL2); + + aspeed_gfx_setup_mode_config(drm); + + ret = drm_vblank_init(drm, 1); + if (ret < 0) { + dev_err(drm->dev, "Failed to initialise vblank\n"); + return ret; + } + + ret = aspeed_gfx_create_output(drm); + if (ret < 0) { + dev_err(drm->dev, "Failed to create outputs\n"); + return ret; + } + + ret = aspeed_gfx_create_pipe(drm); + if (ret < 0) { + dev_err(drm->dev, "Cannot setup simple display pipe\n"); + return ret; + } + + ret = devm_request_irq(drm->dev, platform_get_irq(pdev, 0), + aspeed_gfx_irq_handler, 0, "aspeed gfx", drm); + if (ret < 0) { + dev_err(drm->dev, "Failed to install IRQ handler\n"); + return ret; + } + + drm_mode_config_reset(drm); + + drm_fbdev_generic_setup(drm, 32); + + return 0; +} + +static void aspeed_gfx_unload(struct drm_device *drm) +{ + drm_kms_helper_poll_fini(drm); + drm_mode_config_cleanup(drm); + + drm->dev_private = NULL; +} + +DEFINE_DRM_GEM_CMA_FOPS(fops); + +static struct drm_driver aspeed_gfx_driver = { + .driver_features = DRIVER_GEM | DRIVER_MODESET | + DRIVER_PRIME | DRIVER_ATOMIC, + .gem_create_object = drm_cma_gem_create_object_default_funcs, + .dumb_create = drm_gem_cma_dumb_create, + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table, + .gem_prime_mmap = drm_gem_prime_mmap, + .fops = &fops, + .name = "aspeed-gfx-drm", + .desc = "ASPEED GFX DRM", + .date = "20180319", + .major = 1, + .minor = 0, +}; + +static const struct of_device_id aspeed_gfx_match[] = { + { .compatible = "aspeed,ast2500-gfx" }, + { } +}; + +static int aspeed_gfx_probe(struct platform_device *pdev) +{ + struct drm_device *drm; + int ret; + + drm = drm_dev_alloc(&aspeed_gfx_driver, &pdev->dev); + if (IS_ERR(drm)) + return PTR_ERR(drm); + + ret = aspeed_gfx_load(drm); + if (ret) + goto err_free; + + ret = drm_dev_register(drm, 0); + if (ret) + goto err_unload; + + return 0; + +err_unload: + aspeed_gfx_unload(drm); +err_free: + drm_dev_put(drm); + + return ret; +} + +static int aspeed_gfx_remove(struct platform_device *pdev) +{ + struct drm_device *drm = platform_get_drvdata(pdev); + + drm_dev_unregister(drm); + aspeed_gfx_unload(drm); + drm_dev_put(drm); + + return 0; +} + +static struct platform_driver aspeed_gfx_platform_driver = { + .probe = aspeed_gfx_probe, + .remove = aspeed_gfx_remove, + .driver = { + .name = "aspeed_gfx", + .of_match_table = aspeed_gfx_match, + }, +}; + +module_platform_driver(aspeed_gfx_platform_driver); + +MODULE_AUTHOR("Joel Stanley <joel@jms.id.au>"); +MODULE_DESCRIPTION("ASPEED BMC DRM/KMS driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_out.c b/drivers/gpu/drm/aspeed/aspeed_gfx_out.c new file mode 100644 index 000000000000..67ee5fa10055 --- /dev/null +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_out.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright 2018 IBM Corporation + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_connector.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_probe_helper.h> + +#include "aspeed_gfx.h" + +static int aspeed_gfx_get_modes(struct drm_connector *connector) +{ + return drm_add_modes_noedid(connector, 800, 600); +} + +static const struct +drm_connector_helper_funcs aspeed_gfx_connector_helper_funcs = { + .get_modes = aspeed_gfx_get_modes, +}; + +static const struct drm_connector_funcs aspeed_gfx_connector_funcs = { + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +int aspeed_gfx_create_output(struct drm_device *drm) +{ + struct aspeed_gfx *priv = drm->dev_private; + int ret; + + priv->connector.dpms = DRM_MODE_DPMS_OFF; + priv->connector.polled = 0; + drm_connector_helper_add(&priv->connector, + &aspeed_gfx_connector_helper_funcs); + ret = drm_connector_init(drm, &priv->connector, + &aspeed_gfx_connector_funcs, + DRM_MODE_CONNECTOR_Unknown); + return ret; +} diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h index 7425d083b944..049d058571d4 100644 --- a/drivers/gpu/drm/bochs/bochs.h +++ b/drivers/gpu/drm/bochs/bochs.h @@ -73,7 +73,6 @@ struct bochs_device { struct drm_crtc crtc; struct drm_encoder encoder; struct drm_connector connector; - bool mode_config_initialized; /* ttm */ struct { diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c index 9e7cd6b34106..485f9cf05e8b 100644 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ b/drivers/gpu/drm/bochs/bochs_kms.c @@ -267,7 +267,6 @@ const struct drm_mode_config_funcs bochs_mode_funcs = { int bochs_kms_init(struct bochs_device *bochs) { drm_mode_config_init(bochs->dev); - bochs->mode_config_initialized = true; bochs->dev->mode_config.max_width = 8192; bochs->dev->mode_config.max_height = 8192; @@ -292,8 +291,6 @@ int bochs_kms_init(struct bochs_device *bochs) void bochs_kms_fini(struct bochs_device *bochs) { - if (bochs->mode_config_initialized) { - drm_mode_config_cleanup(bochs->dev); - bochs->mode_config_initialized = false; - } + drm_atomic_helper_shutdown(bochs->dev); + drm_mode_config_cleanup(bochs->dev); } diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h index 013dffc8c1bd..1bd816be3aae 100644 --- a/drivers/gpu/drm/cirrus/cirrus_drv.h +++ b/drivers/gpu/drm/cirrus/cirrus_drv.h @@ -101,7 +101,6 @@ struct cirrus_crtc { struct cirrus_fbdev; struct cirrus_mode_info { - bool mode_config_initialized; struct cirrus_crtc *crtc; /* pointer to fbdev info structure */ struct cirrus_fbdev *gfbdev; diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c index 7f9bc32af685..b109cd71426f 100644 --- a/drivers/gpu/drm/cirrus/cirrus_mode.c +++ b/drivers/gpu/drm/cirrus/cirrus_mode.c @@ -575,7 +575,6 @@ int cirrus_modeset_init(struct cirrus_device *cdev) int ret; drm_mode_config_init(cdev->dev); - cdev->mode_info.mode_config_initialized = true; cdev->dev->mode_config.max_width = CIRRUS_MAX_FB_WIDTH; cdev->dev->mode_config.max_height = CIRRUS_MAX_FB_HEIGHT; @@ -613,9 +612,6 @@ int cirrus_modeset_init(struct cirrus_device *cdev) void cirrus_modeset_fini(struct cirrus_device *cdev) { cirrus_fbdev_fini(cdev); - - if (cdev->mode_info.mode_config_initialized) { - drm_mode_config_cleanup(cdev->dev); - cdev->mode_info.mode_config_initialized = false; - } + drm_helper_force_disable_all(cdev->dev); + drm_mode_config_cleanup(cdev->dev); } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 03749a24e4dd..84791dd4a90d 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -639,20 +639,19 @@ static struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { }; static void dpms_legacy(struct drm_fb_helper *fb_helper, int dpms_mode) { struct drm_device *dev = fb_helper->dev; - struct drm_crtc *crtc; struct drm_connector *connector; + struct drm_mode_set *modeset; int i, j; drm_modeset_lock_all(dev); for (i = 0; i < fb_helper->crtc_count; i++) { - crtc = fb_helper->crtc_info[i].mode_set.crtc; + modeset = &fb_helper->crtc_info[i].mode_set; - if (!crtc->enabled) + if (!modeset->crtc->enabled) continue; - /* Walk the connectors & encoders on this fb turning them on/off */ - drm_fb_helper_for_each_connector(fb_helper, j) { - connector = fb_helper->connector_info[j]->connector; + for (j = 0; j < modeset->num_connectors; j++) { + connector = modeset->connectors[j]; connector->funcs->dpms(connector, dpms_mode); drm_object_property_set_value(&connector->base, dev->mode_config.dpms_property, dpms_mode); @@ -1874,7 +1873,6 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper, int crtc_count = 0; int i; struct drm_fb_helper_surface_size sizes; - int gamma_size = 0; int best_depth = 0; memset(&sizes, 0, sizeof(struct drm_fb_helper_surface_size)); @@ -1890,7 +1888,6 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper, if (preferred_bpp != sizes.surface_bpp) sizes.surface_depth = sizes.surface_bpp = preferred_bpp; - /* first up get a count of crtcs now in use and new min/maxes width/heights */ drm_fb_helper_for_each_connector(fb_helper, i) { struct drm_fb_helper_connector *fb_helper_conn = fb_helper->connector_info[i]; struct drm_cmdline_mode *cmdline_mode; @@ -1970,6 +1967,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper, sizes.surface_depth = best_depth; } + /* first up get a count of crtcs now in use and new min/maxes width/heights */ crtc_count = 0; for (i = 0; i < fb_helper->crtc_count; i++) { struct drm_display_mode *desired_mode; @@ -1992,9 +1990,6 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper, x = fb_helper->crtc_info[i].x; y = fb_helper->crtc_info[i].y; - if (gamma_size == 0) - gamma_size = fb_helper->crtc_info[i].mode_set.crtc->gamma_size; - sizes.surface_width = max_t(u32, desired_mode->hdisplay + x, sizes.surface_width); sizes.surface_height = max_t(u32, desired_mode->vdisplay + y, sizes.surface_height); @@ -3317,8 +3312,6 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp) return ret; } - drm_client_add(&fb_helper->client); - if (!preferred_bpp) preferred_bpp = dev->mode_config.preferred_depth; if (!preferred_bpp) @@ -3329,6 +3322,8 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp) if (ret) DRM_DEV_DEBUG(dev->dev, "client hotplug ret=%d\n", ret); + drm_client_add(&fb_helper->client); + return 0; } EXPORT_SYMBOL(drm_fbdev_generic_setup); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 3750a982aaf6..1ee208c2c85e 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -408,7 +408,7 @@ static vm_fault_t drm_gem_shmem_fault(struct vm_fault *vmf) loff_t num_pages = obj->size >> PAGE_SHIFT; struct page *page; - if (vmf->pgoff > num_pages || WARN_ON_ONCE(!shmem->pages)) + if (vmf->pgoff >= num_pages || WARN_ON_ONCE(!shmem->pages)) return VM_FAULT_SIGBUS; page = shmem->pages[vmf->pgoff]; diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 251d67e04c2d..d9a483a5fce0 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -180,12 +180,20 @@ int drm_syncobj_handle_to_fd_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); int drm_syncobj_fd_to_handle_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); +int drm_syncobj_transfer_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private); int drm_syncobj_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); +int drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private); int drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); int drm_syncobj_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private); +int drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private); +int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private); /* drm_framebuffer.c */ void drm_framebuffer_print_info(struct drm_printer *p, unsigned int indent, diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 687943df58e1..d337f161909c 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -686,12 +686,20 @@ static const struct drm_ioctl_desc drm_ioctls[] = { DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE, drm_syncobj_fd_to_handle_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_TRANSFER, drm_syncobj_transfer_ioctl, + DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_WAIT, drm_syncobj_wait_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT, drm_syncobj_timeline_wait_ioctl, + DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_RESET, drm_syncobj_reset_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_SIGNAL, drm_syncobj_signal_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL, drm_syncobj_timeline_signal_ioctl, + DRM_UNLOCKED|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF(DRM_IOCTL_SYNCOBJ_QUERY, drm_syncobj_query_ioctl, + DRM_UNLOCKED|DRM_RENDER_ALLOW), DRM_IOCTL_DEF(DRM_IOCTL_CRTC_GET_SEQUENCE, drm_crtc_get_sequence_ioctl, DRM_UNLOCKED), DRM_IOCTL_DEF(DRM_IOCTL_CRTC_QUEUE_SEQUENCE, drm_crtc_queue_sequence_ioctl, DRM_UNLOCKED), DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_LEASE, drm_mode_create_lease_ioctl, DRM_MASTER|DRM_UNLOCKED), diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c index 8dbcdc77f6bf..132fef8ff1b6 100644 --- a/drivers/gpu/drm/drm_memory.c +++ b/drivers/gpu/drm/drm_memory.c @@ -168,6 +168,13 @@ bool drm_need_swiotlb(int dma_bits) if (xen_pv_domain()) return true; + /* + * Enforce dma_alloc_coherent when memory encryption is active as well + * for the same reasons as for Xen paravirtual hosts. + */ + if (mem_encrypt_active()) + return true; + for (tmp = iomem_resource.child; tmp; tmp = tmp->sibling) { max_iomem = max(max_iomem, tmp->end); } diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 0e7fc3e7dfb4..f5cb0aabfe35 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -253,3 +253,31 @@ void drm_err(const char *format, ...) va_end(args); } EXPORT_SYMBOL(drm_err); + +/** + * drm_print_regset32 - print the contents of registers to a + * &drm_printer stream. + * + * @p: the &drm printer + * @regset: the list of registers to print. + * + * Often in driver debug, it's useful to be able to either capture the + * contents of registers in the steady state using debugfs or at + * specific points during operation. This lets the driver have a + * single list of registers for both. + */ +void drm_print_regset32(struct drm_printer *p, struct debugfs_regset32 *regset) +{ + int namelen = 0; + int i; + + for (i = 0; i < regset->nregs; i++) + namelen = max(namelen, (int)strlen(regset->regs[i].name)); + + for (i = 0; i < regset->nregs; i++) { + drm_printf(p, "%*s = 0x%08x\n", + namelen, regset->regs[i].name, + readl(regset->base + regset->regs[i].offset)); + } +} +EXPORT_SYMBOL(drm_print_regset32); diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 5329e66598c6..f3ceeb504e6c 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -61,6 +61,7 @@ struct syncobj_wait_entry { struct task_struct *task; struct dma_fence *fence; struct dma_fence_cb fence_cb; + u64 point; }; static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj, @@ -95,6 +96,8 @@ EXPORT_SYMBOL(drm_syncobj_find); static void drm_syncobj_fence_add_wait(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait) { + struct dma_fence *fence; + if (wait->fence) return; @@ -103,11 +106,15 @@ static void drm_syncobj_fence_add_wait(struct drm_syncobj *syncobj, * have the lock, try one more time just to be sure we don't add a * callback when a fence has already been set. */ - if (syncobj->fence) - wait->fence = dma_fence_get( - rcu_dereference_protected(syncobj->fence, 1)); - else + fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, 1)); + if (!fence || dma_fence_chain_find_seqno(&fence, wait->point)) { + dma_fence_put(fence); list_add_tail(&wait->node, &syncobj->cb_list); + } else if (!fence) { + wait->fence = dma_fence_get_stub(); + } else { + wait->fence = fence; + } spin_unlock(&syncobj->lock); } @@ -123,6 +130,44 @@ static void drm_syncobj_remove_wait(struct drm_syncobj *syncobj, } /** + * drm_syncobj_add_point - add new timeline point to the syncobj + * @syncobj: sync object to add timeline point do + * @chain: chain node to use to add the point + * @fence: fence to encapsulate in the chain node + * @point: sequence number to use for the point + * + * Add the chain node as new timeline point to the syncobj. + */ +void drm_syncobj_add_point(struct drm_syncobj *syncobj, + struct dma_fence_chain *chain, + struct dma_fence *fence, + uint64_t point) +{ + struct syncobj_wait_entry *cur, *tmp; + struct dma_fence *prev; + + dma_fence_get(fence); + + spin_lock(&syncobj->lock); + + prev = drm_syncobj_fence_get(syncobj); + /* You are adding an unorder point to timeline, which could cause payload returned from query_ioctl is 0! */ + if (prev && prev->seqno >= point) + DRM_ERROR("You are adding an unorder point to timeline!\n"); + dma_fence_chain_init(chain, prev, fence, point); + rcu_assign_pointer(syncobj->fence, &chain->base); + + list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) + syncobj_wait_syncobj_func(syncobj, cur); + spin_unlock(&syncobj->lock); + + /* Walk the chain once to trigger garbage collection */ + dma_fence_chain_for_each(fence, prev); + dma_fence_put(prev); +} +EXPORT_SYMBOL(drm_syncobj_add_point); + +/** * drm_syncobj_replace_fence - replace fence in a sync object. * @syncobj: Sync object to replace fence in * @fence: fence to install in sync file. @@ -145,10 +190,8 @@ void drm_syncobj_replace_fence(struct drm_syncobj *syncobj, rcu_assign_pointer(syncobj->fence, fence); if (fence != old_fence) { - list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) { - list_del_init(&cur->node); + list_for_each_entry_safe(cur, tmp, &syncobj->cb_list, node) syncobj_wait_syncobj_func(syncobj, cur); - } } spin_unlock(&syncobj->lock); @@ -171,6 +214,8 @@ static void drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) dma_fence_put(fence); } +/* 5s default for wait submission */ +#define DRM_SYNCOBJ_WAIT_FOR_SUBMIT_TIMEOUT 5000000000ULL /** * drm_syncobj_find_fence - lookup and reference the fence in a sync object * @file_private: drm file private pointer @@ -191,16 +236,58 @@ int drm_syncobj_find_fence(struct drm_file *file_private, struct dma_fence **fence) { struct drm_syncobj *syncobj = drm_syncobj_find(file_private, handle); - int ret = 0; + struct syncobj_wait_entry wait; + u64 timeout = nsecs_to_jiffies64(DRM_SYNCOBJ_WAIT_FOR_SUBMIT_TIMEOUT); + int ret; if (!syncobj) return -ENOENT; *fence = drm_syncobj_fence_get(syncobj); - if (!*fence) { + drm_syncobj_put(syncobj); + + if (*fence) { + ret = dma_fence_chain_find_seqno(fence, point); + if (!ret) + return 0; + dma_fence_put(*fence); + } else { ret = -EINVAL; } - drm_syncobj_put(syncobj); + + if (!(flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT)) + return ret; + + memset(&wait, 0, sizeof(wait)); + wait.task = current; + wait.point = point; + drm_syncobj_fence_add_wait(syncobj, &wait); + + do { + set_current_state(TASK_INTERRUPTIBLE); + if (wait.fence) { + ret = 0; + break; + } + if (timeout == 0) { + ret = -ETIME; + break; + } + + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + + timeout = schedule_timeout(timeout); + } while (1); + + __set_current_state(TASK_RUNNING); + *fence = wait.fence; + + if (wait.node.next) + drm_syncobj_remove_wait(syncobj, &wait); + return ret; } EXPORT_SYMBOL(drm_syncobj_find_fence); @@ -593,6 +680,80 @@ drm_syncobj_fd_to_handle_ioctl(struct drm_device *dev, void *data, &args->handle); } +static int drm_syncobj_transfer_to_timeline(struct drm_file *file_private, + struct drm_syncobj_transfer *args) +{ + struct drm_syncobj *timeline_syncobj = NULL; + struct dma_fence *fence; + struct dma_fence_chain *chain; + int ret; + + timeline_syncobj = drm_syncobj_find(file_private, args->dst_handle); + if (!timeline_syncobj) { + return -ENOENT; + } + ret = drm_syncobj_find_fence(file_private, args->src_handle, + args->src_point, args->flags, + &fence); + if (ret) + goto err; + chain = kzalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); + if (!chain) { + ret = -ENOMEM; + goto err1; + } + drm_syncobj_add_point(timeline_syncobj, chain, fence, args->dst_point); +err1: + dma_fence_put(fence); +err: + drm_syncobj_put(timeline_syncobj); + + return ret; +} + +static int +drm_syncobj_transfer_to_binary(struct drm_file *file_private, + struct drm_syncobj_transfer *args) +{ + struct drm_syncobj *binary_syncobj = NULL; + struct dma_fence *fence; + int ret; + + binary_syncobj = drm_syncobj_find(file_private, args->dst_handle); + if (!binary_syncobj) + return -ENOENT; + ret = drm_syncobj_find_fence(file_private, args->src_handle, + args->src_point, args->flags, &fence); + if (ret) + goto err; + drm_syncobj_replace_fence(binary_syncobj, fence); + dma_fence_put(fence); +err: + drm_syncobj_put(binary_syncobj); + + return ret; +} +int +drm_syncobj_transfer_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_transfer *args = data; + int ret; + + if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) + return -ENODEV; + + if (args->pad) + return -EINVAL; + + if (args->dst_point) + ret = drm_syncobj_transfer_to_timeline(file_private, args); + else + ret = drm_syncobj_transfer_to_binary(file_private, args); + + return ret; +} + static void syncobj_wait_fence_func(struct dma_fence *fence, struct dma_fence_cb *cb) { @@ -605,13 +766,27 @@ static void syncobj_wait_fence_func(struct dma_fence *fence, static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait) { + struct dma_fence *fence; + /* This happens inside the syncobj lock */ - wait->fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, - lockdep_is_held(&syncobj->lock))); + fence = rcu_dereference_protected(syncobj->fence, + lockdep_is_held(&syncobj->lock)); + dma_fence_get(fence); + if (!fence || dma_fence_chain_find_seqno(&fence, wait->point)) { + dma_fence_put(fence); + return; + } else if (!fence) { + wait->fence = dma_fence_get_stub(); + } else { + wait->fence = fence; + } + wake_up_process(wait->task); + list_del_init(&wait->node); } static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, + void __user *user_points, uint32_t count, uint32_t flags, signed long timeout, @@ -619,12 +794,27 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, { struct syncobj_wait_entry *entries; struct dma_fence *fence; + uint64_t *points; uint32_t signaled_count, i; - entries = kcalloc(count, sizeof(*entries), GFP_KERNEL); - if (!entries) + points = kmalloc_array(count, sizeof(*points), GFP_KERNEL); + if (points == NULL) return -ENOMEM; + if (!user_points) { + memset(points, 0, count * sizeof(uint64_t)); + + } else if (copy_from_user(points, user_points, + sizeof(uint64_t) * count)) { + timeout = -EFAULT; + goto err_free_points; + } + + entries = kcalloc(count, sizeof(*entries), GFP_KERNEL); + if (!entries) { + timeout = -ENOMEM; + goto err_free_points; + } /* Walk the list of sync objects and initialize entries. We do * this up-front so that we can properly return -EINVAL if there is * a syncobj with a missing fence and then never have the chance of @@ -632,9 +822,13 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, */ signaled_count = 0; for (i = 0; i < count; ++i) { + struct dma_fence *fence; + entries[i].task = current; - entries[i].fence = drm_syncobj_fence_get(syncobjs[i]); - if (!entries[i].fence) { + entries[i].point = points[i]; + fence = drm_syncobj_fence_get(syncobjs[i]); + if (!fence || dma_fence_chain_find_seqno(&fence, points[i])) { + dma_fence_put(fence); if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { continue; } else { @@ -643,7 +837,13 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, } } - if (dma_fence_is_signaled(entries[i].fence)) { + if (fence) + entries[i].fence = fence; + else + entries[i].fence = dma_fence_get_stub(); + + if ((flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) || + dma_fence_is_signaled(entries[i].fence)) { if (signaled_count == 0 && idx) *idx = i; signaled_count++; @@ -676,7 +876,8 @@ static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, if (!fence) continue; - if (dma_fence_is_signaled(fence) || + if ((flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) || + dma_fence_is_signaled(fence) || (!entries[i].fence_cb.func && dma_fence_add_callback(fence, &entries[i].fence_cb, @@ -721,6 +922,9 @@ cleanup_entries: } kfree(entries); +err_free_points: + kfree(points); + return timeout; } @@ -760,19 +964,33 @@ EXPORT_SYMBOL(drm_timeout_abs_to_jiffies); static int drm_syncobj_array_wait(struct drm_device *dev, struct drm_file *file_private, struct drm_syncobj_wait *wait, - struct drm_syncobj **syncobjs) + struct drm_syncobj_timeline_wait *timeline_wait, + struct drm_syncobj **syncobjs, bool timeline) { - signed long timeout = drm_timeout_abs_to_jiffies(wait->timeout_nsec); + signed long timeout = 0; uint32_t first = ~0; - timeout = drm_syncobj_array_wait_timeout(syncobjs, - wait->count_handles, - wait->flags, - timeout, &first); - if (timeout < 0) - return timeout; - - wait->first_signaled = first; + if (!timeline) { + timeout = drm_timeout_abs_to_jiffies(wait->timeout_nsec); + timeout = drm_syncobj_array_wait_timeout(syncobjs, + NULL, + wait->count_handles, + wait->flags, + timeout, &first); + if (timeout < 0) + return timeout; + wait->first_signaled = first; + } else { + timeout = drm_timeout_abs_to_jiffies(timeline_wait->timeout_nsec); + timeout = drm_syncobj_array_wait_timeout(syncobjs, + u64_to_user_ptr(timeline_wait->points), + timeline_wait->count_handles, + timeline_wait->flags, + timeout, &first); + if (timeout < 0) + return timeout; + timeline_wait->first_signaled = first; + } return 0; } @@ -858,13 +1076,48 @@ drm_syncobj_wait_ioctl(struct drm_device *dev, void *data, return ret; ret = drm_syncobj_array_wait(dev, file_private, - args, syncobjs); + args, NULL, syncobjs, false); + + drm_syncobj_array_free(syncobjs, args->count_handles); + + return ret; +} + +int +drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_timeline_wait *args = data; + struct drm_syncobj **syncobjs; + int ret = 0; + + if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) + return -ENODEV; + + if (args->flags & ~(DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | + DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) + return -EINVAL; + + if (args->count_handles == 0) + return -EINVAL; + + ret = drm_syncobj_array_find(file_private, + u64_to_user_ptr(args->handles), + args->count_handles, + &syncobjs); + if (ret < 0) + return ret; + + ret = drm_syncobj_array_wait(dev, file_private, + NULL, args, syncobjs, true); drm_syncobj_array_free(syncobjs, args->count_handles); return ret; } + int drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) @@ -930,3 +1183,138 @@ drm_syncobj_signal_ioctl(struct drm_device *dev, void *data, return ret; } + +int +drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_timeline_array *args = data; + struct drm_syncobj **syncobjs; + struct dma_fence_chain **chains; + uint64_t *points; + uint32_t i, j; + int ret; + + if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) + return -EOPNOTSUPP; + + if (args->pad != 0) + return -EINVAL; + + if (args->count_handles == 0) + return -EINVAL; + + ret = drm_syncobj_array_find(file_private, + u64_to_user_ptr(args->handles), + args->count_handles, + &syncobjs); + if (ret < 0) + return ret; + + points = kmalloc_array(args->count_handles, sizeof(*points), + GFP_KERNEL); + if (!points) { + ret = -ENOMEM; + goto out; + } + if (!u64_to_user_ptr(args->points)) { + memset(points, 0, args->count_handles * sizeof(uint64_t)); + } else if (copy_from_user(points, u64_to_user_ptr(args->points), + sizeof(uint64_t) * args->count_handles)) { + ret = -EFAULT; + goto err_points; + } + + chains = kmalloc_array(args->count_handles, sizeof(void *), GFP_KERNEL); + if (!chains) { + ret = -ENOMEM; + goto err_points; + } + for (i = 0; i < args->count_handles; i++) { + chains[i] = kzalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); + if (!chains[i]) { + for (j = 0; j < i; j++) + kfree(chains[j]); + ret = -ENOMEM; + goto err_chains; + } + } + + for (i = 0; i < args->count_handles; i++) { + struct dma_fence *fence = dma_fence_get_stub(); + + drm_syncobj_add_point(syncobjs[i], chains[i], + fence, points[i]); + dma_fence_put(fence); + } +err_chains: + kfree(chains); +err_points: + kfree(points); +out: + drm_syncobj_array_free(syncobjs, args->count_handles); + + return ret; +} + +int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_private) +{ + struct drm_syncobj_timeline_array *args = data; + struct drm_syncobj **syncobjs; + uint64_t __user *points = u64_to_user_ptr(args->points); + uint32_t i; + int ret; + + if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) + return -ENODEV; + + if (args->pad != 0) + return -EINVAL; + + if (args->count_handles == 0) + return -EINVAL; + + ret = drm_syncobj_array_find(file_private, + u64_to_user_ptr(args->handles), + args->count_handles, + &syncobjs); + if (ret < 0) + return ret; + + for (i = 0; i < args->count_handles; i++) { + struct dma_fence_chain *chain; + struct dma_fence *fence; + uint64_t point; + + fence = drm_syncobj_fence_get(syncobjs[i]); + chain = to_dma_fence_chain(fence); + if (chain) { + struct dma_fence *iter, *last_signaled = NULL; + + dma_fence_chain_for_each(iter, fence) { + if (!iter) + break; + dma_fence_put(last_signaled); + last_signaled = dma_fence_get(iter); + if (!to_dma_fence_chain(last_signaled)->prev_seqno) + /* It is most likely that timeline has + * unorder points. */ + break; + } + point = dma_fence_is_signaled(last_signaled) ? + last_signaled->seqno : + to_dma_fence_chain(last_signaled)->prev_seqno; + dma_fence_put(last_signaled); + } else { + point = 0; + } + ret = copy_to_user(&points[i], &point, sizeof(uint64_t)); + ret = ret ? -EFAULT : 0; + if (ret) + break; + } + drm_syncobj_array_free(syncobjs, args->count_handles); + + return ret; +} diff --git a/drivers/gpu/drm/lima/Kconfig b/drivers/gpu/drm/lima/Kconfig new file mode 100644 index 000000000000..f11314448093 --- /dev/null +++ b/drivers/gpu/drm/lima/Kconfig @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 OR MIT +# Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> + +config DRM_LIMA + tristate "LIMA (DRM support for ARM Mali 400/450 GPU)" + depends on DRM + depends on ARM || ARM64 || COMPILE_TEST + select DRM_SCHED + help + DRM driver for ARM Mali 400/450 GPUs. diff --git a/drivers/gpu/drm/lima/Makefile b/drivers/gpu/drm/lima/Makefile new file mode 100644 index 000000000000..38cc70281ba5 --- /dev/null +++ b/drivers/gpu/drm/lima/Makefile @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: GPL-2.0 OR MIT +# Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> + +lima-y := \ + lima_drv.o \ + lima_device.o \ + lima_pmu.o \ + lima_l2_cache.o \ + lima_mmu.o \ + lima_gp.o \ + lima_pp.o \ + lima_gem.o \ + lima_vm.o \ + lima_sched.o \ + lima_ctx.o \ + lima_gem_prime.o \ + lima_dlbu.o \ + lima_bcast.o \ + lima_object.o + +obj-$(CONFIG_DRM_LIMA) += lima.o diff --git a/drivers/gpu/drm/lima/lima_bcast.c b/drivers/gpu/drm/lima/lima_bcast.c new file mode 100644 index 000000000000..288398027bfa --- /dev/null +++ b/drivers/gpu/drm/lima/lima_bcast.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/io.h> +#include <linux/device.h> + +#include "lima_device.h" +#include "lima_bcast.h" +#include "lima_regs.h" + +#define bcast_write(reg, data) writel(data, ip->iomem + reg) +#define bcast_read(reg) readl(ip->iomem + reg) + +void lima_bcast_enable(struct lima_device *dev, int num_pp) +{ + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + struct lima_ip *ip = dev->ip + lima_ip_bcast; + int i, mask = bcast_read(LIMA_BCAST_BROADCAST_MASK) & 0xffff0000; + + for (i = 0; i < num_pp; i++) { + struct lima_ip *pp = pipe->processor[i]; + + mask |= 1 << (pp->id - lima_ip_pp0); + } + + bcast_write(LIMA_BCAST_BROADCAST_MASK, mask); +} + +int lima_bcast_init(struct lima_ip *ip) +{ + int i, mask = 0; + + for (i = lima_ip_pp0; i <= lima_ip_pp7; i++) { + if (ip->dev->ip[i].present) + mask |= 1 << (i - lima_ip_pp0); + } + + bcast_write(LIMA_BCAST_BROADCAST_MASK, mask << 16); + bcast_write(LIMA_BCAST_INTERRUPT_MASK, mask); + return 0; +} + +void lima_bcast_fini(struct lima_ip *ip) +{ + +} + diff --git a/drivers/gpu/drm/lima/lima_bcast.h b/drivers/gpu/drm/lima/lima_bcast.h new file mode 100644 index 000000000000..c47e58563d0a --- /dev/null +++ b/drivers/gpu/drm/lima/lima_bcast.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_BCAST_H__ +#define __LIMA_BCAST_H__ + +struct lima_ip; + +int lima_bcast_init(struct lima_ip *ip); +void lima_bcast_fini(struct lima_ip *ip); + +void lima_bcast_enable(struct lima_device *dev, int num_pp); + +#endif diff --git a/drivers/gpu/drm/lima/lima_ctx.c b/drivers/gpu/drm/lima/lima_ctx.c new file mode 100644 index 000000000000..22fff6caa961 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_ctx.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/slab.h> + +#include "lima_device.h" +#include "lima_ctx.h" + +int lima_ctx_create(struct lima_device *dev, struct lima_ctx_mgr *mgr, u32 *id) +{ + struct lima_ctx *ctx; + int i, err; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + ctx->dev = dev; + kref_init(&ctx->refcnt); + + for (i = 0; i < lima_pipe_num; i++) { + err = lima_sched_context_init(dev->pipe + i, ctx->context + i, &ctx->guilty); + if (err) + goto err_out0; + } + + err = xa_alloc(&mgr->handles, id, ctx, xa_limit_32b, GFP_KERNEL); + if (err < 0) + goto err_out0; + + return 0; + +err_out0: + for (i--; i >= 0; i--) + lima_sched_context_fini(dev->pipe + i, ctx->context + i); + kfree(ctx); + return err; +} + +static void lima_ctx_do_release(struct kref *ref) +{ + struct lima_ctx *ctx = container_of(ref, struct lima_ctx, refcnt); + int i; + + for (i = 0; i < lima_pipe_num; i++) + lima_sched_context_fini(ctx->dev->pipe + i, ctx->context + i); + kfree(ctx); +} + +int lima_ctx_free(struct lima_ctx_mgr *mgr, u32 id) +{ + struct lima_ctx *ctx; + int ret = 0; + + mutex_lock(&mgr->lock); + ctx = xa_erase(&mgr->handles, id); + if (ctx) + kref_put(&ctx->refcnt, lima_ctx_do_release); + else + ret = -EINVAL; + mutex_unlock(&mgr->lock); + return ret; +} + +struct lima_ctx *lima_ctx_get(struct lima_ctx_mgr *mgr, u32 id) +{ + struct lima_ctx *ctx; + + mutex_lock(&mgr->lock); + ctx = xa_load(&mgr->handles, id); + if (ctx) + kref_get(&ctx->refcnt); + mutex_unlock(&mgr->lock); + return ctx; +} + +void lima_ctx_put(struct lima_ctx *ctx) +{ + kref_put(&ctx->refcnt, lima_ctx_do_release); +} + +void lima_ctx_mgr_init(struct lima_ctx_mgr *mgr) +{ + mutex_init(&mgr->lock); + xa_init_flags(&mgr->handles, XA_FLAGS_ALLOC); +} + +void lima_ctx_mgr_fini(struct lima_ctx_mgr *mgr) +{ + struct lima_ctx *ctx; + unsigned long id; + + xa_for_each(&mgr->handles, id, ctx) { + kref_put(&ctx->refcnt, lima_ctx_do_release); + } + + xa_destroy(&mgr->handles); + mutex_destroy(&mgr->lock); +} diff --git a/drivers/gpu/drm/lima/lima_ctx.h b/drivers/gpu/drm/lima/lima_ctx.h new file mode 100644 index 000000000000..6154e5c9bfe4 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_ctx.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_CTX_H__ +#define __LIMA_CTX_H__ + +#include <linux/xarray.h> + +#include "lima_device.h" + +struct lima_ctx { + struct kref refcnt; + struct lima_device *dev; + struct lima_sched_context context[lima_pipe_num]; + atomic_t guilty; +}; + +struct lima_ctx_mgr { + struct mutex lock; + struct xarray handles; +}; + +int lima_ctx_create(struct lima_device *dev, struct lima_ctx_mgr *mgr, u32 *id); +int lima_ctx_free(struct lima_ctx_mgr *mgr, u32 id); +struct lima_ctx *lima_ctx_get(struct lima_ctx_mgr *mgr, u32 id); +void lima_ctx_put(struct lima_ctx *ctx); +void lima_ctx_mgr_init(struct lima_ctx_mgr *mgr); +void lima_ctx_mgr_fini(struct lima_ctx_mgr *mgr); + +#endif diff --git a/drivers/gpu/drm/lima/lima_device.c b/drivers/gpu/drm/lima/lima_device.c new file mode 100644 index 000000000000..570d0e93f9a9 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_device.c @@ -0,0 +1,385 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/regulator/consumer.h> +#include <linux/reset.h> +#include <linux/clk.h> +#include <linux/dma-mapping.h> +#include <linux/platform_device.h> + +#include "lima_device.h" +#include "lima_gp.h" +#include "lima_pp.h" +#include "lima_mmu.h" +#include "lima_pmu.h" +#include "lima_l2_cache.h" +#include "lima_dlbu.h" +#include "lima_bcast.h" +#include "lima_vm.h" + +struct lima_ip_desc { + char *name; + char *irq_name; + bool must_have[lima_gpu_num]; + int offset[lima_gpu_num]; + + int (*init)(struct lima_ip *ip); + void (*fini)(struct lima_ip *ip); +}; + +#define LIMA_IP_DESC(ipname, mst0, mst1, off0, off1, func, irq) \ + [lima_ip_##ipname] = { \ + .name = #ipname, \ + .irq_name = irq, \ + .must_have = { \ + [lima_gpu_mali400] = mst0, \ + [lima_gpu_mali450] = mst1, \ + }, \ + .offset = { \ + [lima_gpu_mali400] = off0, \ + [lima_gpu_mali450] = off1, \ + }, \ + .init = lima_##func##_init, \ + .fini = lima_##func##_fini, \ + } + +static struct lima_ip_desc lima_ip_desc[lima_ip_num] = { + LIMA_IP_DESC(pmu, false, false, 0x02000, 0x02000, pmu, "pmu"), + LIMA_IP_DESC(l2_cache0, true, true, 0x01000, 0x10000, l2_cache, NULL), + LIMA_IP_DESC(l2_cache1, false, true, -1, 0x01000, l2_cache, NULL), + LIMA_IP_DESC(l2_cache2, false, false, -1, 0x11000, l2_cache, NULL), + LIMA_IP_DESC(gp, true, true, 0x00000, 0x00000, gp, "gp"), + LIMA_IP_DESC(pp0, true, true, 0x08000, 0x08000, pp, "pp0"), + LIMA_IP_DESC(pp1, false, false, 0x0A000, 0x0A000, pp, "pp1"), + LIMA_IP_DESC(pp2, false, false, 0x0C000, 0x0C000, pp, "pp2"), + LIMA_IP_DESC(pp3, false, false, 0x0E000, 0x0E000, pp, "pp3"), + LIMA_IP_DESC(pp4, false, false, -1, 0x28000, pp, "pp4"), + LIMA_IP_DESC(pp5, false, false, -1, 0x2A000, pp, "pp5"), + LIMA_IP_DESC(pp6, false, false, -1, 0x2C000, pp, "pp6"), + LIMA_IP_DESC(pp7, false, false, -1, 0x2E000, pp, "pp7"), + LIMA_IP_DESC(gpmmu, true, true, 0x03000, 0x03000, mmu, "gpmmu"), + LIMA_IP_DESC(ppmmu0, true, true, 0x04000, 0x04000, mmu, "ppmmu0"), + LIMA_IP_DESC(ppmmu1, false, false, 0x05000, 0x05000, mmu, "ppmmu1"), + LIMA_IP_DESC(ppmmu2, false, false, 0x06000, 0x06000, mmu, "ppmmu2"), + LIMA_IP_DESC(ppmmu3, false, false, 0x07000, 0x07000, mmu, "ppmmu3"), + LIMA_IP_DESC(ppmmu4, false, false, -1, 0x1C000, mmu, "ppmmu4"), + LIMA_IP_DESC(ppmmu5, false, false, -1, 0x1D000, mmu, "ppmmu5"), + LIMA_IP_DESC(ppmmu6, false, false, -1, 0x1E000, mmu, "ppmmu6"), + LIMA_IP_DESC(ppmmu7, false, false, -1, 0x1F000, mmu, "ppmmu7"), + LIMA_IP_DESC(dlbu, false, true, -1, 0x14000, dlbu, NULL), + LIMA_IP_DESC(bcast, false, true, -1, 0x13000, bcast, NULL), + LIMA_IP_DESC(pp_bcast, false, true, -1, 0x16000, pp_bcast, "pp"), + LIMA_IP_DESC(ppmmu_bcast, false, true, -1, 0x15000, mmu, NULL), +}; + +const char *lima_ip_name(struct lima_ip *ip) +{ + return lima_ip_desc[ip->id].name; +} + +static int lima_clk_init(struct lima_device *dev) +{ + int err; + unsigned long bus_rate, gpu_rate; + + dev->clk_bus = devm_clk_get(dev->dev, "bus"); + if (IS_ERR(dev->clk_bus)) { + dev_err(dev->dev, "get bus clk failed %ld\n", PTR_ERR(dev->clk_bus)); + return PTR_ERR(dev->clk_bus); + } + + dev->clk_gpu = devm_clk_get(dev->dev, "core"); + if (IS_ERR(dev->clk_gpu)) { + dev_err(dev->dev, "get core clk failed %ld\n", PTR_ERR(dev->clk_gpu)); + return PTR_ERR(dev->clk_gpu); + } + + bus_rate = clk_get_rate(dev->clk_bus); + dev_info(dev->dev, "bus rate = %lu\n", bus_rate); + + gpu_rate = clk_get_rate(dev->clk_gpu); + dev_info(dev->dev, "mod rate = %lu", gpu_rate); + + err = clk_prepare_enable(dev->clk_bus); + if (err) + return err; + + err = clk_prepare_enable(dev->clk_gpu); + if (err) + goto error_out0; + + dev->reset = devm_reset_control_get_optional(dev->dev, NULL); + if (IS_ERR(dev->reset)) { + err = PTR_ERR(dev->reset); + goto error_out1; + } else if (dev->reset != NULL) { + err = reset_control_deassert(dev->reset); + if (err) + goto error_out1; + } + + return 0; + +error_out1: + clk_disable_unprepare(dev->clk_gpu); +error_out0: + clk_disable_unprepare(dev->clk_bus); + return err; +} + +static void lima_clk_fini(struct lima_device *dev) +{ + if (dev->reset != NULL) + reset_control_assert(dev->reset); + clk_disable_unprepare(dev->clk_gpu); + clk_disable_unprepare(dev->clk_bus); +} + +static int lima_regulator_init(struct lima_device *dev) +{ + int ret; + + dev->regulator = devm_regulator_get_optional(dev->dev, "mali"); + if (IS_ERR(dev->regulator)) { + ret = PTR_ERR(dev->regulator); + dev->regulator = NULL; + if (ret == -ENODEV) + return 0; + dev_err(dev->dev, "failed to get regulator: %d\n", ret); + return ret; + } + + ret = regulator_enable(dev->regulator); + if (ret < 0) { + dev_err(dev->dev, "failed to enable regulator: %d\n", ret); + return ret; + } + + return 0; +} + +static void lima_regulator_fini(struct lima_device *dev) +{ + if (dev->regulator) + regulator_disable(dev->regulator); +} + +static int lima_init_ip(struct lima_device *dev, int index) +{ + struct lima_ip_desc *desc = lima_ip_desc + index; + struct lima_ip *ip = dev->ip + index; + int offset = desc->offset[dev->id]; + bool must = desc->must_have[dev->id]; + int err; + + if (offset < 0) + return 0; + + ip->dev = dev; + ip->id = index; + ip->iomem = dev->iomem + offset; + if (desc->irq_name) { + err = platform_get_irq_byname(dev->pdev, desc->irq_name); + if (err < 0) + goto out; + ip->irq = err; + } + + err = desc->init(ip); + if (!err) { + ip->present = true; + return 0; + } + +out: + return must ? err : 0; +} + +static void lima_fini_ip(struct lima_device *ldev, int index) +{ + struct lima_ip_desc *desc = lima_ip_desc + index; + struct lima_ip *ip = ldev->ip + index; + + if (ip->present) + desc->fini(ip); +} + +static int lima_init_gp_pipe(struct lima_device *dev) +{ + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp; + int err; + + err = lima_sched_pipe_init(pipe, "gp"); + if (err) + return err; + + pipe->l2_cache[pipe->num_l2_cache++] = dev->ip + lima_ip_l2_cache0; + pipe->mmu[pipe->num_mmu++] = dev->ip + lima_ip_gpmmu; + pipe->processor[pipe->num_processor++] = dev->ip + lima_ip_gp; + + err = lima_gp_pipe_init(dev); + if (err) { + lima_sched_pipe_fini(pipe); + return err; + } + + return 0; +} + +static void lima_fini_gp_pipe(struct lima_device *dev) +{ + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp; + + lima_gp_pipe_fini(dev); + lima_sched_pipe_fini(pipe); +} + +static int lima_init_pp_pipe(struct lima_device *dev) +{ + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + int err, i; + + err = lima_sched_pipe_init(pipe, "pp"); + if (err) + return err; + + for (i = 0; i < LIMA_SCHED_PIPE_MAX_PROCESSOR; i++) { + struct lima_ip *pp = dev->ip + lima_ip_pp0 + i; + struct lima_ip *ppmmu = dev->ip + lima_ip_ppmmu0 + i; + struct lima_ip *l2_cache; + + if (dev->id == lima_gpu_mali400) + l2_cache = dev->ip + lima_ip_l2_cache0; + else + l2_cache = dev->ip + lima_ip_l2_cache1 + (i >> 2); + + if (pp->present && ppmmu->present && l2_cache->present) { + pipe->mmu[pipe->num_mmu++] = ppmmu; + pipe->processor[pipe->num_processor++] = pp; + if (!pipe->l2_cache[i >> 2]) + pipe->l2_cache[pipe->num_l2_cache++] = l2_cache; + } + } + + if (dev->ip[lima_ip_bcast].present) { + pipe->bcast_processor = dev->ip + lima_ip_pp_bcast; + pipe->bcast_mmu = dev->ip + lima_ip_ppmmu_bcast; + } + + err = lima_pp_pipe_init(dev); + if (err) { + lima_sched_pipe_fini(pipe); + return err; + } + + return 0; +} + +static void lima_fini_pp_pipe(struct lima_device *dev) +{ + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + + lima_pp_pipe_fini(dev); + lima_sched_pipe_fini(pipe); +} + +int lima_device_init(struct lima_device *ldev) +{ + int err, i; + struct resource *res; + + dma_set_coherent_mask(ldev->dev, DMA_BIT_MASK(32)); + + err = lima_clk_init(ldev); + if (err) { + dev_err(ldev->dev, "clk init fail %d\n", err); + return err; + } + + err = lima_regulator_init(ldev); + if (err) { + dev_err(ldev->dev, "regulator init fail %d\n", err); + goto err_out0; + } + + ldev->empty_vm = lima_vm_create(ldev); + if (!ldev->empty_vm) { + err = -ENOMEM; + goto err_out1; + } + + ldev->va_start = 0; + if (ldev->id == lima_gpu_mali450) { + ldev->va_end = LIMA_VA_RESERVE_START; + ldev->dlbu_cpu = dma_alloc_wc( + ldev->dev, LIMA_PAGE_SIZE, + &ldev->dlbu_dma, GFP_KERNEL); + if (!ldev->dlbu_cpu) { + err = -ENOMEM; + goto err_out2; + } + } else + ldev->va_end = LIMA_VA_RESERVE_END; + + res = platform_get_resource(ldev->pdev, IORESOURCE_MEM, 0); + ldev->iomem = devm_ioremap_resource(ldev->dev, res); + if (IS_ERR(ldev->iomem)) { + dev_err(ldev->dev, "fail to ioremap iomem\n"); + err = PTR_ERR(ldev->iomem); + goto err_out3; + } + + for (i = 0; i < lima_ip_num; i++) { + err = lima_init_ip(ldev, i); + if (err) + goto err_out4; + } + + err = lima_init_gp_pipe(ldev); + if (err) + goto err_out4; + + err = lima_init_pp_pipe(ldev); + if (err) + goto err_out5; + + return 0; + +err_out5: + lima_fini_gp_pipe(ldev); +err_out4: + while (--i >= 0) + lima_fini_ip(ldev, i); +err_out3: + if (ldev->dlbu_cpu) + dma_free_wc(ldev->dev, LIMA_PAGE_SIZE, + ldev->dlbu_cpu, ldev->dlbu_dma); +err_out2: + lima_vm_put(ldev->empty_vm); +err_out1: + lima_regulator_fini(ldev); +err_out0: + lima_clk_fini(ldev); + return err; +} + +void lima_device_fini(struct lima_device *ldev) +{ + int i; + + lima_fini_pp_pipe(ldev); + lima_fini_gp_pipe(ldev); + + for (i = lima_ip_num - 1; i >= 0; i--) + lima_fini_ip(ldev, i); + + if (ldev->dlbu_cpu) + dma_free_wc(ldev->dev, LIMA_PAGE_SIZE, + ldev->dlbu_cpu, ldev->dlbu_dma); + + lima_vm_put(ldev->empty_vm); + + lima_regulator_fini(ldev); + + lima_clk_fini(ldev); +} diff --git a/drivers/gpu/drm/lima/lima_device.h b/drivers/gpu/drm/lima/lima_device.h new file mode 100644 index 000000000000..31158d86271c --- /dev/null +++ b/drivers/gpu/drm/lima/lima_device.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_DEVICE_H__ +#define __LIMA_DEVICE_H__ + +#include <drm/drm_device.h> +#include <linux/delay.h> + +#include "lima_sched.h" + +enum lima_gpu_id { + lima_gpu_mali400 = 0, + lima_gpu_mali450, + lima_gpu_num, +}; + +enum lima_ip_id { + lima_ip_pmu, + lima_ip_gpmmu, + lima_ip_ppmmu0, + lima_ip_ppmmu1, + lima_ip_ppmmu2, + lima_ip_ppmmu3, + lima_ip_ppmmu4, + lima_ip_ppmmu5, + lima_ip_ppmmu6, + lima_ip_ppmmu7, + lima_ip_gp, + lima_ip_pp0, + lima_ip_pp1, + lima_ip_pp2, + lima_ip_pp3, + lima_ip_pp4, + lima_ip_pp5, + lima_ip_pp6, + lima_ip_pp7, + lima_ip_l2_cache0, + lima_ip_l2_cache1, + lima_ip_l2_cache2, + lima_ip_dlbu, + lima_ip_bcast, + lima_ip_pp_bcast, + lima_ip_ppmmu_bcast, + lima_ip_num, +}; + +struct lima_device; + +struct lima_ip { + struct lima_device *dev; + enum lima_ip_id id; + bool present; + + void __iomem *iomem; + int irq; + + union { + /* gp/pp */ + bool async_reset; + /* l2 cache */ + spinlock_t lock; + } data; +}; + +enum lima_pipe_id { + lima_pipe_gp, + lima_pipe_pp, + lima_pipe_num, +}; + +struct lima_device { + struct device *dev; + struct drm_device *ddev; + struct platform_device *pdev; + + enum lima_gpu_id id; + u32 gp_version; + u32 pp_version; + int num_pp; + + void __iomem *iomem; + struct clk *clk_bus; + struct clk *clk_gpu; + struct reset_control *reset; + struct regulator *regulator; + + struct lima_ip ip[lima_ip_num]; + struct lima_sched_pipe pipe[lima_pipe_num]; + + struct lima_vm *empty_vm; + uint64_t va_start; + uint64_t va_end; + + u32 *dlbu_cpu; + dma_addr_t dlbu_dma; +}; + +static inline struct lima_device * +to_lima_dev(struct drm_device *dev) +{ + return dev->dev_private; +} + +int lima_device_init(struct lima_device *ldev); +void lima_device_fini(struct lima_device *ldev); + +const char *lima_ip_name(struct lima_ip *ip); + +typedef int (*lima_poll_func_t)(struct lima_ip *); + +static inline int lima_poll_timeout(struct lima_ip *ip, lima_poll_func_t func, + int sleep_us, int timeout_us) +{ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); + + might_sleep_if(sleep_us); + while (1) { + if (func(ip)) + return 0; + + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) + return -ETIMEDOUT; + + if (sleep_us) + usleep_range((sleep_us >> 2) + 1, sleep_us); + } + return 0; +} + +#endif diff --git a/drivers/gpu/drm/lima/lima_dlbu.c b/drivers/gpu/drm/lima/lima_dlbu.c new file mode 100644 index 000000000000..8399ceffb94b --- /dev/null +++ b/drivers/gpu/drm/lima/lima_dlbu.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/io.h> +#include <linux/device.h> + +#include "lima_device.h" +#include "lima_dlbu.h" +#include "lima_vm.h" +#include "lima_regs.h" + +#define dlbu_write(reg, data) writel(data, ip->iomem + reg) +#define dlbu_read(reg) readl(ip->iomem + reg) + +void lima_dlbu_enable(struct lima_device *dev, int num_pp) +{ + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + struct lima_ip *ip = dev->ip + lima_ip_dlbu; + int i, mask = 0; + + for (i = 0; i < num_pp; i++) { + struct lima_ip *pp = pipe->processor[i]; + + mask |= 1 << (pp->id - lima_ip_pp0); + } + + dlbu_write(LIMA_DLBU_PP_ENABLE_MASK, mask); +} + +void lima_dlbu_disable(struct lima_device *dev) +{ + struct lima_ip *ip = dev->ip + lima_ip_dlbu; + + dlbu_write(LIMA_DLBU_PP_ENABLE_MASK, 0); +} + +void lima_dlbu_set_reg(struct lima_ip *ip, u32 *reg) +{ + dlbu_write(LIMA_DLBU_TLLIST_VBASEADDR, reg[0]); + dlbu_write(LIMA_DLBU_FB_DIM, reg[1]); + dlbu_write(LIMA_DLBU_TLLIST_CONF, reg[2]); + dlbu_write(LIMA_DLBU_START_TILE_POS, reg[3]); +} + +int lima_dlbu_init(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + + dlbu_write(LIMA_DLBU_MASTER_TLLIST_PHYS_ADDR, dev->dlbu_dma | 1); + dlbu_write(LIMA_DLBU_MASTER_TLLIST_VADDR, LIMA_VA_RESERVE_DLBU); + + return 0; +} + +void lima_dlbu_fini(struct lima_ip *ip) +{ + +} diff --git a/drivers/gpu/drm/lima/lima_dlbu.h b/drivers/gpu/drm/lima/lima_dlbu.h new file mode 100644 index 000000000000..16f877984466 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_dlbu.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_DLBU_H__ +#define __LIMA_DLBU_H__ + +struct lima_ip; +struct lima_device; + +void lima_dlbu_enable(struct lima_device *dev, int num_pp); +void lima_dlbu_disable(struct lima_device *dev); + +void lima_dlbu_set_reg(struct lima_ip *ip, u32 *reg); + +int lima_dlbu_init(struct lima_ip *ip); +void lima_dlbu_fini(struct lima_ip *ip); + +#endif diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c new file mode 100644 index 000000000000..f9a281a62083 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_drv.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/module.h> +#include <linux/of_platform.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <drm/drm_ioctl.h> +#include <drm/drm_drv.h> +#include <drm/drm_prime.h> +#include <drm/lima_drm.h> + +#include "lima_drv.h" +#include "lima_gem.h" +#include "lima_gem_prime.h" +#include "lima_vm.h" + +int lima_sched_timeout_ms; + +MODULE_PARM_DESC(sched_timeout_ms, "task run timeout in ms (0 = no timeout (default))"); +module_param_named(sched_timeout_ms, lima_sched_timeout_ms, int, 0444); + +static int lima_ioctl_get_param(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_lima_get_param *args = data; + struct lima_device *ldev = to_lima_dev(dev); + + if (args->pad) + return -EINVAL; + + switch (args->param) { + case DRM_LIMA_PARAM_GPU_ID: + switch (ldev->id) { + case lima_gpu_mali400: + args->value = DRM_LIMA_PARAM_GPU_ID_MALI400; + break; + case lima_gpu_mali450: + args->value = DRM_LIMA_PARAM_GPU_ID_MALI450; + break; + default: + args->value = DRM_LIMA_PARAM_GPU_ID_UNKNOWN; + break; + } + break; + + case DRM_LIMA_PARAM_NUM_PP: + args->value = ldev->pipe[lima_pipe_pp].num_processor; + break; + + case DRM_LIMA_PARAM_GP_VERSION: + args->value = ldev->gp_version; + break; + + case DRM_LIMA_PARAM_PP_VERSION: + args->value = ldev->pp_version; + break; + + default: + return -EINVAL; + } + + return 0; +} + +static int lima_ioctl_gem_create(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_lima_gem_create *args = data; + + if (args->pad) + return -EINVAL; + + if (args->flags) + return -EINVAL; + + if (args->size == 0) + return -EINVAL; + + return lima_gem_create_handle(dev, file, args->size, args->flags, &args->handle); +} + +static int lima_ioctl_gem_info(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_lima_gem_info *args = data; + + return lima_gem_get_info(file, args->handle, &args->va, &args->offset); +} + +static int lima_ioctl_gem_submit(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_lima_gem_submit *args = data; + struct lima_device *ldev = to_lima_dev(dev); + struct lima_drm_priv *priv = file->driver_priv; + struct drm_lima_gem_submit_bo *bos; + struct lima_sched_pipe *pipe; + struct lima_sched_task *task; + struct lima_ctx *ctx; + struct lima_submit submit = {0}; + size_t size; + int err = 0; + + if (args->pipe >= lima_pipe_num || args->nr_bos == 0) + return -EINVAL; + + if (args->flags & ~(LIMA_SUBMIT_FLAG_EXPLICIT_FENCE)) + return -EINVAL; + + pipe = ldev->pipe + args->pipe; + if (args->frame_size != pipe->frame_size) + return -EINVAL; + + bos = kvcalloc(args->nr_bos, sizeof(*submit.bos) + sizeof(*submit.lbos), GFP_KERNEL); + if (!bos) + return -ENOMEM; + + size = args->nr_bos * sizeof(*submit.bos); + if (copy_from_user(bos, u64_to_user_ptr(args->bos), size)) { + err = -EFAULT; + goto out0; + } + + task = kmem_cache_zalloc(pipe->task_slab, GFP_KERNEL); + if (!task) { + err = -ENOMEM; + goto out0; + } + + task->frame = task + 1; + if (copy_from_user(task->frame, u64_to_user_ptr(args->frame), args->frame_size)) { + err = -EFAULT; + goto out1; + } + + err = pipe->task_validate(pipe, task); + if (err) + goto out1; + + ctx = lima_ctx_get(&priv->ctx_mgr, args->ctx); + if (!ctx) { + err = -ENOENT; + goto out1; + } + + submit.pipe = args->pipe; + submit.bos = bos; + submit.lbos = (void *)bos + size; + submit.nr_bos = args->nr_bos; + submit.task = task; + submit.ctx = ctx; + submit.flags = args->flags; + submit.in_sync[0] = args->in_sync[0]; + submit.in_sync[1] = args->in_sync[1]; + submit.out_sync = args->out_sync; + + err = lima_gem_submit(file, &submit); + + lima_ctx_put(ctx); +out1: + if (err) + kmem_cache_free(pipe->task_slab, task); +out0: + kvfree(bos); + return err; +} + +static int lima_ioctl_gem_wait(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_lima_gem_wait *args = data; + + if (args->op & ~(LIMA_GEM_WAIT_READ|LIMA_GEM_WAIT_WRITE)) + return -EINVAL; + + return lima_gem_wait(file, args->handle, args->op, args->timeout_ns); +} + +static int lima_ioctl_ctx_create(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_lima_ctx_create *args = data; + struct lima_drm_priv *priv = file->driver_priv; + struct lima_device *ldev = to_lima_dev(dev); + + if (args->_pad) + return -EINVAL; + + return lima_ctx_create(ldev, &priv->ctx_mgr, &args->id); +} + +static int lima_ioctl_ctx_free(struct drm_device *dev, void *data, struct drm_file *file) +{ + struct drm_lima_ctx_create *args = data; + struct lima_drm_priv *priv = file->driver_priv; + + if (args->_pad) + return -EINVAL; + + return lima_ctx_free(&priv->ctx_mgr, args->id); +} + +static int lima_drm_driver_open(struct drm_device *dev, struct drm_file *file) +{ + int err; + struct lima_drm_priv *priv; + struct lima_device *ldev = to_lima_dev(dev); + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->vm = lima_vm_create(ldev); + if (!priv->vm) { + err = -ENOMEM; + goto err_out0; + } + + lima_ctx_mgr_init(&priv->ctx_mgr); + + file->driver_priv = priv; + return 0; + +err_out0: + kfree(priv); + return err; +} + +static void lima_drm_driver_postclose(struct drm_device *dev, struct drm_file *file) +{ + struct lima_drm_priv *priv = file->driver_priv; + + lima_ctx_mgr_fini(&priv->ctx_mgr); + lima_vm_put(priv->vm); + kfree(priv); +} + +static const struct drm_ioctl_desc lima_drm_driver_ioctls[] = { + DRM_IOCTL_DEF_DRV(LIMA_GET_PARAM, lima_ioctl_get_param, DRM_AUTH|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(LIMA_GEM_CREATE, lima_ioctl_gem_create, DRM_AUTH|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(LIMA_GEM_INFO, lima_ioctl_gem_info, DRM_AUTH|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(LIMA_GEM_SUBMIT, lima_ioctl_gem_submit, DRM_AUTH|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(LIMA_GEM_WAIT, lima_ioctl_gem_wait, DRM_AUTH|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(LIMA_CTX_CREATE, lima_ioctl_ctx_create, DRM_AUTH|DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(LIMA_CTX_FREE, lima_ioctl_ctx_free, DRM_AUTH|DRM_RENDER_ALLOW), +}; + +static const struct file_operations lima_drm_driver_fops = { + .owner = THIS_MODULE, + .open = drm_open, + .release = drm_release, + .unlocked_ioctl = drm_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = drm_compat_ioctl, +#endif + .mmap = lima_gem_mmap, +}; + +static struct drm_driver lima_drm_driver = { + .driver_features = DRIVER_RENDER | DRIVER_GEM | DRIVER_PRIME | DRIVER_SYNCOBJ, + .open = lima_drm_driver_open, + .postclose = lima_drm_driver_postclose, + .ioctls = lima_drm_driver_ioctls, + .num_ioctls = ARRAY_SIZE(lima_drm_driver_ioctls), + .fops = &lima_drm_driver_fops, + .gem_free_object_unlocked = lima_gem_free_object, + .gem_open_object = lima_gem_object_open, + .gem_close_object = lima_gem_object_close, + .gem_vm_ops = &lima_gem_vm_ops, + .name = "lima", + .desc = "lima DRM", + .date = "20190217", + .major = 1, + .minor = 0, + .patchlevel = 0, + + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, + .gem_prime_import_sg_table = lima_gem_prime_import_sg_table, + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .gem_prime_get_sg_table = lima_gem_prime_get_sg_table, + .gem_prime_mmap = lima_gem_prime_mmap, +}; + +static int lima_pdev_probe(struct platform_device *pdev) +{ + struct lima_device *ldev; + struct drm_device *ddev; + int err; + + err = lima_sched_slab_init(); + if (err) + return err; + + ldev = devm_kzalloc(&pdev->dev, sizeof(*ldev), GFP_KERNEL); + if (!ldev) { + err = -ENOMEM; + goto err_out0; + } + + ldev->pdev = pdev; + ldev->dev = &pdev->dev; + ldev->id = (enum lima_gpu_id)of_device_get_match_data(&pdev->dev); + + platform_set_drvdata(pdev, ldev); + + /* Allocate and initialize the DRM device. */ + ddev = drm_dev_alloc(&lima_drm_driver, &pdev->dev); + if (IS_ERR(ddev)) + return PTR_ERR(ddev); + + ddev->dev_private = ldev; + ldev->ddev = ddev; + + err = lima_device_init(ldev); + if (err) { + dev_err(&pdev->dev, "Fatal error during GPU init\n"); + goto err_out1; + } + + /* + * Register the DRM device with the core and the connectors with + * sysfs. + */ + err = drm_dev_register(ddev, 0); + if (err < 0) + goto err_out2; + + return 0; + +err_out2: + lima_device_fini(ldev); +err_out1: + drm_dev_put(ddev); +err_out0: + lima_sched_slab_fini(); + return err; +} + +static int lima_pdev_remove(struct platform_device *pdev) +{ + struct lima_device *ldev = platform_get_drvdata(pdev); + struct drm_device *ddev = ldev->ddev; + + drm_dev_unregister(ddev); + lima_device_fini(ldev); + drm_dev_put(ddev); + lima_sched_slab_fini(); + return 0; +} + +static const struct of_device_id dt_match[] = { + { .compatible = "arm,mali-400", .data = (void *)lima_gpu_mali400 }, + { .compatible = "arm,mali-450", .data = (void *)lima_gpu_mali450 }, + {} +}; +MODULE_DEVICE_TABLE(of, dt_match); + +static struct platform_driver lima_platform_driver = { + .probe = lima_pdev_probe, + .remove = lima_pdev_remove, + .driver = { + .name = "lima", + .of_match_table = dt_match, + }, +}; + +static int __init lima_init(void) +{ + return platform_driver_register(&lima_platform_driver); +} +module_init(lima_init); + +static void __exit lima_exit(void) +{ + platform_driver_unregister(&lima_platform_driver); +} +module_exit(lima_exit); + +MODULE_AUTHOR("Lima Project Developers"); +MODULE_DESCRIPTION("Lima DRM Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/lima/lima_drv.h b/drivers/gpu/drm/lima/lima_drv.h new file mode 100644 index 000000000000..69c7344715c9 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_drv.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_DRV_H__ +#define __LIMA_DRV_H__ + +#include <drm/drm_file.h> + +#include "lima_ctx.h" + +extern int lima_sched_timeout_ms; + +struct lima_vm; +struct lima_bo; +struct lima_sched_task; + +struct drm_lima_gem_submit_bo; + +struct lima_drm_priv { + struct lima_vm *vm; + struct lima_ctx_mgr ctx_mgr; +}; + +struct lima_submit { + struct lima_ctx *ctx; + int pipe; + u32 flags; + + struct drm_lima_gem_submit_bo *bos; + struct lima_bo **lbos; + u32 nr_bos; + + u32 in_sync[2]; + u32 out_sync; + + struct lima_sched_task *task; +}; + +static inline struct lima_drm_priv * +to_lima_drm_priv(struct drm_file *file) +{ + return file->driver_priv; +} + +#endif diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c new file mode 100644 index 000000000000..2d3cf96f6c58 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -0,0 +1,381 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/sync_file.h> +#include <linux/pfn_t.h> + +#include <drm/drm_file.h> +#include <drm/drm_syncobj.h> +#include <drm/drm_utils.h> + +#include <drm/lima_drm.h> + +#include "lima_drv.h" +#include "lima_gem.h" +#include "lima_gem_prime.h" +#include "lima_vm.h" +#include "lima_object.h" + +int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file, + u32 size, u32 flags, u32 *handle) +{ + int err; + struct lima_bo *bo; + struct lima_device *ldev = to_lima_dev(dev); + + bo = lima_bo_create(ldev, size, flags, NULL, NULL); + if (IS_ERR(bo)) + return PTR_ERR(bo); + + err = drm_gem_handle_create(file, &bo->gem, handle); + + /* drop reference from allocate - handle holds it now */ + drm_gem_object_put_unlocked(&bo->gem); + + return err; +} + +void lima_gem_free_object(struct drm_gem_object *obj) +{ + struct lima_bo *bo = to_lima_bo(obj); + + if (!list_empty(&bo->va)) + dev_err(obj->dev->dev, "lima gem free bo still has va\n"); + + lima_bo_destroy(bo); +} + +int lima_gem_object_open(struct drm_gem_object *obj, struct drm_file *file) +{ + struct lima_bo *bo = to_lima_bo(obj); + struct lima_drm_priv *priv = to_lima_drm_priv(file); + struct lima_vm *vm = priv->vm; + + return lima_vm_bo_add(vm, bo, true); +} + +void lima_gem_object_close(struct drm_gem_object *obj, struct drm_file *file) +{ + struct lima_bo *bo = to_lima_bo(obj); + struct lima_drm_priv *priv = to_lima_drm_priv(file); + struct lima_vm *vm = priv->vm; + + lima_vm_bo_del(vm, bo); +} + +int lima_gem_get_info(struct drm_file *file, u32 handle, u32 *va, u64 *offset) +{ + struct drm_gem_object *obj; + struct lima_bo *bo; + struct lima_drm_priv *priv = to_lima_drm_priv(file); + struct lima_vm *vm = priv->vm; + int err; + + obj = drm_gem_object_lookup(file, handle); + if (!obj) + return -ENOENT; + + bo = to_lima_bo(obj); + + *va = lima_vm_get_va(vm, bo); + + err = drm_gem_create_mmap_offset(obj); + if (!err) + *offset = drm_vma_node_offset_addr(&obj->vma_node); + + drm_gem_object_put_unlocked(obj); + return err; +} + +static vm_fault_t lima_gem_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct drm_gem_object *obj = vma->vm_private_data; + struct lima_bo *bo = to_lima_bo(obj); + pfn_t pfn; + pgoff_t pgoff; + + /* We don't use vmf->pgoff since that has the fake offset: */ + pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT; + pfn = __pfn_to_pfn_t(page_to_pfn(bo->pages[pgoff]), PFN_DEV); + + return vmf_insert_mixed(vma, vmf->address, pfn); +} + +const struct vm_operations_struct lima_gem_vm_ops = { + .fault = lima_gem_fault, + .open = drm_gem_vm_open, + .close = drm_gem_vm_close, +}; + +void lima_set_vma_flags(struct vm_area_struct *vma) +{ + pgprot_t prot = vm_get_page_prot(vma->vm_flags); + + vma->vm_flags |= VM_MIXEDMAP; + vma->vm_flags &= ~VM_PFNMAP; + vma->vm_page_prot = pgprot_writecombine(prot); +} + +int lima_gem_mmap(struct file *filp, struct vm_area_struct *vma) +{ + int ret; + + ret = drm_gem_mmap(filp, vma); + if (ret) + return ret; + + lima_set_vma_flags(vma); + return 0; +} + +static int lima_gem_sync_bo(struct lima_sched_task *task, struct lima_bo *bo, + bool write, bool explicit) +{ + int err = 0; + + if (!write) { + err = reservation_object_reserve_shared(bo->gem.resv, 1); + if (err) + return err; + } + + /* explicit sync use user passed dep fence */ + if (explicit) + return 0; + + /* implicit sync use bo fence in resv obj */ + if (write) { + unsigned nr_fences; + struct dma_fence **fences; + int i; + + err = reservation_object_get_fences_rcu( + bo->gem.resv, NULL, &nr_fences, &fences); + if (err || !nr_fences) + return err; + + for (i = 0; i < nr_fences; i++) { + err = lima_sched_task_add_dep(task, fences[i]); + if (err) + break; + } + + /* for error case free remaining fences */ + for ( ; i < nr_fences; i++) + dma_fence_put(fences[i]); + + kfree(fences); + } else { + struct dma_fence *fence; + + fence = reservation_object_get_excl_rcu(bo->gem.resv); + if (fence) { + err = lima_sched_task_add_dep(task, fence); + if (err) + dma_fence_put(fence); + } + } + + return err; +} + +static int lima_gem_lock_bos(struct lima_bo **bos, u32 nr_bos, + struct ww_acquire_ctx *ctx) +{ + int i, ret = 0, contended, slow_locked = -1; + + ww_acquire_init(ctx, &reservation_ww_class); + +retry: + for (i = 0; i < nr_bos; i++) { + if (i == slow_locked) { + slow_locked = -1; + continue; + } + + ret = ww_mutex_lock_interruptible(&bos[i]->gem.resv->lock, ctx); + if (ret < 0) { + contended = i; + goto err; + } + } + + ww_acquire_done(ctx); + return 0; + +err: + for (i--; i >= 0; i--) + ww_mutex_unlock(&bos[i]->gem.resv->lock); + + if (slow_locked >= 0) + ww_mutex_unlock(&bos[slow_locked]->gem.resv->lock); + + if (ret == -EDEADLK) { + /* we lost out in a seqno race, lock and retry.. */ + ret = ww_mutex_lock_slow_interruptible( + &bos[contended]->gem.resv->lock, ctx); + if (!ret) { + slow_locked = contended; + goto retry; + } + } + ww_acquire_fini(ctx); + + return ret; +} + +static void lima_gem_unlock_bos(struct lima_bo **bos, u32 nr_bos, + struct ww_acquire_ctx *ctx) +{ + int i; + + for (i = 0; i < nr_bos; i++) + ww_mutex_unlock(&bos[i]->gem.resv->lock); + ww_acquire_fini(ctx); +} + +static int lima_gem_add_deps(struct drm_file *file, struct lima_submit *submit) +{ + int i, err; + + for (i = 0; i < ARRAY_SIZE(submit->in_sync); i++) { + struct dma_fence *fence = NULL; + + if (!submit->in_sync[i]) + continue; + + err = drm_syncobj_find_fence(file, submit->in_sync[i], + 0, 0, &fence); + if (err) + return err; + + err = lima_sched_task_add_dep(submit->task, fence); + if (err) { + dma_fence_put(fence); + return err; + } + } + + return 0; +} + +int lima_gem_submit(struct drm_file *file, struct lima_submit *submit) +{ + int i, err = 0; + struct ww_acquire_ctx ctx; + struct lima_drm_priv *priv = to_lima_drm_priv(file); + struct lima_vm *vm = priv->vm; + struct drm_syncobj *out_sync = NULL; + struct dma_fence *fence; + struct lima_bo **bos = submit->lbos; + + if (submit->out_sync) { + out_sync = drm_syncobj_find(file, submit->out_sync); + if (!out_sync) + return -ENOENT; + } + + for (i = 0; i < submit->nr_bos; i++) { + struct drm_gem_object *obj; + struct lima_bo *bo; + + obj = drm_gem_object_lookup(file, submit->bos[i].handle); + if (!obj) { + err = -ENOENT; + goto err_out0; + } + + bo = to_lima_bo(obj); + + /* increase refcnt of gpu va map to prevent unmapped when executing, + * will be decreased when task done + */ + err = lima_vm_bo_add(vm, bo, false); + if (err) { + drm_gem_object_put_unlocked(obj); + goto err_out0; + } + + bos[i] = bo; + } + + err = lima_gem_lock_bos(bos, submit->nr_bos, &ctx); + if (err) + goto err_out0; + + err = lima_sched_task_init( + submit->task, submit->ctx->context + submit->pipe, + bos, submit->nr_bos, vm); + if (err) + goto err_out1; + + err = lima_gem_add_deps(file, submit); + if (err) + goto err_out2; + + for (i = 0; i < submit->nr_bos; i++) { + err = lima_gem_sync_bo( + submit->task, bos[i], + submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE, + submit->flags & LIMA_SUBMIT_FLAG_EXPLICIT_FENCE); + if (err) + goto err_out2; + } + + fence = lima_sched_context_queue_task( + submit->ctx->context + submit->pipe, submit->task); + + for (i = 0; i < submit->nr_bos; i++) { + if (submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE) + reservation_object_add_excl_fence(bos[i]->gem.resv, fence); + else + reservation_object_add_shared_fence(bos[i]->gem.resv, fence); + } + + lima_gem_unlock_bos(bos, submit->nr_bos, &ctx); + + for (i = 0; i < submit->nr_bos; i++) + drm_gem_object_put_unlocked(&bos[i]->gem); + + if (out_sync) { + drm_syncobj_replace_fence(out_sync, fence); + drm_syncobj_put(out_sync); + } + + dma_fence_put(fence); + + return 0; + +err_out2: + lima_sched_task_fini(submit->task); +err_out1: + lima_gem_unlock_bos(bos, submit->nr_bos, &ctx); +err_out0: + for (i = 0; i < submit->nr_bos; i++) { + if (!bos[i]) + break; + lima_vm_bo_del(vm, bos[i]); + drm_gem_object_put_unlocked(&bos[i]->gem); + } + if (out_sync) + drm_syncobj_put(out_sync); + return err; +} + +int lima_gem_wait(struct drm_file *file, u32 handle, u32 op, s64 timeout_ns) +{ + bool write = op & LIMA_GEM_WAIT_WRITE; + long ret, timeout; + + if (!op) + return 0; + + timeout = drm_timeout_abs_to_jiffies(timeout_ns); + + ret = drm_gem_reservation_object_wait(file, handle, write, timeout); + if (ret == 0) + ret = timeout ? -ETIMEDOUT : -EBUSY; + + return ret; +} diff --git a/drivers/gpu/drm/lima/lima_gem.h b/drivers/gpu/drm/lima/lima_gem.h new file mode 100644 index 000000000000..556111a01135 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_gem.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_GEM_H__ +#define __LIMA_GEM_H__ + +struct lima_bo; +struct lima_submit; + +extern const struct vm_operations_struct lima_gem_vm_ops; + +struct lima_bo *lima_gem_create_bo(struct drm_device *dev, u32 size, u32 flags); +int lima_gem_create_handle(struct drm_device *dev, struct drm_file *file, + u32 size, u32 flags, u32 *handle); +void lima_gem_free_object(struct drm_gem_object *obj); +int lima_gem_object_open(struct drm_gem_object *obj, struct drm_file *file); +void lima_gem_object_close(struct drm_gem_object *obj, struct drm_file *file); +int lima_gem_get_info(struct drm_file *file, u32 handle, u32 *va, u64 *offset); +int lima_gem_mmap(struct file *filp, struct vm_area_struct *vma); +int lima_gem_submit(struct drm_file *file, struct lima_submit *submit); +int lima_gem_wait(struct drm_file *file, u32 handle, u32 op, s64 timeout_ns); + +void lima_set_vma_flags(struct vm_area_struct *vma); + +#endif diff --git a/drivers/gpu/drm/lima/lima_gem_prime.c b/drivers/gpu/drm/lima/lima_gem_prime.c new file mode 100644 index 000000000000..9c6d9f1dba55 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_gem_prime.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/dma-buf.h> +#include <drm/drm_prime.h> +#include <drm/drm_drv.h> +#include <drm/drm_file.h> + +#include "lima_device.h" +#include "lima_object.h" +#include "lima_gem.h" +#include "lima_gem_prime.h" + +struct drm_gem_object *lima_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *sgt) +{ + struct lima_device *ldev = to_lima_dev(dev); + struct lima_bo *bo; + + bo = lima_bo_create(ldev, attach->dmabuf->size, 0, sgt, + attach->dmabuf->resv); + if (IS_ERR(bo)) + return ERR_CAST(bo); + + return &bo->gem; +} + +struct sg_table *lima_gem_prime_get_sg_table(struct drm_gem_object *obj) +{ + struct lima_bo *bo = to_lima_bo(obj); + int npages = obj->size >> PAGE_SHIFT; + + return drm_prime_pages_to_sg(bo->pages, npages); +} + +int lima_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) +{ + int ret; + + ret = drm_gem_mmap_obj(obj, obj->size, vma); + if (ret) + return ret; + + lima_set_vma_flags(vma); + return 0; +} diff --git a/drivers/gpu/drm/lima/lima_gem_prime.h b/drivers/gpu/drm/lima/lima_gem_prime.h new file mode 100644 index 000000000000..34b4d35c21e3 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_gem_prime.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_GEM_PRIME_H__ +#define __LIMA_GEM_PRIME_H__ + +struct drm_gem_object *lima_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *sgt); +struct sg_table *lima_gem_prime_get_sg_table(struct drm_gem_object *obj); +int lima_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma); + +#endif diff --git a/drivers/gpu/drm/lima/lima_gp.c b/drivers/gpu/drm/lima/lima_gp.c new file mode 100644 index 000000000000..ccf49faedebf --- /dev/null +++ b/drivers/gpu/drm/lima/lima_gp.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/device.h> +#include <linux/slab.h> + +#include <drm/lima_drm.h> + +#include "lima_device.h" +#include "lima_gp.h" +#include "lima_regs.h" + +#define gp_write(reg, data) writel(data, ip->iomem + reg) +#define gp_read(reg) readl(ip->iomem + reg) + +static irqreturn_t lima_gp_irq_handler(int irq, void *data) +{ + struct lima_ip *ip = data; + struct lima_device *dev = ip->dev; + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp; + u32 state = gp_read(LIMA_GP_INT_STAT); + u32 status = gp_read(LIMA_GP_STATUS); + bool done = false; + + /* for shared irq case */ + if (!state) + return IRQ_NONE; + + if (state & LIMA_GP_IRQ_MASK_ERROR) { + dev_err(dev->dev, "gp error irq state=%x status=%x\n", + state, status); + + /* mask all interrupts before hard reset */ + gp_write(LIMA_GP_INT_MASK, 0); + + pipe->error = true; + done = true; + } else { + bool valid = state & (LIMA_GP_IRQ_VS_END_CMD_LST | + LIMA_GP_IRQ_PLBU_END_CMD_LST); + bool active = status & (LIMA_GP_STATUS_VS_ACTIVE | + LIMA_GP_STATUS_PLBU_ACTIVE); + done = valid && !active; + } + + gp_write(LIMA_GP_INT_CLEAR, state); + + if (done) + lima_sched_pipe_task_done(pipe); + + return IRQ_HANDLED; +} + +static void lima_gp_soft_reset_async(struct lima_ip *ip) +{ + if (ip->data.async_reset) + return; + + gp_write(LIMA_GP_INT_MASK, 0); + gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_RESET_COMPLETED); + gp_write(LIMA_GP_CMD, LIMA_GP_CMD_SOFT_RESET); + ip->data.async_reset = true; +} + +static int lima_gp_soft_reset_async_wait(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int err; + u32 v; + + if (!ip->data.async_reset) + return 0; + + err = readl_poll_timeout(ip->iomem + LIMA_GP_INT_RAWSTAT, v, + v & LIMA_GP_IRQ_RESET_COMPLETED, + 0, 100); + if (err) { + dev_err(dev->dev, "gp soft reset time out\n"); + return err; + } + + gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_MASK_ALL); + gp_write(LIMA_GP_INT_MASK, LIMA_GP_IRQ_MASK_USED); + + ip->data.async_reset = false; + return 0; +} + +static int lima_gp_task_validate(struct lima_sched_pipe *pipe, + struct lima_sched_task *task) +{ + struct drm_lima_gp_frame *frame = task->frame; + u32 *f = frame->frame; + (void)pipe; + + if (f[LIMA_GP_VSCL_START_ADDR >> 2] > + f[LIMA_GP_VSCL_END_ADDR >> 2] || + f[LIMA_GP_PLBUCL_START_ADDR >> 2] > + f[LIMA_GP_PLBUCL_END_ADDR >> 2] || + f[LIMA_GP_PLBU_ALLOC_START_ADDR >> 2] > + f[LIMA_GP_PLBU_ALLOC_END_ADDR >> 2]) + return -EINVAL; + + if (f[LIMA_GP_VSCL_START_ADDR >> 2] == + f[LIMA_GP_VSCL_END_ADDR >> 2] && + f[LIMA_GP_PLBUCL_START_ADDR >> 2] == + f[LIMA_GP_PLBUCL_END_ADDR >> 2]) + return -EINVAL; + + return 0; +} + +static void lima_gp_task_run(struct lima_sched_pipe *pipe, + struct lima_sched_task *task) +{ + struct lima_ip *ip = pipe->processor[0]; + struct drm_lima_gp_frame *frame = task->frame; + u32 *f = frame->frame; + u32 cmd = 0; + int i; + + if (f[LIMA_GP_VSCL_START_ADDR >> 2] != + f[LIMA_GP_VSCL_END_ADDR >> 2]) + cmd |= LIMA_GP_CMD_START_VS; + if (f[LIMA_GP_PLBUCL_START_ADDR >> 2] != + f[LIMA_GP_PLBUCL_END_ADDR >> 2]) + cmd |= LIMA_GP_CMD_START_PLBU; + + /* before any hw ops, wait last success task async soft reset */ + lima_gp_soft_reset_async_wait(ip); + + for (i = 0; i < LIMA_GP_FRAME_REG_NUM; i++) + writel(f[i], ip->iomem + LIMA_GP_VSCL_START_ADDR + i * 4); + + gp_write(LIMA_GP_CMD, LIMA_GP_CMD_UPDATE_PLBU_ALLOC); + gp_write(LIMA_GP_CMD, cmd); +} + +static int lima_gp_hard_reset_poll(struct lima_ip *ip) +{ + gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC01A0000); + return gp_read(LIMA_GP_PERF_CNT_0_LIMIT) == 0xC01A0000; +} + +static int lima_gp_hard_reset(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int ret; + + gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC0FFE000); + gp_write(LIMA_GP_INT_MASK, 0); + gp_write(LIMA_GP_CMD, LIMA_GP_CMD_RESET); + ret = lima_poll_timeout(ip, lima_gp_hard_reset_poll, 10, 100); + if (ret) { + dev_err(dev->dev, "gp hard reset timeout\n"); + return ret; + } + + gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0); + gp_write(LIMA_GP_INT_CLEAR, LIMA_GP_IRQ_MASK_ALL); + gp_write(LIMA_GP_INT_MASK, LIMA_GP_IRQ_MASK_USED); + return 0; +} + +static void lima_gp_task_fini(struct lima_sched_pipe *pipe) +{ + lima_gp_soft_reset_async(pipe->processor[0]); +} + +static void lima_gp_task_error(struct lima_sched_pipe *pipe) +{ + struct lima_ip *ip = pipe->processor[0]; + + dev_err(ip->dev->dev, "gp task error int_state=%x status=%x\n", + gp_read(LIMA_GP_INT_STAT), gp_read(LIMA_GP_STATUS)); + + lima_gp_hard_reset(ip); +} + +static void lima_gp_task_mmu_error(struct lima_sched_pipe *pipe) +{ + lima_sched_pipe_task_done(pipe); +} + +static void lima_gp_print_version(struct lima_ip *ip) +{ + u32 version, major, minor; + char *name; + + version = gp_read(LIMA_GP_VERSION); + major = (version >> 8) & 0xFF; + minor = version & 0xFF; + switch (version >> 16) { + case 0xA07: + name = "mali200"; + break; + case 0xC07: + name = "mali300"; + break; + case 0xB07: + name = "mali400"; + break; + case 0xD07: + name = "mali450"; + break; + default: + name = "unknown"; + break; + } + dev_info(ip->dev->dev, "%s - %s version major %d minor %d\n", + lima_ip_name(ip), name, major, minor); +} + +static struct kmem_cache *lima_gp_task_slab; +static int lima_gp_task_slab_refcnt; + +int lima_gp_init(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int err; + + lima_gp_print_version(ip); + + ip->data.async_reset = false; + lima_gp_soft_reset_async(ip); + err = lima_gp_soft_reset_async_wait(ip); + if (err) + return err; + + err = devm_request_irq(dev->dev, ip->irq, lima_gp_irq_handler, + IRQF_SHARED, lima_ip_name(ip), ip); + if (err) { + dev_err(dev->dev, "gp %s fail to request irq\n", + lima_ip_name(ip)); + return err; + } + + dev->gp_version = gp_read(LIMA_GP_VERSION); + + return 0; +} + +void lima_gp_fini(struct lima_ip *ip) +{ + +} + +int lima_gp_pipe_init(struct lima_device *dev) +{ + int frame_size = sizeof(struct drm_lima_gp_frame); + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_gp; + + if (!lima_gp_task_slab) { + lima_gp_task_slab = kmem_cache_create_usercopy( + "lima_gp_task", sizeof(struct lima_sched_task) + frame_size, + 0, SLAB_HWCACHE_ALIGN, sizeof(struct lima_sched_task), + frame_size, NULL); + if (!lima_gp_task_slab) + return -ENOMEM; + } + lima_gp_task_slab_refcnt++; + + pipe->frame_size = frame_size; + pipe->task_slab = lima_gp_task_slab; + + pipe->task_validate = lima_gp_task_validate; + pipe->task_run = lima_gp_task_run; + pipe->task_fini = lima_gp_task_fini; + pipe->task_error = lima_gp_task_error; + pipe->task_mmu_error = lima_gp_task_mmu_error; + + return 0; +} + +void lima_gp_pipe_fini(struct lima_device *dev) +{ + if (!--lima_gp_task_slab_refcnt) { + kmem_cache_destroy(lima_gp_task_slab); + lima_gp_task_slab = NULL; + } +} diff --git a/drivers/gpu/drm/lima/lima_gp.h b/drivers/gpu/drm/lima/lima_gp.h new file mode 100644 index 000000000000..516e5c1babbb --- /dev/null +++ b/drivers/gpu/drm/lima/lima_gp.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_GP_H__ +#define __LIMA_GP_H__ + +struct lima_ip; +struct lima_device; + +int lima_gp_init(struct lima_ip *ip); +void lima_gp_fini(struct lima_ip *ip); + +int lima_gp_pipe_init(struct lima_device *dev); +void lima_gp_pipe_fini(struct lima_device *dev); + +#endif diff --git a/drivers/gpu/drm/lima/lima_l2_cache.c b/drivers/gpu/drm/lima/lima_l2_cache.c new file mode 100644 index 000000000000..6873a7af5a5c --- /dev/null +++ b/drivers/gpu/drm/lima/lima_l2_cache.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/iopoll.h> +#include <linux/device.h> + +#include "lima_device.h" +#include "lima_l2_cache.h" +#include "lima_regs.h" + +#define l2_cache_write(reg, data) writel(data, ip->iomem + reg) +#define l2_cache_read(reg) readl(ip->iomem + reg) + +static int lima_l2_cache_wait_idle(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int err; + u32 v; + + err = readl_poll_timeout(ip->iomem + LIMA_L2_CACHE_STATUS, v, + !(v & LIMA_L2_CACHE_STATUS_COMMAND_BUSY), + 0, 1000); + if (err) { + dev_err(dev->dev, "l2 cache wait command timeout\n"); + return err; + } + return 0; +} + +int lima_l2_cache_flush(struct lima_ip *ip) +{ + int ret; + + spin_lock(&ip->data.lock); + l2_cache_write(LIMA_L2_CACHE_COMMAND, LIMA_L2_CACHE_COMMAND_CLEAR_ALL); + ret = lima_l2_cache_wait_idle(ip); + spin_unlock(&ip->data.lock); + return ret; +} + +int lima_l2_cache_init(struct lima_ip *ip) +{ + int i, err; + u32 size; + struct lima_device *dev = ip->dev; + + /* l2_cache2 only exists when one of PP4-7 present */ + if (ip->id == lima_ip_l2_cache2) { + for (i = lima_ip_pp4; i <= lima_ip_pp7; i++) { + if (dev->ip[i].present) + break; + } + if (i > lima_ip_pp7) + return -ENODEV; + } + + spin_lock_init(&ip->data.lock); + + size = l2_cache_read(LIMA_L2_CACHE_SIZE); + dev_info(dev->dev, "l2 cache %uK, %u-way, %ubyte cache line, %ubit external bus\n", + 1 << (((size >> 16) & 0xff) - 10), + 1 << ((size >> 8) & 0xff), + 1 << (size & 0xff), + 1 << ((size >> 24) & 0xff)); + + err = lima_l2_cache_flush(ip); + if (err) + return err; + + l2_cache_write(LIMA_L2_CACHE_ENABLE, + LIMA_L2_CACHE_ENABLE_ACCESS|LIMA_L2_CACHE_ENABLE_READ_ALLOCATE); + l2_cache_write(LIMA_L2_CACHE_MAX_READS, 0x1c); + + return 0; +} + +void lima_l2_cache_fini(struct lima_ip *ip) +{ + +} diff --git a/drivers/gpu/drm/lima/lima_l2_cache.h b/drivers/gpu/drm/lima/lima_l2_cache.h new file mode 100644 index 000000000000..c63fb676ff14 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_l2_cache.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_L2_CACHE_H__ +#define __LIMA_L2_CACHE_H__ + +struct lima_ip; + +int lima_l2_cache_init(struct lima_ip *ip); +void lima_l2_cache_fini(struct lima_ip *ip); + +int lima_l2_cache_flush(struct lima_ip *ip); + +#endif diff --git a/drivers/gpu/drm/lima/lima_mmu.c b/drivers/gpu/drm/lima/lima_mmu.c new file mode 100644 index 000000000000..8e1651d6a61f --- /dev/null +++ b/drivers/gpu/drm/lima/lima_mmu.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/device.h> + +#include "lima_device.h" +#include "lima_mmu.h" +#include "lima_vm.h" +#include "lima_object.h" +#include "lima_regs.h" + +#define mmu_write(reg, data) writel(data, ip->iomem + reg) +#define mmu_read(reg) readl(ip->iomem + reg) + +#define lima_mmu_send_command(cmd, addr, val, cond) \ +({ \ + int __ret; \ + \ + mmu_write(LIMA_MMU_COMMAND, cmd); \ + __ret = readl_poll_timeout(ip->iomem + (addr), val, \ + cond, 0, 100); \ + if (__ret) \ + dev_err(dev->dev, \ + "mmu command %x timeout\n", cmd); \ + __ret; \ +}) + +static irqreturn_t lima_mmu_irq_handler(int irq, void *data) +{ + struct lima_ip *ip = data; + struct lima_device *dev = ip->dev; + u32 status = mmu_read(LIMA_MMU_INT_STATUS); + struct lima_sched_pipe *pipe; + + /* for shared irq case */ + if (!status) + return IRQ_NONE; + + if (status & LIMA_MMU_INT_PAGE_FAULT) { + u32 fault = mmu_read(LIMA_MMU_PAGE_FAULT_ADDR); + + dev_err(dev->dev, "mmu page fault at 0x%x from bus id %d of type %s on %s\n", + fault, LIMA_MMU_STATUS_BUS_ID(status), + status & LIMA_MMU_STATUS_PAGE_FAULT_IS_WRITE ? "write" : "read", + lima_ip_name(ip)); + } + + if (status & LIMA_MMU_INT_READ_BUS_ERROR) + dev_err(dev->dev, "mmu %s irq bus error\n", lima_ip_name(ip)); + + /* mask all interrupts before resume */ + mmu_write(LIMA_MMU_INT_MASK, 0); + mmu_write(LIMA_MMU_INT_CLEAR, status); + + pipe = dev->pipe + (ip->id == lima_ip_gpmmu ? lima_pipe_gp : lima_pipe_pp); + lima_sched_pipe_mmu_error(pipe); + + return IRQ_HANDLED; +} + +int lima_mmu_init(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int err; + u32 v; + + if (ip->id == lima_ip_ppmmu_bcast) + return 0; + + mmu_write(LIMA_MMU_DTE_ADDR, 0xCAFEBABE); + if (mmu_read(LIMA_MMU_DTE_ADDR) != 0xCAFEB000) { + dev_err(dev->dev, "mmu %s dte write test fail\n", lima_ip_name(ip)); + return -EIO; + } + + mmu_write(LIMA_MMU_COMMAND, LIMA_MMU_COMMAND_HARD_RESET); + err = lima_mmu_send_command(LIMA_MMU_COMMAND_HARD_RESET, + LIMA_MMU_DTE_ADDR, v, v == 0); + if (err) + return err; + + err = devm_request_irq(dev->dev, ip->irq, lima_mmu_irq_handler, + IRQF_SHARED, lima_ip_name(ip), ip); + if (err) { + dev_err(dev->dev, "mmu %s fail to request irq\n", lima_ip_name(ip)); + return err; + } + + mmu_write(LIMA_MMU_INT_MASK, LIMA_MMU_INT_PAGE_FAULT | LIMA_MMU_INT_READ_BUS_ERROR); + mmu_write(LIMA_MMU_DTE_ADDR, dev->empty_vm->pd.dma); + return lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_PAGING, + LIMA_MMU_STATUS, v, + v & LIMA_MMU_STATUS_PAGING_ENABLED); +} + +void lima_mmu_fini(struct lima_ip *ip) +{ + +} + +void lima_mmu_switch_vm(struct lima_ip *ip, struct lima_vm *vm) +{ + struct lima_device *dev = ip->dev; + u32 v; + + lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_STALL, + LIMA_MMU_STATUS, v, + v & LIMA_MMU_STATUS_STALL_ACTIVE); + + if (vm) + mmu_write(LIMA_MMU_DTE_ADDR, vm->pd.dma); + + /* flush the TLB */ + mmu_write(LIMA_MMU_COMMAND, LIMA_MMU_COMMAND_ZAP_CACHE); + + lima_mmu_send_command(LIMA_MMU_COMMAND_DISABLE_STALL, + LIMA_MMU_STATUS, v, + !(v & LIMA_MMU_STATUS_STALL_ACTIVE)); +} + +void lima_mmu_page_fault_resume(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + u32 status = mmu_read(LIMA_MMU_STATUS); + u32 v; + + if (status & LIMA_MMU_STATUS_PAGE_FAULT_ACTIVE) { + dev_info(dev->dev, "mmu resume\n"); + + mmu_write(LIMA_MMU_INT_MASK, 0); + mmu_write(LIMA_MMU_DTE_ADDR, 0xCAFEBABE); + lima_mmu_send_command(LIMA_MMU_COMMAND_HARD_RESET, + LIMA_MMU_DTE_ADDR, v, v == 0); + mmu_write(LIMA_MMU_INT_MASK, LIMA_MMU_INT_PAGE_FAULT | LIMA_MMU_INT_READ_BUS_ERROR); + mmu_write(LIMA_MMU_DTE_ADDR, dev->empty_vm->pd.dma); + lima_mmu_send_command(LIMA_MMU_COMMAND_ENABLE_PAGING, + LIMA_MMU_STATUS, v, + v & LIMA_MMU_STATUS_PAGING_ENABLED); + } +} diff --git a/drivers/gpu/drm/lima/lima_mmu.h b/drivers/gpu/drm/lima/lima_mmu.h new file mode 100644 index 000000000000..8c78319bcc8e --- /dev/null +++ b/drivers/gpu/drm/lima/lima_mmu.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_MMU_H__ +#define __LIMA_MMU_H__ + +struct lima_ip; +struct lima_vm; + +int lima_mmu_init(struct lima_ip *ip); +void lima_mmu_fini(struct lima_ip *ip); + +void lima_mmu_switch_vm(struct lima_ip *ip, struct lima_vm *vm); +void lima_mmu_page_fault_resume(struct lima_ip *ip); + +#endif diff --git a/drivers/gpu/drm/lima/lima_object.c b/drivers/gpu/drm/lima/lima_object.c new file mode 100644 index 000000000000..5c41f859a72f --- /dev/null +++ b/drivers/gpu/drm/lima/lima_object.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <drm/drm_prime.h> +#include <linux/pagemap.h> +#include <linux/dma-mapping.h> + +#include "lima_object.h" + +void lima_bo_destroy(struct lima_bo *bo) +{ + if (bo->sgt) { + kfree(bo->pages); + drm_prime_gem_destroy(&bo->gem, bo->sgt); + } else { + if (bo->pages_dma_addr) { + int i, npages = bo->gem.size >> PAGE_SHIFT; + + for (i = 0; i < npages; i++) { + if (bo->pages_dma_addr[i]) + dma_unmap_page(bo->gem.dev->dev, + bo->pages_dma_addr[i], + PAGE_SIZE, DMA_BIDIRECTIONAL); + } + } + + if (bo->pages) + drm_gem_put_pages(&bo->gem, bo->pages, true, true); + } + + kfree(bo->pages_dma_addr); + drm_gem_object_release(&bo->gem); + kfree(bo); +} + +static struct lima_bo *lima_bo_create_struct(struct lima_device *dev, u32 size, u32 flags, + struct reservation_object *resv) +{ + struct lima_bo *bo; + int err; + + size = PAGE_ALIGN(size); + + bo = kzalloc(sizeof(*bo), GFP_KERNEL); + if (!bo) + return ERR_PTR(-ENOMEM); + + mutex_init(&bo->lock); + INIT_LIST_HEAD(&bo->va); + bo->gem.resv = resv; + + err = drm_gem_object_init(dev->ddev, &bo->gem, size); + if (err) { + kfree(bo); + return ERR_PTR(err); + } + + return bo; +} + +struct lima_bo *lima_bo_create(struct lima_device *dev, u32 size, + u32 flags, struct sg_table *sgt, + struct reservation_object *resv) +{ + int i, err; + size_t npages; + struct lima_bo *bo, *ret; + + bo = lima_bo_create_struct(dev, size, flags, resv); + if (IS_ERR(bo)) + return bo; + + npages = bo->gem.size >> PAGE_SHIFT; + + bo->pages_dma_addr = kcalloc(npages, sizeof(dma_addr_t), GFP_KERNEL); + if (!bo->pages_dma_addr) { + ret = ERR_PTR(-ENOMEM); + goto err_out; + } + + if (sgt) { + bo->sgt = sgt; + + bo->pages = kcalloc(npages, sizeof(*bo->pages), GFP_KERNEL); + if (!bo->pages) { + ret = ERR_PTR(-ENOMEM); + goto err_out; + } + + err = drm_prime_sg_to_page_addr_arrays( + sgt, bo->pages, bo->pages_dma_addr, npages); + if (err) { + ret = ERR_PTR(err); + goto err_out; + } + } else { + mapping_set_gfp_mask(bo->gem.filp->f_mapping, GFP_DMA32); + bo->pages = drm_gem_get_pages(&bo->gem); + if (IS_ERR(bo->pages)) { + ret = ERR_CAST(bo->pages); + bo->pages = NULL; + goto err_out; + } + + for (i = 0; i < npages; i++) { + dma_addr_t addr = dma_map_page(dev->dev, bo->pages[i], 0, + PAGE_SIZE, DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev->dev, addr)) { + ret = ERR_PTR(-EFAULT); + goto err_out; + } + bo->pages_dma_addr[i] = addr; + } + + } + + return bo; + +err_out: + lima_bo_destroy(bo); + return ret; +} diff --git a/drivers/gpu/drm/lima/lima_object.h b/drivers/gpu/drm/lima/lima_object.h new file mode 100644 index 000000000000..6738724afb7b --- /dev/null +++ b/drivers/gpu/drm/lima/lima_object.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2018-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_OBJECT_H__ +#define __LIMA_OBJECT_H__ + +#include <drm/drm_gem.h> + +#include "lima_device.h" + +struct lima_bo { + struct drm_gem_object gem; + + struct page **pages; + dma_addr_t *pages_dma_addr; + struct sg_table *sgt; + void *vaddr; + + struct mutex lock; + struct list_head va; +}; + +static inline struct lima_bo * +to_lima_bo(struct drm_gem_object *obj) +{ + return container_of(obj, struct lima_bo, gem); +} + +struct lima_bo *lima_bo_create(struct lima_device *dev, u32 size, + u32 flags, struct sg_table *sgt, + struct reservation_object *resv); +void lima_bo_destroy(struct lima_bo *bo); +void *lima_bo_vmap(struct lima_bo *bo); +void lima_bo_vunmap(struct lima_bo *bo); + +#endif diff --git a/drivers/gpu/drm/lima/lima_pmu.c b/drivers/gpu/drm/lima/lima_pmu.c new file mode 100644 index 000000000000..571f6d661581 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_pmu.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/iopoll.h> +#include <linux/device.h> + +#include "lima_device.h" +#include "lima_pmu.h" +#include "lima_regs.h" + +#define pmu_write(reg, data) writel(data, ip->iomem + reg) +#define pmu_read(reg) readl(ip->iomem + reg) + +static int lima_pmu_wait_cmd(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int err; + u32 v; + + err = readl_poll_timeout(ip->iomem + LIMA_PMU_INT_RAWSTAT, + v, v & LIMA_PMU_INT_CMD_MASK, + 100, 100000); + if (err) { + dev_err(dev->dev, "timeout wait pmd cmd\n"); + return err; + } + + pmu_write(LIMA_PMU_INT_CLEAR, LIMA_PMU_INT_CMD_MASK); + return 0; +} + +int lima_pmu_init(struct lima_ip *ip) +{ + int err; + u32 stat; + + pmu_write(LIMA_PMU_INT_MASK, 0); + + /* If this value is too low, when in high GPU clk freq, + * GPU will be in unstable state. + */ + pmu_write(LIMA_PMU_SW_DELAY, 0xffff); + + /* status reg 1=off 0=on */ + stat = pmu_read(LIMA_PMU_STATUS); + + /* power up all ip */ + if (stat) { + pmu_write(LIMA_PMU_POWER_UP, stat); + err = lima_pmu_wait_cmd(ip); + if (err) + return err; + } + return 0; +} + +void lima_pmu_fini(struct lima_ip *ip) +{ + +} diff --git a/drivers/gpu/drm/lima/lima_pmu.h b/drivers/gpu/drm/lima/lima_pmu.h new file mode 100644 index 000000000000..a2a18775eb07 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_pmu.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_PMU_H__ +#define __LIMA_PMU_H__ + +struct lima_ip; + +int lima_pmu_init(struct lima_ip *ip); +void lima_pmu_fini(struct lima_ip *ip); + +#endif diff --git a/drivers/gpu/drm/lima/lima_pp.c b/drivers/gpu/drm/lima/lima_pp.c new file mode 100644 index 000000000000..d29721e177bf --- /dev/null +++ b/drivers/gpu/drm/lima/lima_pp.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/device.h> +#include <linux/slab.h> + +#include <drm/lima_drm.h> + +#include "lima_device.h" +#include "lima_pp.h" +#include "lima_dlbu.h" +#include "lima_bcast.h" +#include "lima_vm.h" +#include "lima_regs.h" + +#define pp_write(reg, data) writel(data, ip->iomem + reg) +#define pp_read(reg) readl(ip->iomem + reg) + +static void lima_pp_handle_irq(struct lima_ip *ip, u32 state) +{ + struct lima_device *dev = ip->dev; + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + + if (state & LIMA_PP_IRQ_MASK_ERROR) { + u32 status = pp_read(LIMA_PP_STATUS); + + dev_err(dev->dev, "pp error irq state=%x status=%x\n", + state, status); + + pipe->error = true; + + /* mask all interrupts before hard reset */ + pp_write(LIMA_PP_INT_MASK, 0); + } + + pp_write(LIMA_PP_INT_CLEAR, state); +} + +static irqreturn_t lima_pp_irq_handler(int irq, void *data) +{ + struct lima_ip *ip = data; + struct lima_device *dev = ip->dev; + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + u32 state = pp_read(LIMA_PP_INT_STATUS); + + /* for shared irq case */ + if (!state) + return IRQ_NONE; + + lima_pp_handle_irq(ip, state); + + if (atomic_dec_and_test(&pipe->task)) + lima_sched_pipe_task_done(pipe); + + return IRQ_HANDLED; +} + +static irqreturn_t lima_pp_bcast_irq_handler(int irq, void *data) +{ + int i; + irqreturn_t ret = IRQ_NONE; + struct lima_ip *pp_bcast = data; + struct lima_device *dev = pp_bcast->dev; + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + struct drm_lima_m450_pp_frame *frame = pipe->current_task->frame; + + for (i = 0; i < frame->num_pp; i++) { + struct lima_ip *ip = pipe->processor[i]; + u32 status, state; + + if (pipe->done & (1 << i)) + continue; + + /* status read first in case int state change in the middle + * which may miss the interrupt handling + */ + status = pp_read(LIMA_PP_STATUS); + state = pp_read(LIMA_PP_INT_STATUS); + + if (state) { + lima_pp_handle_irq(ip, state); + ret = IRQ_HANDLED; + } else { + if (status & LIMA_PP_STATUS_RENDERING_ACTIVE) + continue; + } + + pipe->done |= (1 << i); + if (atomic_dec_and_test(&pipe->task)) + lima_sched_pipe_task_done(pipe); + } + + return ret; +} + +static void lima_pp_soft_reset_async(struct lima_ip *ip) +{ + if (ip->data.async_reset) + return; + + pp_write(LIMA_PP_INT_MASK, 0); + pp_write(LIMA_PP_INT_RAWSTAT, LIMA_PP_IRQ_MASK_ALL); + pp_write(LIMA_PP_CTRL, LIMA_PP_CTRL_SOFT_RESET); + ip->data.async_reset = true; +} + +static int lima_pp_soft_reset_poll(struct lima_ip *ip) +{ + return !(pp_read(LIMA_PP_STATUS) & LIMA_PP_STATUS_RENDERING_ACTIVE) && + pp_read(LIMA_PP_INT_RAWSTAT) == LIMA_PP_IRQ_RESET_COMPLETED; +} + +static int lima_pp_soft_reset_async_wait_one(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int ret; + + ret = lima_poll_timeout(ip, lima_pp_soft_reset_poll, 0, 100); + if (ret) { + dev_err(dev->dev, "pp %s reset time out\n", lima_ip_name(ip)); + return ret; + } + + pp_write(LIMA_PP_INT_CLEAR, LIMA_PP_IRQ_MASK_ALL); + pp_write(LIMA_PP_INT_MASK, LIMA_PP_IRQ_MASK_USED); + return 0; +} + +static int lima_pp_soft_reset_async_wait(struct lima_ip *ip) +{ + int i, err = 0; + + if (!ip->data.async_reset) + return 0; + + if (ip->id == lima_ip_pp_bcast) { + struct lima_device *dev = ip->dev; + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + struct drm_lima_m450_pp_frame *frame = pipe->current_task->frame; + + for (i = 0; i < frame->num_pp; i++) + err |= lima_pp_soft_reset_async_wait_one(pipe->processor[i]); + } else + err = lima_pp_soft_reset_async_wait_one(ip); + + ip->data.async_reset = false; + return err; +} + +static void lima_pp_write_frame(struct lima_ip *ip, u32 *frame, u32 *wb) +{ + int i, j, n = 0; + + for (i = 0; i < LIMA_PP_FRAME_REG_NUM; i++) + writel(frame[i], ip->iomem + LIMA_PP_FRAME + i * 4); + + for (i = 0; i < 3; i++) { + for (j = 0; j < LIMA_PP_WB_REG_NUM; j++) + writel(wb[n++], ip->iomem + LIMA_PP_WB(i) + j * 4); + } +} + +static int lima_pp_hard_reset_poll(struct lima_ip *ip) +{ + pp_write(LIMA_PP_PERF_CNT_0_LIMIT, 0xC01A0000); + return pp_read(LIMA_PP_PERF_CNT_0_LIMIT) == 0xC01A0000; +} + +static int lima_pp_hard_reset(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int ret; + + pp_write(LIMA_PP_PERF_CNT_0_LIMIT, 0xC0FFE000); + pp_write(LIMA_PP_INT_MASK, 0); + pp_write(LIMA_PP_CTRL, LIMA_PP_CTRL_FORCE_RESET); + ret = lima_poll_timeout(ip, lima_pp_hard_reset_poll, 10, 100); + if (ret) { + dev_err(dev->dev, "pp hard reset timeout\n"); + return ret; + } + + pp_write(LIMA_PP_PERF_CNT_0_LIMIT, 0); + pp_write(LIMA_PP_INT_CLEAR, LIMA_PP_IRQ_MASK_ALL); + pp_write(LIMA_PP_INT_MASK, LIMA_PP_IRQ_MASK_USED); + return 0; +} + +static void lima_pp_print_version(struct lima_ip *ip) +{ + u32 version, major, minor; + char *name; + + version = pp_read(LIMA_PP_VERSION); + major = (version >> 8) & 0xFF; + minor = version & 0xFF; + switch (version >> 16) { + case 0xC807: + name = "mali200"; + break; + case 0xCE07: + name = "mali300"; + break; + case 0xCD07: + name = "mali400"; + break; + case 0xCF07: + name = "mali450"; + break; + default: + name = "unknown"; + break; + } + dev_info(ip->dev->dev, "%s - %s version major %d minor %d\n", + lima_ip_name(ip), name, major, minor); +} + +int lima_pp_init(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int err; + + lima_pp_print_version(ip); + + ip->data.async_reset = false; + lima_pp_soft_reset_async(ip); + err = lima_pp_soft_reset_async_wait(ip); + if (err) + return err; + + err = devm_request_irq(dev->dev, ip->irq, lima_pp_irq_handler, + IRQF_SHARED, lima_ip_name(ip), ip); + if (err) { + dev_err(dev->dev, "pp %s fail to request irq\n", + lima_ip_name(ip)); + return err; + } + + dev->pp_version = pp_read(LIMA_PP_VERSION); + + return 0; +} + +void lima_pp_fini(struct lima_ip *ip) +{ + +} + +int lima_pp_bcast_init(struct lima_ip *ip) +{ + struct lima_device *dev = ip->dev; + int err; + + err = devm_request_irq(dev->dev, ip->irq, lima_pp_bcast_irq_handler, + IRQF_SHARED, lima_ip_name(ip), ip); + if (err) { + dev_err(dev->dev, "pp %s fail to request irq\n", + lima_ip_name(ip)); + return err; + } + + return 0; +} + +void lima_pp_bcast_fini(struct lima_ip *ip) +{ + +} + +static int lima_pp_task_validate(struct lima_sched_pipe *pipe, + struct lima_sched_task *task) +{ + u32 num_pp; + + if (pipe->bcast_processor) { + struct drm_lima_m450_pp_frame *f = task->frame; + + num_pp = f->num_pp; + + if (f->_pad) + return -EINVAL; + } else { + struct drm_lima_m400_pp_frame *f = task->frame; + + num_pp = f->num_pp; + } + + if (num_pp == 0 || num_pp > pipe->num_processor) + return -EINVAL; + + return 0; +} + +static void lima_pp_task_run(struct lima_sched_pipe *pipe, + struct lima_sched_task *task) +{ + if (pipe->bcast_processor) { + struct drm_lima_m450_pp_frame *frame = task->frame; + struct lima_device *dev = pipe->bcast_processor->dev; + struct lima_ip *ip = pipe->bcast_processor; + int i; + + pipe->done = 0; + atomic_set(&pipe->task, frame->num_pp); + + if (frame->use_dlbu) { + lima_dlbu_enable(dev, frame->num_pp); + + frame->frame[LIMA_PP_FRAME >> 2] = LIMA_VA_RESERVE_DLBU; + lima_dlbu_set_reg(dev->ip + lima_ip_dlbu, frame->dlbu_regs); + } else + lima_dlbu_disable(dev); + + lima_bcast_enable(dev, frame->num_pp); + + lima_pp_soft_reset_async_wait(ip); + + lima_pp_write_frame(ip, frame->frame, frame->wb); + + for (i = 0; i < frame->num_pp; i++) { + struct lima_ip *ip = pipe->processor[i]; + + pp_write(LIMA_PP_STACK, frame->fragment_stack_address[i]); + if (!frame->use_dlbu) + pp_write(LIMA_PP_FRAME, frame->plbu_array_address[i]); + } + + pp_write(LIMA_PP_CTRL, LIMA_PP_CTRL_START_RENDERING); + } else { + struct drm_lima_m400_pp_frame *frame = task->frame; + int i; + + atomic_set(&pipe->task, frame->num_pp); + + for (i = 0; i < frame->num_pp; i++) { + struct lima_ip *ip = pipe->processor[i]; + + frame->frame[LIMA_PP_FRAME >> 2] = + frame->plbu_array_address[i]; + frame->frame[LIMA_PP_STACK >> 2] = + frame->fragment_stack_address[i]; + + lima_pp_soft_reset_async_wait(ip); + + lima_pp_write_frame(ip, frame->frame, frame->wb); + + pp_write(LIMA_PP_CTRL, LIMA_PP_CTRL_START_RENDERING); + } + } +} + +static void lima_pp_task_fini(struct lima_sched_pipe *pipe) +{ + if (pipe->bcast_processor) + lima_pp_soft_reset_async(pipe->bcast_processor); + else { + int i; + + for (i = 0; i < pipe->num_processor; i++) + lima_pp_soft_reset_async(pipe->processor[i]); + } +} + +static void lima_pp_task_error(struct lima_sched_pipe *pipe) +{ + int i; + + for (i = 0; i < pipe->num_processor; i++) { + struct lima_ip *ip = pipe->processor[i]; + + dev_err(ip->dev->dev, "pp task error %d int_state=%x status=%x\n", + i, pp_read(LIMA_PP_INT_STATUS), pp_read(LIMA_PP_STATUS)); + + lima_pp_hard_reset(ip); + } +} + +static void lima_pp_task_mmu_error(struct lima_sched_pipe *pipe) +{ + if (atomic_dec_and_test(&pipe->task)) + lima_sched_pipe_task_done(pipe); +} + +static struct kmem_cache *lima_pp_task_slab; +static int lima_pp_task_slab_refcnt; + +int lima_pp_pipe_init(struct lima_device *dev) +{ + int frame_size; + struct lima_sched_pipe *pipe = dev->pipe + lima_pipe_pp; + + if (dev->id == lima_gpu_mali400) + frame_size = sizeof(struct drm_lima_m400_pp_frame); + else + frame_size = sizeof(struct drm_lima_m450_pp_frame); + + if (!lima_pp_task_slab) { + lima_pp_task_slab = kmem_cache_create_usercopy( + "lima_pp_task", sizeof(struct lima_sched_task) + frame_size, + 0, SLAB_HWCACHE_ALIGN, sizeof(struct lima_sched_task), + frame_size, NULL); + if (!lima_pp_task_slab) + return -ENOMEM; + } + lima_pp_task_slab_refcnt++; + + pipe->frame_size = frame_size; + pipe->task_slab = lima_pp_task_slab; + + pipe->task_validate = lima_pp_task_validate; + pipe->task_run = lima_pp_task_run; + pipe->task_fini = lima_pp_task_fini; + pipe->task_error = lima_pp_task_error; + pipe->task_mmu_error = lima_pp_task_mmu_error; + + return 0; +} + +void lima_pp_pipe_fini(struct lima_device *dev) +{ + if (!--lima_pp_task_slab_refcnt) { + kmem_cache_destroy(lima_pp_task_slab); + lima_pp_task_slab = NULL; + } +} diff --git a/drivers/gpu/drm/lima/lima_pp.h b/drivers/gpu/drm/lima/lima_pp.h new file mode 100644 index 000000000000..bf60c77b2633 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_pp.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_PP_H__ +#define __LIMA_PP_H__ + +struct lima_ip; +struct lima_device; + +int lima_pp_init(struct lima_ip *ip); +void lima_pp_fini(struct lima_ip *ip); + +int lima_pp_bcast_init(struct lima_ip *ip); +void lima_pp_bcast_fini(struct lima_ip *ip); + +int lima_pp_pipe_init(struct lima_device *dev); +void lima_pp_pipe_fini(struct lima_device *dev); + +#endif diff --git a/drivers/gpu/drm/lima/lima_regs.h b/drivers/gpu/drm/lima/lima_regs.h new file mode 100644 index 000000000000..ace8ecefbe90 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_regs.h @@ -0,0 +1,298 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright 2010-2017 ARM Limited. All rights reserved. + * Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> + */ + +#ifndef __LIMA_REGS_H__ +#define __LIMA_REGS_H__ + +/* This file's register definition is collected from the + * official ARM Mali Utgard GPU kernel driver source code + */ + +/* PMU regs */ +#define LIMA_PMU_POWER_UP 0x00 +#define LIMA_PMU_POWER_DOWN 0x04 +#define LIMA_PMU_POWER_GP0_MASK BIT(0) +#define LIMA_PMU_POWER_L2_MASK BIT(1) +#define LIMA_PMU_POWER_PP_MASK(i) BIT(2 + i) + +/* + * On Mali450 each block automatically starts up its corresponding L2 + * and the PPs are not fully independent controllable. + * Instead PP0, PP1-3 and PP4-7 can be turned on or off. + */ +#define LIMA450_PMU_POWER_PP0_MASK BIT(1) +#define LIMA450_PMU_POWER_PP13_MASK BIT(2) +#define LIMA450_PMU_POWER_PP47_MASK BIT(3) + +#define LIMA_PMU_STATUS 0x08 +#define LIMA_PMU_INT_MASK 0x0C +#define LIMA_PMU_INT_RAWSTAT 0x10 +#define LIMA_PMU_INT_CLEAR 0x18 +#define LIMA_PMU_INT_CMD_MASK BIT(0) +#define LIMA_PMU_SW_DELAY 0x1C + +/* L2 cache regs */ +#define LIMA_L2_CACHE_SIZE 0x0004 +#define LIMA_L2_CACHE_STATUS 0x0008 +#define LIMA_L2_CACHE_STATUS_COMMAND_BUSY BIT(0) +#define LIMA_L2_CACHE_STATUS_DATA_BUSY BIT(1) +#define LIMA_L2_CACHE_COMMAND 0x0010 +#define LIMA_L2_CACHE_COMMAND_CLEAR_ALL BIT(0) +#define LIMA_L2_CACHE_CLEAR_PAGE 0x0014 +#define LIMA_L2_CACHE_MAX_READS 0x0018 +#define LIMA_L2_CACHE_ENABLE 0x001C +#define LIMA_L2_CACHE_ENABLE_ACCESS BIT(0) +#define LIMA_L2_CACHE_ENABLE_READ_ALLOCATE BIT(1) +#define LIMA_L2_CACHE_PERFCNT_SRC0 0x0020 +#define LIMA_L2_CACHE_PERFCNT_VAL0 0x0024 +#define LIMA_L2_CACHE_PERFCNT_SRC1 0x0028 +#define LIMA_L2_CACHE_ERFCNT_VAL1 0x002C + +/* GP regs */ +#define LIMA_GP_VSCL_START_ADDR 0x00 +#define LIMA_GP_VSCL_END_ADDR 0x04 +#define LIMA_GP_PLBUCL_START_ADDR 0x08 +#define LIMA_GP_PLBUCL_END_ADDR 0x0c +#define LIMA_GP_PLBU_ALLOC_START_ADDR 0x10 +#define LIMA_GP_PLBU_ALLOC_END_ADDR 0x14 +#define LIMA_GP_CMD 0x20 +#define LIMA_GP_CMD_START_VS BIT(0) +#define LIMA_GP_CMD_START_PLBU BIT(1) +#define LIMA_GP_CMD_UPDATE_PLBU_ALLOC BIT(4) +#define LIMA_GP_CMD_RESET BIT(5) +#define LIMA_GP_CMD_FORCE_HANG BIT(6) +#define LIMA_GP_CMD_STOP_BUS BIT(9) +#define LIMA_GP_CMD_SOFT_RESET BIT(10) +#define LIMA_GP_INT_RAWSTAT 0x24 +#define LIMA_GP_INT_CLEAR 0x28 +#define LIMA_GP_INT_MASK 0x2C +#define LIMA_GP_INT_STAT 0x30 +#define LIMA_GP_IRQ_VS_END_CMD_LST BIT(0) +#define LIMA_GP_IRQ_PLBU_END_CMD_LST BIT(1) +#define LIMA_GP_IRQ_PLBU_OUT_OF_MEM BIT(2) +#define LIMA_GP_IRQ_VS_SEM_IRQ BIT(3) +#define LIMA_GP_IRQ_PLBU_SEM_IRQ BIT(4) +#define LIMA_GP_IRQ_HANG BIT(5) +#define LIMA_GP_IRQ_FORCE_HANG BIT(6) +#define LIMA_GP_IRQ_PERF_CNT_0_LIMIT BIT(7) +#define LIMA_GP_IRQ_PERF_CNT_1_LIMIT BIT(8) +#define LIMA_GP_IRQ_WRITE_BOUND_ERR BIT(9) +#define LIMA_GP_IRQ_SYNC_ERROR BIT(10) +#define LIMA_GP_IRQ_AXI_BUS_ERROR BIT(11) +#define LIMA_GP_IRQ_AXI_BUS_STOPPED BIT(12) +#define LIMA_GP_IRQ_VS_INVALID_CMD BIT(13) +#define LIMA_GP_IRQ_PLB_INVALID_CMD BIT(14) +#define LIMA_GP_IRQ_RESET_COMPLETED BIT(19) +#define LIMA_GP_IRQ_SEMAPHORE_UNDERFLOW BIT(20) +#define LIMA_GP_IRQ_SEMAPHORE_OVERFLOW BIT(21) +#define LIMA_GP_IRQ_PTR_ARRAY_OUT_OF_BOUNDS BIT(22) +#define LIMA_GP_WRITE_BOUND_LOW 0x34 +#define LIMA_GP_PERF_CNT_0_ENABLE 0x3C +#define LIMA_GP_PERF_CNT_1_ENABLE 0x40 +#define LIMA_GP_PERF_CNT_0_SRC 0x44 +#define LIMA_GP_PERF_CNT_1_SRC 0x48 +#define LIMA_GP_PERF_CNT_0_VALUE 0x4C +#define LIMA_GP_PERF_CNT_1_VALUE 0x50 +#define LIMA_GP_PERF_CNT_0_LIMIT 0x54 +#define LIMA_GP_STATUS 0x68 +#define LIMA_GP_STATUS_VS_ACTIVE BIT(1) +#define LIMA_GP_STATUS_BUS_STOPPED BIT(2) +#define LIMA_GP_STATUS_PLBU_ACTIVE BIT(3) +#define LIMA_GP_STATUS_BUS_ERROR BIT(6) +#define LIMA_GP_STATUS_WRITE_BOUND_ERR BIT(8) +#define LIMA_GP_VERSION 0x6C +#define LIMA_GP_VSCL_START_ADDR_READ 0x80 +#define LIMA_GP_PLBCL_START_ADDR_READ 0x84 +#define LIMA_GP_CONTR_AXI_BUS_ERROR_STAT 0x94 + +#define LIMA_GP_IRQ_MASK_ALL \ + ( \ + LIMA_GP_IRQ_VS_END_CMD_LST | \ + LIMA_GP_IRQ_PLBU_END_CMD_LST | \ + LIMA_GP_IRQ_PLBU_OUT_OF_MEM | \ + LIMA_GP_IRQ_VS_SEM_IRQ | \ + LIMA_GP_IRQ_PLBU_SEM_IRQ | \ + LIMA_GP_IRQ_HANG | \ + LIMA_GP_IRQ_FORCE_HANG | \ + LIMA_GP_IRQ_PERF_CNT_0_LIMIT | \ + LIMA_GP_IRQ_PERF_CNT_1_LIMIT | \ + LIMA_GP_IRQ_WRITE_BOUND_ERR | \ + LIMA_GP_IRQ_SYNC_ERROR | \ + LIMA_GP_IRQ_AXI_BUS_ERROR | \ + LIMA_GP_IRQ_AXI_BUS_STOPPED | \ + LIMA_GP_IRQ_VS_INVALID_CMD | \ + LIMA_GP_IRQ_PLB_INVALID_CMD | \ + LIMA_GP_IRQ_RESET_COMPLETED | \ + LIMA_GP_IRQ_SEMAPHORE_UNDERFLOW | \ + LIMA_GP_IRQ_SEMAPHORE_OVERFLOW | \ + LIMA_GP_IRQ_PTR_ARRAY_OUT_OF_BOUNDS) + +#define LIMA_GP_IRQ_MASK_ERROR \ + ( \ + LIMA_GP_IRQ_PLBU_OUT_OF_MEM | \ + LIMA_GP_IRQ_FORCE_HANG | \ + LIMA_GP_IRQ_WRITE_BOUND_ERR | \ + LIMA_GP_IRQ_SYNC_ERROR | \ + LIMA_GP_IRQ_AXI_BUS_ERROR | \ + LIMA_GP_IRQ_VS_INVALID_CMD | \ + LIMA_GP_IRQ_PLB_INVALID_CMD | \ + LIMA_GP_IRQ_SEMAPHORE_UNDERFLOW | \ + LIMA_GP_IRQ_SEMAPHORE_OVERFLOW | \ + LIMA_GP_IRQ_PTR_ARRAY_OUT_OF_BOUNDS) + +#define LIMA_GP_IRQ_MASK_USED \ + ( \ + LIMA_GP_IRQ_VS_END_CMD_LST | \ + LIMA_GP_IRQ_PLBU_END_CMD_LST | \ + LIMA_GP_IRQ_MASK_ERROR) + +/* PP regs */ +#define LIMA_PP_FRAME 0x0000 +#define LIMA_PP_RSW 0x0004 +#define LIMA_PP_STACK 0x0030 +#define LIMA_PP_STACK_SIZE 0x0034 +#define LIMA_PP_ORIGIN_OFFSET_X 0x0040 +#define LIMA_PP_WB(i) (0x0100 * (i + 1)) +#define LIMA_PP_WB_SOURCE_SELECT 0x0000 +#define LIMA_PP_WB_SOURCE_ADDR 0x0004 + +#define LIMA_PP_VERSION 0x1000 +#define LIMA_PP_CURRENT_REND_LIST_ADDR 0x1004 +#define LIMA_PP_STATUS 0x1008 +#define LIMA_PP_STATUS_RENDERING_ACTIVE BIT(0) +#define LIMA_PP_STATUS_BUS_STOPPED BIT(4) +#define LIMA_PP_CTRL 0x100c +#define LIMA_PP_CTRL_STOP_BUS BIT(0) +#define LIMA_PP_CTRL_FLUSH_CACHES BIT(3) +#define LIMA_PP_CTRL_FORCE_RESET BIT(5) +#define LIMA_PP_CTRL_START_RENDERING BIT(6) +#define LIMA_PP_CTRL_SOFT_RESET BIT(7) +#define LIMA_PP_INT_RAWSTAT 0x1020 +#define LIMA_PP_INT_CLEAR 0x1024 +#define LIMA_PP_INT_MASK 0x1028 +#define LIMA_PP_INT_STATUS 0x102c +#define LIMA_PP_IRQ_END_OF_FRAME BIT(0) +#define LIMA_PP_IRQ_END_OF_TILE BIT(1) +#define LIMA_PP_IRQ_HANG BIT(2) +#define LIMA_PP_IRQ_FORCE_HANG BIT(3) +#define LIMA_PP_IRQ_BUS_ERROR BIT(4) +#define LIMA_PP_IRQ_BUS_STOP BIT(5) +#define LIMA_PP_IRQ_CNT_0_LIMIT BIT(6) +#define LIMA_PP_IRQ_CNT_1_LIMIT BIT(7) +#define LIMA_PP_IRQ_WRITE_BOUNDARY_ERROR BIT(8) +#define LIMA_PP_IRQ_INVALID_PLIST_COMMAND BIT(9) +#define LIMA_PP_IRQ_CALL_STACK_UNDERFLOW BIT(10) +#define LIMA_PP_IRQ_CALL_STACK_OVERFLOW BIT(11) +#define LIMA_PP_IRQ_RESET_COMPLETED BIT(12) +#define LIMA_PP_WRITE_BOUNDARY_LOW 0x1044 +#define LIMA_PP_BUS_ERROR_STATUS 0x1050 +#define LIMA_PP_PERF_CNT_0_ENABLE 0x1080 +#define LIMA_PP_PERF_CNT_0_SRC 0x1084 +#define LIMA_PP_PERF_CNT_0_LIMIT 0x1088 +#define LIMA_PP_PERF_CNT_0_VALUE 0x108c +#define LIMA_PP_PERF_CNT_1_ENABLE 0x10a0 +#define LIMA_PP_PERF_CNT_1_SRC 0x10a4 +#define LIMA_PP_PERF_CNT_1_LIMIT 0x10a8 +#define LIMA_PP_PERF_CNT_1_VALUE 0x10ac +#define LIMA_PP_PERFMON_CONTR 0x10b0 +#define LIMA_PP_PERFMON_BASE 0x10b4 + +#define LIMA_PP_IRQ_MASK_ALL \ + ( \ + LIMA_PP_IRQ_END_OF_FRAME | \ + LIMA_PP_IRQ_END_OF_TILE | \ + LIMA_PP_IRQ_HANG | \ + LIMA_PP_IRQ_FORCE_HANG | \ + LIMA_PP_IRQ_BUS_ERROR | \ + LIMA_PP_IRQ_BUS_STOP | \ + LIMA_PP_IRQ_CNT_0_LIMIT | \ + LIMA_PP_IRQ_CNT_1_LIMIT | \ + LIMA_PP_IRQ_WRITE_BOUNDARY_ERROR | \ + LIMA_PP_IRQ_INVALID_PLIST_COMMAND | \ + LIMA_PP_IRQ_CALL_STACK_UNDERFLOW | \ + LIMA_PP_IRQ_CALL_STACK_OVERFLOW | \ + LIMA_PP_IRQ_RESET_COMPLETED) + +#define LIMA_PP_IRQ_MASK_ERROR \ + ( \ + LIMA_PP_IRQ_FORCE_HANG | \ + LIMA_PP_IRQ_BUS_ERROR | \ + LIMA_PP_IRQ_WRITE_BOUNDARY_ERROR | \ + LIMA_PP_IRQ_INVALID_PLIST_COMMAND | \ + LIMA_PP_IRQ_CALL_STACK_UNDERFLOW | \ + LIMA_PP_IRQ_CALL_STACK_OVERFLOW) + +#define LIMA_PP_IRQ_MASK_USED \ + ( \ + LIMA_PP_IRQ_END_OF_FRAME | \ + LIMA_PP_IRQ_MASK_ERROR) + +/* MMU regs */ +#define LIMA_MMU_DTE_ADDR 0x0000 +#define LIMA_MMU_STATUS 0x0004 +#define LIMA_MMU_STATUS_PAGING_ENABLED BIT(0) +#define LIMA_MMU_STATUS_PAGE_FAULT_ACTIVE BIT(1) +#define LIMA_MMU_STATUS_STALL_ACTIVE BIT(2) +#define LIMA_MMU_STATUS_IDLE BIT(3) +#define LIMA_MMU_STATUS_REPLAY_BUFFER_EMPTY BIT(4) +#define LIMA_MMU_STATUS_PAGE_FAULT_IS_WRITE BIT(5) +#define LIMA_MMU_STATUS_BUS_ID(x) ((x >> 6) & 0x1F) +#define LIMA_MMU_COMMAND 0x0008 +#define LIMA_MMU_COMMAND_ENABLE_PAGING 0x00 +#define LIMA_MMU_COMMAND_DISABLE_PAGING 0x01 +#define LIMA_MMU_COMMAND_ENABLE_STALL 0x02 +#define LIMA_MMU_COMMAND_DISABLE_STALL 0x03 +#define LIMA_MMU_COMMAND_ZAP_CACHE 0x04 +#define LIMA_MMU_COMMAND_PAGE_FAULT_DONE 0x05 +#define LIMA_MMU_COMMAND_HARD_RESET 0x06 +#define LIMA_MMU_PAGE_FAULT_ADDR 0x000C +#define LIMA_MMU_ZAP_ONE_LINE 0x0010 +#define LIMA_MMU_INT_RAWSTAT 0x0014 +#define LIMA_MMU_INT_CLEAR 0x0018 +#define LIMA_MMU_INT_MASK 0x001C +#define LIMA_MMU_INT_PAGE_FAULT BIT(0) +#define LIMA_MMU_INT_READ_BUS_ERROR BIT(1) +#define LIMA_MMU_INT_STATUS 0x0020 + +#define LIMA_VM_FLAG_PRESENT BIT(0) +#define LIMA_VM_FLAG_READ_PERMISSION BIT(1) +#define LIMA_VM_FLAG_WRITE_PERMISSION BIT(2) +#define LIMA_VM_FLAG_OVERRIDE_CACHE BIT(3) +#define LIMA_VM_FLAG_WRITE_CACHEABLE BIT(4) +#define LIMA_VM_FLAG_WRITE_ALLOCATE BIT(5) +#define LIMA_VM_FLAG_WRITE_BUFFERABLE BIT(6) +#define LIMA_VM_FLAG_READ_CACHEABLE BIT(7) +#define LIMA_VM_FLAG_READ_ALLOCATE BIT(8) +#define LIMA_VM_FLAG_MASK 0x1FF + +#define LIMA_VM_FLAGS_CACHE ( \ + LIMA_VM_FLAG_PRESENT | \ + LIMA_VM_FLAG_READ_PERMISSION | \ + LIMA_VM_FLAG_WRITE_PERMISSION | \ + LIMA_VM_FLAG_OVERRIDE_CACHE | \ + LIMA_VM_FLAG_WRITE_CACHEABLE | \ + LIMA_VM_FLAG_WRITE_BUFFERABLE | \ + LIMA_VM_FLAG_READ_CACHEABLE | \ + LIMA_VM_FLAG_READ_ALLOCATE) + +#define LIMA_VM_FLAGS_UNCACHE ( \ + LIMA_VM_FLAG_PRESENT | \ + LIMA_VM_FLAG_READ_PERMISSION | \ + LIMA_VM_FLAG_WRITE_PERMISSION) + +/* DLBU regs */ +#define LIMA_DLBU_MASTER_TLLIST_PHYS_ADDR 0x0000 +#define LIMA_DLBU_MASTER_TLLIST_VADDR 0x0004 +#define LIMA_DLBU_TLLIST_VBASEADDR 0x0008 +#define LIMA_DLBU_FB_DIM 0x000C +#define LIMA_DLBU_TLLIST_CONF 0x0010 +#define LIMA_DLBU_START_TILE_POS 0x0014 +#define LIMA_DLBU_PP_ENABLE_MASK 0x0018 + +/* BCAST regs */ +#define LIMA_BCAST_BROADCAST_MASK 0x0 +#define LIMA_BCAST_INTERRUPT_MASK 0x4 + +#endif diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c new file mode 100644 index 000000000000..97bd9c1deb87 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -0,0 +1,404 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/kthread.h> +#include <linux/slab.h> + +#include "lima_drv.h" +#include "lima_sched.h" +#include "lima_vm.h" +#include "lima_mmu.h" +#include "lima_l2_cache.h" +#include "lima_object.h" + +struct lima_fence { + struct dma_fence base; + struct lima_sched_pipe *pipe; +}; + +static struct kmem_cache *lima_fence_slab; +static int lima_fence_slab_refcnt; + +int lima_sched_slab_init(void) +{ + if (!lima_fence_slab) { + lima_fence_slab = kmem_cache_create( + "lima_fence", sizeof(struct lima_fence), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!lima_fence_slab) + return -ENOMEM; + } + + lima_fence_slab_refcnt++; + return 0; +} + +void lima_sched_slab_fini(void) +{ + if (!--lima_fence_slab_refcnt) { + kmem_cache_destroy(lima_fence_slab); + lima_fence_slab = NULL; + } +} + +static inline struct lima_fence *to_lima_fence(struct dma_fence *fence) +{ + return container_of(fence, struct lima_fence, base); +} + +static const char *lima_fence_get_driver_name(struct dma_fence *fence) +{ + return "lima"; +} + +static const char *lima_fence_get_timeline_name(struct dma_fence *fence) +{ + struct lima_fence *f = to_lima_fence(fence); + + return f->pipe->base.name; +} + +static void lima_fence_release_rcu(struct rcu_head *rcu) +{ + struct dma_fence *f = container_of(rcu, struct dma_fence, rcu); + struct lima_fence *fence = to_lima_fence(f); + + kmem_cache_free(lima_fence_slab, fence); +} + +static void lima_fence_release(struct dma_fence *fence) +{ + struct lima_fence *f = to_lima_fence(fence); + + call_rcu(&f->base.rcu, lima_fence_release_rcu); +} + +static const struct dma_fence_ops lima_fence_ops = { + .get_driver_name = lima_fence_get_driver_name, + .get_timeline_name = lima_fence_get_timeline_name, + .release = lima_fence_release, +}; + +static struct lima_fence *lima_fence_create(struct lima_sched_pipe *pipe) +{ + struct lima_fence *fence; + + fence = kmem_cache_zalloc(lima_fence_slab, GFP_KERNEL); + if (!fence) + return NULL; + + fence->pipe = pipe; + dma_fence_init(&fence->base, &lima_fence_ops, &pipe->fence_lock, + pipe->fence_context, ++pipe->fence_seqno); + + return fence; +} + +static inline struct lima_sched_task *to_lima_task(struct drm_sched_job *job) +{ + return container_of(job, struct lima_sched_task, base); +} + +static inline struct lima_sched_pipe *to_lima_pipe(struct drm_gpu_scheduler *sched) +{ + return container_of(sched, struct lima_sched_pipe, base); +} + +int lima_sched_task_init(struct lima_sched_task *task, + struct lima_sched_context *context, + struct lima_bo **bos, int num_bos, + struct lima_vm *vm) +{ + int err, i; + + task->bos = kmemdup(bos, sizeof(*bos) * num_bos, GFP_KERNEL); + if (!task->bos) + return -ENOMEM; + + for (i = 0; i < num_bos; i++) + drm_gem_object_get(&bos[i]->gem); + + err = drm_sched_job_init(&task->base, &context->base, vm); + if (err) { + kfree(task->bos); + return err; + } + + task->num_bos = num_bos; + task->vm = lima_vm_get(vm); + return 0; +} + +void lima_sched_task_fini(struct lima_sched_task *task) +{ + int i; + + drm_sched_job_cleanup(&task->base); + + for (i = 0; i < task->num_dep; i++) + dma_fence_put(task->dep[i]); + + kfree(task->dep); + + if (task->bos) { + for (i = 0; i < task->num_bos; i++) + drm_gem_object_put_unlocked(&task->bos[i]->gem); + kfree(task->bos); + } + + lima_vm_put(task->vm); +} + +int lima_sched_task_add_dep(struct lima_sched_task *task, struct dma_fence *fence) +{ + int i, new_dep = 4; + + /* same context's fence is definitly earlier then this task */ + if (fence->context == task->base.s_fence->finished.context) { + dma_fence_put(fence); + return 0; + } + + if (task->dep && task->num_dep == task->max_dep) + new_dep = task->max_dep * 2; + + if (task->max_dep < new_dep) { + void *dep = krealloc(task->dep, sizeof(*task->dep) * new_dep, GFP_KERNEL); + + if (!dep) + return -ENOMEM; + + task->max_dep = new_dep; + task->dep = dep; + } + + for (i = 0; i < task->num_dep; i++) { + if (task->dep[i]->context == fence->context && + dma_fence_is_later(fence, task->dep[i])) { + dma_fence_put(task->dep[i]); + task->dep[i] = fence; + return 0; + } + } + + task->dep[task->num_dep++] = fence; + return 0; +} + +int lima_sched_context_init(struct lima_sched_pipe *pipe, + struct lima_sched_context *context, + atomic_t *guilty) +{ + struct drm_sched_rq *rq = pipe->base.sched_rq + DRM_SCHED_PRIORITY_NORMAL; + + return drm_sched_entity_init(&context->base, &rq, 1, guilty); +} + +void lima_sched_context_fini(struct lima_sched_pipe *pipe, + struct lima_sched_context *context) +{ + drm_sched_entity_fini(&context->base); +} + +struct dma_fence *lima_sched_context_queue_task(struct lima_sched_context *context, + struct lima_sched_task *task) +{ + struct dma_fence *fence = dma_fence_get(&task->base.s_fence->finished); + + drm_sched_entity_push_job(&task->base, &context->base); + return fence; +} + +static struct dma_fence *lima_sched_dependency(struct drm_sched_job *job, + struct drm_sched_entity *entity) +{ + struct lima_sched_task *task = to_lima_task(job); + int i; + + for (i = 0; i < task->num_dep; i++) { + struct dma_fence *fence = task->dep[i]; + + if (!task->dep[i]) + continue; + + task->dep[i] = NULL; + + if (!dma_fence_is_signaled(fence)) + return fence; + + dma_fence_put(fence); + } + + return NULL; +} + +static struct dma_fence *lima_sched_run_job(struct drm_sched_job *job) +{ + struct lima_sched_task *task = to_lima_task(job); + struct lima_sched_pipe *pipe = to_lima_pipe(job->sched); + struct lima_fence *fence; + struct dma_fence *ret; + struct lima_vm *vm = NULL, *last_vm = NULL; + int i; + + /* after GPU reset */ + if (job->s_fence->finished.error < 0) + return NULL; + + fence = lima_fence_create(pipe); + if (!fence) + return NULL; + task->fence = &fence->base; + + /* for caller usage of the fence, otherwise irq handler + * may consume the fence before caller use it + */ + ret = dma_fence_get(task->fence); + + pipe->current_task = task; + + /* this is needed for MMU to work correctly, otherwise GP/PP + * will hang or page fault for unknown reason after running for + * a while. + * + * Need to investigate: + * 1. is it related to TLB + * 2. how much performance will be affected by L2 cache flush + * 3. can we reduce the calling of this function because all + * GP/PP use the same L2 cache on mali400 + * + * TODO: + * 1. move this to task fini to save some wait time? + * 2. when GP/PP use different l2 cache, need PP wait GP l2 + * cache flush? + */ + for (i = 0; i < pipe->num_l2_cache; i++) + lima_l2_cache_flush(pipe->l2_cache[i]); + + if (task->vm != pipe->current_vm) { + vm = lima_vm_get(task->vm); + last_vm = pipe->current_vm; + pipe->current_vm = task->vm; + } + + if (pipe->bcast_mmu) + lima_mmu_switch_vm(pipe->bcast_mmu, vm); + else { + for (i = 0; i < pipe->num_mmu; i++) + lima_mmu_switch_vm(pipe->mmu[i], vm); + } + + if (last_vm) + lima_vm_put(last_vm); + + pipe->error = false; + pipe->task_run(pipe, task); + + return task->fence; +} + +static void lima_sched_handle_error_task(struct lima_sched_pipe *pipe, + struct lima_sched_task *task) +{ + drm_sched_stop(&pipe->base); + + if (task) + drm_sched_increase_karma(&task->base); + + pipe->task_error(pipe); + + if (pipe->bcast_mmu) + lima_mmu_page_fault_resume(pipe->bcast_mmu); + else { + int i; + + for (i = 0; i < pipe->num_mmu; i++) + lima_mmu_page_fault_resume(pipe->mmu[i]); + } + + if (pipe->current_vm) + lima_vm_put(pipe->current_vm); + + pipe->current_vm = NULL; + pipe->current_task = NULL; + + drm_sched_resubmit_jobs(&pipe->base); + drm_sched_start(&pipe->base, true); +} + +static void lima_sched_timedout_job(struct drm_sched_job *job) +{ + struct lima_sched_pipe *pipe = to_lima_pipe(job->sched); + struct lima_sched_task *task = to_lima_task(job); + + DRM_ERROR("lima job timeout\n"); + + lima_sched_handle_error_task(pipe, task); +} + +static void lima_sched_free_job(struct drm_sched_job *job) +{ + struct lima_sched_task *task = to_lima_task(job); + struct lima_sched_pipe *pipe = to_lima_pipe(job->sched); + struct lima_vm *vm = task->vm; + struct lima_bo **bos = task->bos; + int i; + + dma_fence_put(task->fence); + + for (i = 0; i < task->num_bos; i++) + lima_vm_bo_del(vm, bos[i]); + + lima_sched_task_fini(task); + kmem_cache_free(pipe->task_slab, task); +} + +const struct drm_sched_backend_ops lima_sched_ops = { + .dependency = lima_sched_dependency, + .run_job = lima_sched_run_job, + .timedout_job = lima_sched_timedout_job, + .free_job = lima_sched_free_job, +}; + +static void lima_sched_error_work(struct work_struct *work) +{ + struct lima_sched_pipe *pipe = + container_of(work, struct lima_sched_pipe, error_work); + struct lima_sched_task *task = pipe->current_task; + + lima_sched_handle_error_task(pipe, task); +} + +int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name) +{ + long timeout; + + if (lima_sched_timeout_ms <= 0) + timeout = MAX_SCHEDULE_TIMEOUT; + else + timeout = msecs_to_jiffies(lima_sched_timeout_ms); + + pipe->fence_context = dma_fence_context_alloc(1); + spin_lock_init(&pipe->fence_lock); + + INIT_WORK(&pipe->error_work, lima_sched_error_work); + + return drm_sched_init(&pipe->base, &lima_sched_ops, 1, 0, timeout, name); +} + +void lima_sched_pipe_fini(struct lima_sched_pipe *pipe) +{ + drm_sched_fini(&pipe->base); +} + +void lima_sched_pipe_task_done(struct lima_sched_pipe *pipe) +{ + if (pipe->error) + schedule_work(&pipe->error_work); + else { + struct lima_sched_task *task = pipe->current_task; + + pipe->task_fini(pipe); + dma_fence_signal(task->fence); + } +} diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h new file mode 100644 index 000000000000..b017cfa7e327 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_sched.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_SCHED_H__ +#define __LIMA_SCHED_H__ + +#include <drm/gpu_scheduler.h> + +struct lima_vm; + +struct lima_sched_task { + struct drm_sched_job base; + + struct lima_vm *vm; + void *frame; + + struct dma_fence **dep; + int num_dep; + int max_dep; + + struct lima_bo **bos; + int num_bos; + + /* pipe fence */ + struct dma_fence *fence; +}; + +struct lima_sched_context { + struct drm_sched_entity base; +}; + +#define LIMA_SCHED_PIPE_MAX_MMU 8 +#define LIMA_SCHED_PIPE_MAX_L2_CACHE 2 +#define LIMA_SCHED_PIPE_MAX_PROCESSOR 8 + +struct lima_ip; + +struct lima_sched_pipe { + struct drm_gpu_scheduler base; + + u64 fence_context; + u32 fence_seqno; + spinlock_t fence_lock; + + struct lima_sched_task *current_task; + struct lima_vm *current_vm; + + struct lima_ip *mmu[LIMA_SCHED_PIPE_MAX_MMU]; + int num_mmu; + + struct lima_ip *l2_cache[LIMA_SCHED_PIPE_MAX_L2_CACHE]; + int num_l2_cache; + + struct lima_ip *processor[LIMA_SCHED_PIPE_MAX_PROCESSOR]; + int num_processor; + + struct lima_ip *bcast_processor; + struct lima_ip *bcast_mmu; + + u32 done; + bool error; + atomic_t task; + + int frame_size; + struct kmem_cache *task_slab; + + int (*task_validate)(struct lima_sched_pipe *pipe, struct lima_sched_task *task); + void (*task_run)(struct lima_sched_pipe *pipe, struct lima_sched_task *task); + void (*task_fini)(struct lima_sched_pipe *pipe); + void (*task_error)(struct lima_sched_pipe *pipe); + void (*task_mmu_error)(struct lima_sched_pipe *pipe); + + struct work_struct error_work; +}; + +int lima_sched_task_init(struct lima_sched_task *task, + struct lima_sched_context *context, + struct lima_bo **bos, int num_bos, + struct lima_vm *vm); +void lima_sched_task_fini(struct lima_sched_task *task); +int lima_sched_task_add_dep(struct lima_sched_task *task, struct dma_fence *fence); + +int lima_sched_context_init(struct lima_sched_pipe *pipe, + struct lima_sched_context *context, + atomic_t *guilty); +void lima_sched_context_fini(struct lima_sched_pipe *pipe, + struct lima_sched_context *context); +struct dma_fence *lima_sched_context_queue_task(struct lima_sched_context *context, + struct lima_sched_task *task); + +int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name); +void lima_sched_pipe_fini(struct lima_sched_pipe *pipe); +void lima_sched_pipe_task_done(struct lima_sched_pipe *pipe); + +static inline void lima_sched_pipe_mmu_error(struct lima_sched_pipe *pipe) +{ + pipe->error = true; + pipe->task_mmu_error(pipe); +} + +int lima_sched_slab_init(void); +void lima_sched_slab_fini(void); + +#endif diff --git a/drivers/gpu/drm/lima/lima_vm.c b/drivers/gpu/drm/lima/lima_vm.c new file mode 100644 index 000000000000..19e88ca16527 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_vm.c @@ -0,0 +1,282 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#include <linux/slab.h> +#include <linux/dma-mapping.h> + +#include "lima_device.h" +#include "lima_vm.h" +#include "lima_object.h" +#include "lima_regs.h" + +struct lima_bo_va { + struct list_head list; + unsigned int ref_count; + + struct drm_mm_node node; + + struct lima_vm *vm; +}; + +#define LIMA_VM_PD_SHIFT 22 +#define LIMA_VM_PT_SHIFT 12 +#define LIMA_VM_PB_SHIFT (LIMA_VM_PD_SHIFT + LIMA_VM_NUM_PT_PER_BT_SHIFT) +#define LIMA_VM_BT_SHIFT LIMA_VM_PT_SHIFT + +#define LIMA_VM_PT_MASK ((1 << LIMA_VM_PD_SHIFT) - 1) +#define LIMA_VM_BT_MASK ((1 << LIMA_VM_PB_SHIFT) - 1) + +#define LIMA_PDE(va) (va >> LIMA_VM_PD_SHIFT) +#define LIMA_PTE(va) ((va & LIMA_VM_PT_MASK) >> LIMA_VM_PT_SHIFT) +#define LIMA_PBE(va) (va >> LIMA_VM_PB_SHIFT) +#define LIMA_BTE(va) ((va & LIMA_VM_BT_MASK) >> LIMA_VM_BT_SHIFT) + + +static void lima_vm_unmap_page_table(struct lima_vm *vm, u32 start, u32 end) +{ + u32 addr; + + for (addr = start; addr <= end; addr += LIMA_PAGE_SIZE) { + u32 pbe = LIMA_PBE(addr); + u32 bte = LIMA_BTE(addr); + + vm->bts[pbe].cpu[bte] = 0; + } +} + +static int lima_vm_map_page_table(struct lima_vm *vm, dma_addr_t *dma, + u32 start, u32 end) +{ + u64 addr; + int i = 0; + + for (addr = start; addr <= end; addr += LIMA_PAGE_SIZE) { + u32 pbe = LIMA_PBE(addr); + u32 bte = LIMA_BTE(addr); + + if (!vm->bts[pbe].cpu) { + dma_addr_t pts; + u32 *pd; + int j; + + vm->bts[pbe].cpu = dma_alloc_wc( + vm->dev->dev, LIMA_PAGE_SIZE << LIMA_VM_NUM_PT_PER_BT_SHIFT, + &vm->bts[pbe].dma, GFP_KERNEL | __GFP_ZERO); + if (!vm->bts[pbe].cpu) { + if (addr != start) + lima_vm_unmap_page_table(vm, start, addr - 1); + return -ENOMEM; + } + + pts = vm->bts[pbe].dma; + pd = vm->pd.cpu + (pbe << LIMA_VM_NUM_PT_PER_BT_SHIFT); + for (j = 0; j < LIMA_VM_NUM_PT_PER_BT; j++) { + pd[j] = pts | LIMA_VM_FLAG_PRESENT; + pts += LIMA_PAGE_SIZE; + } + } + + vm->bts[pbe].cpu[bte] = dma[i++] | LIMA_VM_FLAGS_CACHE; + } + + return 0; +} + +static struct lima_bo_va * +lima_vm_bo_find(struct lima_vm *vm, struct lima_bo *bo) +{ + struct lima_bo_va *bo_va, *ret = NULL; + + list_for_each_entry(bo_va, &bo->va, list) { + if (bo_va->vm == vm) { + ret = bo_va; + break; + } + } + + return ret; +} + +int lima_vm_bo_add(struct lima_vm *vm, struct lima_bo *bo, bool create) +{ + struct lima_bo_va *bo_va; + int err; + + mutex_lock(&bo->lock); + + bo_va = lima_vm_bo_find(vm, bo); + if (bo_va) { + bo_va->ref_count++; + mutex_unlock(&bo->lock); + return 0; + } + + /* should not create new bo_va if not asked by caller */ + if (!create) { + mutex_unlock(&bo->lock); + return -ENOENT; + } + + bo_va = kzalloc(sizeof(*bo_va), GFP_KERNEL); + if (!bo_va) { + err = -ENOMEM; + goto err_out0; + } + + bo_va->vm = vm; + bo_va->ref_count = 1; + + mutex_lock(&vm->lock); + + err = drm_mm_insert_node(&vm->mm, &bo_va->node, bo->gem.size); + if (err) + goto err_out1; + + err = lima_vm_map_page_table(vm, bo->pages_dma_addr, bo_va->node.start, + bo_va->node.start + bo_va->node.size - 1); + if (err) + goto err_out2; + + mutex_unlock(&vm->lock); + + list_add_tail(&bo_va->list, &bo->va); + + mutex_unlock(&bo->lock); + return 0; + +err_out2: + drm_mm_remove_node(&bo_va->node); +err_out1: + mutex_unlock(&vm->lock); + kfree(bo_va); +err_out0: + mutex_unlock(&bo->lock); + return err; +} + +void lima_vm_bo_del(struct lima_vm *vm, struct lima_bo *bo) +{ + struct lima_bo_va *bo_va; + + mutex_lock(&bo->lock); + + bo_va = lima_vm_bo_find(vm, bo); + if (--bo_va->ref_count > 0) { + mutex_unlock(&bo->lock); + return; + } + + mutex_lock(&vm->lock); + + lima_vm_unmap_page_table(vm, bo_va->node.start, + bo_va->node.start + bo_va->node.size - 1); + + drm_mm_remove_node(&bo_va->node); + + mutex_unlock(&vm->lock); + + list_del(&bo_va->list); + + mutex_unlock(&bo->lock); + + kfree(bo_va); +} + +u32 lima_vm_get_va(struct lima_vm *vm, struct lima_bo *bo) +{ + struct lima_bo_va *bo_va; + u32 ret; + + mutex_lock(&bo->lock); + + bo_va = lima_vm_bo_find(vm, bo); + ret = bo_va->node.start; + + mutex_unlock(&bo->lock); + + return ret; +} + +struct lima_vm *lima_vm_create(struct lima_device *dev) +{ + struct lima_vm *vm; + + vm = kzalloc(sizeof(*vm), GFP_KERNEL); + if (!vm) + return NULL; + + vm->dev = dev; + mutex_init(&vm->lock); + kref_init(&vm->refcount); + + vm->pd.cpu = dma_alloc_wc(dev->dev, LIMA_PAGE_SIZE, &vm->pd.dma, + GFP_KERNEL | __GFP_ZERO); + if (!vm->pd.cpu) + goto err_out0; + + if (dev->dlbu_cpu) { + int err = lima_vm_map_page_table( + vm, &dev->dlbu_dma, LIMA_VA_RESERVE_DLBU, + LIMA_VA_RESERVE_DLBU + LIMA_PAGE_SIZE - 1); + if (err) + goto err_out1; + } + + drm_mm_init(&vm->mm, dev->va_start, dev->va_end - dev->va_start); + + return vm; + +err_out1: + dma_free_wc(dev->dev, LIMA_PAGE_SIZE, vm->pd.cpu, vm->pd.dma); +err_out0: + kfree(vm); + return NULL; +} + +void lima_vm_release(struct kref *kref) +{ + struct lima_vm *vm = container_of(kref, struct lima_vm, refcount); + int i; + + drm_mm_takedown(&vm->mm); + + for (i = 0; i < LIMA_VM_NUM_BT; i++) { + if (vm->bts[i].cpu) + dma_free_wc(vm->dev->dev, LIMA_PAGE_SIZE << LIMA_VM_NUM_PT_PER_BT_SHIFT, + vm->bts[i].cpu, vm->bts[i].dma); + } + + if (vm->pd.cpu) + dma_free_wc(vm->dev->dev, LIMA_PAGE_SIZE, vm->pd.cpu, vm->pd.dma); + + kfree(vm); +} + +void lima_vm_print(struct lima_vm *vm) +{ + int i, j, k; + u32 *pd, *pt; + + if (!vm->pd.cpu) + return; + + pd = vm->pd.cpu; + for (i = 0; i < LIMA_VM_NUM_BT; i++) { + if (!vm->bts[i].cpu) + continue; + + pt = vm->bts[i].cpu; + for (j = 0; j < LIMA_VM_NUM_PT_PER_BT; j++) { + int idx = (i << LIMA_VM_NUM_PT_PER_BT_SHIFT) + j; + + printk(KERN_INFO "lima vm pd %03x:%08x\n", idx, pd[idx]); + + for (k = 0; k < LIMA_PAGE_ENT_NUM; k++) { + u32 pte = *pt++; + + if (pte) + printk(KERN_INFO " pt %03x:%08x\n", k, pte); + } + } + } +} diff --git a/drivers/gpu/drm/lima/lima_vm.h b/drivers/gpu/drm/lima/lima_vm.h new file mode 100644 index 000000000000..caee2f8a29b4 --- /dev/null +++ b/drivers/gpu/drm/lima/lima_vm.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* Copyright 2017-2019 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_VM_H__ +#define __LIMA_VM_H__ + +#include <drm/drm_mm.h> +#include <linux/kref.h> + +#define LIMA_PAGE_SIZE 4096 +#define LIMA_PAGE_MASK (LIMA_PAGE_SIZE - 1) +#define LIMA_PAGE_ENT_NUM (LIMA_PAGE_SIZE / sizeof(u32)) + +#define LIMA_VM_NUM_PT_PER_BT_SHIFT 3 +#define LIMA_VM_NUM_PT_PER_BT (1 << LIMA_VM_NUM_PT_PER_BT_SHIFT) +#define LIMA_VM_NUM_BT (LIMA_PAGE_ENT_NUM >> LIMA_VM_NUM_PT_PER_BT_SHIFT) + +#define LIMA_VA_RESERVE_START 0xFFF00000 +#define LIMA_VA_RESERVE_DLBU LIMA_VA_RESERVE_START +#define LIMA_VA_RESERVE_END 0x100000000 + +struct lima_device; + +struct lima_vm_page { + u32 *cpu; + dma_addr_t dma; +}; + +struct lima_vm { + struct mutex lock; + struct kref refcount; + + struct drm_mm mm; + + struct lima_device *dev; + + struct lima_vm_page pd; + struct lima_vm_page bts[LIMA_VM_NUM_BT]; +}; + +int lima_vm_bo_add(struct lima_vm *vm, struct lima_bo *bo, bool create); +void lima_vm_bo_del(struct lima_vm *vm, struct lima_bo *bo); + +u32 lima_vm_get_va(struct lima_vm *vm, struct lima_bo *bo); + +struct lima_vm *lima_vm_create(struct lima_device *dev); +void lima_vm_release(struct kref *kref); + +static inline struct lima_vm *lima_vm_get(struct lima_vm *vm) +{ + kref_get(&vm->refcount); + return vm; +} + +static inline void lima_vm_put(struct lima_vm *vm) +{ + kref_put(&vm->refcount, lima_vm_release); +} + +void lima_vm_print(struct lima_vm *vm); + +#endif diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index f53f817356db..e36dbb4df867 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -38,6 +38,15 @@ config DRM_PANEL_SIMPLE that it can be automatically turned off when the panel goes into a low power state. +config DRM_PANEL_FEIYANG_FY07024DI26A30D + tristate "Feiyang FY07024DI26A30-D MIPI-DSI LCD panel" + depends on OF + depends on DRM_MIPI_DSI + depends on BACKLIGHT_CLASS_DEVICE + help + Say Y if you want to enable support for panels based on the + Feiyang FY07024DI26A30-D MIPI-DSI interface. + config DRM_PANEL_ILITEK_IL9322 tristate "Ilitek ILI9322 320x240 QVGA panels" depends on OF && SPI @@ -149,6 +158,19 @@ config DRM_PANEL_RAYDIUM_RM68200 Say Y here if you want to enable support for Raydium RM68200 720x1280 DSI video mode panel. +config DRM_PANEL_ROCKTECH_JH057N00900 + tristate "Rocktech JH057N00900 MIPI touchscreen panel" + depends on OF + depends on DRM_MIPI_DSI + depends on BACKLIGHT_CLASS_DEVICE + help + Say Y here if you want to enable support for Rocktech JH057N00900 + MIPI DSI panel as e.g. used in the Librem 5 devkit. It has a + resolution of 720x1440 pixels, a built in backlight and touch + controller. + Touch input support is provided by the goodix driver and needs to be + selected separately. + config DRM_PANEL_RONBO_RB070D30 tristate "Ronbo Electronics RB070D30 panel" depends on OF diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile index 7834947a53b0..78e3dc376bdd 100644 --- a/drivers/gpu/drm/panel/Makefile +++ b/drivers/gpu/drm/panel/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_DRM_PANEL_ARM_VERSATILE) += panel-arm-versatile.o obj-$(CONFIG_DRM_PANEL_LVDS) += panel-lvds.o obj-$(CONFIG_DRM_PANEL_SIMPLE) += panel-simple.o +obj-$(CONFIG_DRM_PANEL_FEIYANG_FY07024DI26A30D) += panel-feiyang-fy07024di26a30d.o obj-$(CONFIG_DRM_PANEL_ILITEK_IL9322) += panel-ilitek-ili9322.o obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9881C) += panel-ilitek-ili9881c.o obj-$(CONFIG_DRM_PANEL_INNOLUX_P079ZCA) += panel-innolux-p079zca.o @@ -13,6 +14,7 @@ obj-$(CONFIG_DRM_PANEL_ORISETECH_OTM8009A) += panel-orisetech-otm8009a.o obj-$(CONFIG_DRM_PANEL_PANASONIC_VVX10F034N00) += panel-panasonic-vvx10f034n00.o obj-$(CONFIG_DRM_PANEL_RASPBERRYPI_TOUCHSCREEN) += panel-raspberrypi-touchscreen.o obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM68200) += panel-raydium-rm68200.o +obj-$(CONFIG_DRM_PANEL_ROCKTECH_JH057N00900) += panel-rocktech-jh057n00900.o obj-$(CONFIG_DRM_PANEL_RONBO_RB070D30) += panel-ronbo-rb070d30.o obj-$(CONFIG_DRM_PANEL_SAMSUNG_LD9040) += panel-samsung-ld9040.o obj-$(CONFIG_DRM_PANEL_SAMSUNG_S6D16D0) += panel-samsung-s6d16d0.o diff --git a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c new file mode 100644 index 000000000000..dabf59e0f56f --- /dev/null +++ b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2018 Amarula Solutions + * Author: Jagan Teki <jagan@amarulasolutions.com> + */ + +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> +#include <drm/drm_print.h> + +#include <linux/backlight.h> +#include <linux/gpio/consumer.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regulator/consumer.h> + +#define FEIYANG_INIT_CMD_LEN 2 + +struct feiyang { + struct drm_panel panel; + struct mipi_dsi_device *dsi; + + struct backlight_device *backlight; + struct regulator *dvdd; + struct regulator *avdd; + struct gpio_desc *reset; +}; + +static inline struct feiyang *panel_to_feiyang(struct drm_panel *panel) +{ + return container_of(panel, struct feiyang, panel); +} + +struct feiyang_init_cmd { + u8 data[FEIYANG_INIT_CMD_LEN]; +}; + +static const struct feiyang_init_cmd feiyang_init_cmds[] = { + { .data = { 0x80, 0x58 } }, + { .data = { 0x81, 0x47 } }, + { .data = { 0x82, 0xD4 } }, + { .data = { 0x83, 0x88 } }, + { .data = { 0x84, 0xA9 } }, + { .data = { 0x85, 0xC3 } }, + { .data = { 0x86, 0x82 } }, +}; + +static int feiyang_prepare(struct drm_panel *panel) +{ + struct feiyang *ctx = panel_to_feiyang(panel); + struct mipi_dsi_device *dsi = ctx->dsi; + unsigned int i; + int ret; + + ret = regulator_enable(ctx->dvdd); + if (ret) + return ret; + + /* T1 (dvdd start + dvdd rise) 0 < T1 <= 10ms */ + msleep(10); + + ret = regulator_enable(ctx->avdd); + if (ret) + return ret; + + /* T3 (dvdd rise + avdd start + avdd rise) T3 >= 20ms */ + msleep(20); + + gpiod_set_value(ctx->reset, 0); + + /* + * T5 + T6 (avdd rise + video & logic signal rise) + * T5 >= 10ms, 0 < T6 <= 10ms + */ + msleep(20); + + gpiod_set_value(ctx->reset, 1); + + /* T12 (video & logic signal rise + backlight rise) T12 >= 200ms */ + msleep(200); + + for (i = 0; i < ARRAY_SIZE(feiyang_init_cmds); i++) { + const struct feiyang_init_cmd *cmd = + &feiyang_init_cmds[i]; + + ret = mipi_dsi_dcs_write_buffer(dsi, cmd->data, + FEIYANG_INIT_CMD_LEN); + if (ret < 0) + return ret; + } + + return 0; +} + +static int feiyang_enable(struct drm_panel *panel) +{ + struct feiyang *ctx = panel_to_feiyang(panel); + + /* T12 (video & logic signal rise + backlight rise) T12 >= 200ms */ + msleep(200); + + mipi_dsi_dcs_set_display_on(ctx->dsi); + backlight_enable(ctx->backlight); + + return 0; +} + +static int feiyang_disable(struct drm_panel *panel) +{ + struct feiyang *ctx = panel_to_feiyang(panel); + + backlight_disable(ctx->backlight); + return mipi_dsi_dcs_set_display_off(ctx->dsi); +} + +static int feiyang_unprepare(struct drm_panel *panel) +{ + struct feiyang *ctx = panel_to_feiyang(panel); + int ret; + + ret = mipi_dsi_dcs_set_display_off(ctx->dsi); + if (ret < 0) + DRM_DEV_ERROR(panel->dev, "failed to set display off: %d\n", + ret); + + ret = mipi_dsi_dcs_enter_sleep_mode(ctx->dsi); + if (ret < 0) + DRM_DEV_ERROR(panel->dev, "failed to enter sleep mode: %d\n", + ret); + + /* T13 (backlight fall + video & logic signal fall) T13 >= 200ms */ + msleep(200); + + gpiod_set_value(ctx->reset, 0); + + regulator_disable(ctx->avdd); + + /* T11 (dvdd rise to fall) 0 < T11 <= 10ms */ + msleep(10); + + regulator_disable(ctx->dvdd); + + return 0; +} + +static const struct drm_display_mode feiyang_default_mode = { + .clock = 55000, + + .hdisplay = 1024, + .hsync_start = 1024 + 310, + .hsync_end = 1024 + 310 + 20, + .htotal = 1024 + 310 + 20 + 90, + + .vdisplay = 600, + .vsync_start = 600 + 12, + .vsync_end = 600 + 12 + 2, + .vtotal = 600 + 12 + 2 + 21, + .vrefresh = 60, + + .type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED, +}; + +static int feiyang_get_modes(struct drm_panel *panel) +{ + struct drm_connector *connector = panel->connector; + struct feiyang *ctx = panel_to_feiyang(panel); + struct drm_display_mode *mode; + + mode = drm_mode_duplicate(panel->drm, &feiyang_default_mode); + if (!mode) { + DRM_DEV_ERROR(&ctx->dsi->dev, "failed to add mode %ux%ux@%u\n", + feiyang_default_mode.hdisplay, + feiyang_default_mode.vdisplay, + feiyang_default_mode.vrefresh); + return -ENOMEM; + } + + drm_mode_set_name(mode); + + drm_mode_probed_add(connector, mode); + + return 1; +} + +static const struct drm_panel_funcs feiyang_funcs = { + .disable = feiyang_disable, + .unprepare = feiyang_unprepare, + .prepare = feiyang_prepare, + .enable = feiyang_enable, + .get_modes = feiyang_get_modes, +}; + +static int feiyang_dsi_probe(struct mipi_dsi_device *dsi) +{ + struct feiyang *ctx; + int ret; + + ctx = devm_kzalloc(&dsi->dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + mipi_dsi_set_drvdata(dsi, ctx); + ctx->dsi = dsi; + + drm_panel_init(&ctx->panel); + ctx->panel.dev = &dsi->dev; + ctx->panel.funcs = &feiyang_funcs; + + ctx->dvdd = devm_regulator_get(&dsi->dev, "dvdd"); + if (IS_ERR(ctx->dvdd)) { + DRM_DEV_ERROR(&dsi->dev, "Couldn't get dvdd regulator\n"); + return PTR_ERR(ctx->dvdd); + } + + ctx->avdd = devm_regulator_get(&dsi->dev, "avdd"); + if (IS_ERR(ctx->avdd)) { + DRM_DEV_ERROR(&dsi->dev, "Couldn't get avdd regulator\n"); + return PTR_ERR(ctx->avdd); + } + + ctx->reset = devm_gpiod_get(&dsi->dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(ctx->reset)) { + DRM_DEV_ERROR(&dsi->dev, "Couldn't get our reset GPIO\n"); + return PTR_ERR(ctx->reset); + } + + ctx->backlight = devm_of_find_backlight(&dsi->dev); + if (IS_ERR(ctx->backlight)) + return PTR_ERR(ctx->backlight); + + ret = drm_panel_add(&ctx->panel); + if (ret < 0) + return ret; + + dsi->mode_flags = MIPI_DSI_MODE_VIDEO_BURST; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->lanes = 4; + + return mipi_dsi_attach(dsi); +} + +static int feiyang_dsi_remove(struct mipi_dsi_device *dsi) +{ + struct feiyang *ctx = mipi_dsi_get_drvdata(dsi); + + mipi_dsi_detach(dsi); + drm_panel_remove(&ctx->panel); + + return 0; +} + +static const struct of_device_id feiyang_of_match[] = { + { .compatible = "feiyang,fy07024di26a30d", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, feiyang_of_match); + +static struct mipi_dsi_driver feiyang_driver = { + .probe = feiyang_dsi_probe, + .remove = feiyang_dsi_remove, + .driver = { + .name = "feiyang-fy07024di26a30d", + .of_match_table = feiyang_of_match, + }, +}; +module_mipi_dsi_driver(feiyang_driver); + +MODULE_AUTHOR("Jagan Teki <jagan@amarulasolutions.com>"); +MODULE_DESCRIPTION("Feiyang FY07024DI26A30-D MIPI-DSI LCD panel"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c index 87fa316e1d7b..f27a7e426574 100644 --- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c +++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c @@ -67,15 +67,15 @@ struct otm8009a { }; static const struct drm_display_mode default_mode = { - .clock = 32729, + .clock = 29700, .hdisplay = 480, - .hsync_start = 480 + 120, - .hsync_end = 480 + 120 + 63, - .htotal = 480 + 120 + 63 + 120, + .hsync_start = 480 + 98, + .hsync_end = 480 + 98 + 32, + .htotal = 480 + 98 + 32 + 98, .vdisplay = 800, - .vsync_start = 800 + 12, - .vsync_end = 800 + 12 + 12, - .vtotal = 800 + 12 + 12 + 12, + .vsync_start = 800 + 15, + .vsync_end = 800 + 15 + 10, + .vtotal = 800 + 15 + 10 + 14, .vrefresh = 50, .flags = 0, .width_mm = 52, @@ -248,6 +248,9 @@ static int otm8009a_init_sequence(struct otm8009a *ctx) /* Send Command GRAM memory write (no parameters) */ dcs_write_seq(ctx, MIPI_DCS_WRITE_MEMORY_START); + /* Wait a short while to let the panel be ready before the 1st frame */ + mdelay(10); + return 0; } @@ -433,7 +436,8 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi) ctx->supply = devm_regulator_get(dev, "power"); if (IS_ERR(ctx->supply)) { ret = PTR_ERR(ctx->supply); - dev_err(dev, "failed to request regulator: %d\n", ret); + if (ret != -EPROBE_DEFER) + dev_err(dev, "failed to request regulator: %d\n", ret); return ret; } diff --git a/drivers/gpu/drm/panel/panel-raydium-rm68200.c b/drivers/gpu/drm/panel/panel-raydium-rm68200.c index 77593533abcd..14186827e591 100644 --- a/drivers/gpu/drm/panel/panel-raydium-rm68200.c +++ b/drivers/gpu/drm/panel/panel-raydium-rm68200.c @@ -383,7 +383,8 @@ static int rm68200_probe(struct mipi_dsi_device *dsi) ctx->supply = devm_regulator_get(dev, "power"); if (IS_ERR(ctx->supply)) { ret = PTR_ERR(ctx->supply); - dev_err(dev, "cannot get regulator: %d\n", ret); + if (ret != -EPROBE_DEFER) + dev_err(dev, "cannot get regulator: %d\n", ret); return ret; } diff --git a/drivers/gpu/drm/panel/panel-rocktech-jh057n00900.c b/drivers/gpu/drm/panel/panel-rocktech-jh057n00900.c new file mode 100644 index 000000000000..158a6d548068 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-rocktech-jh057n00900.c @@ -0,0 +1,386 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Rockteck jh057n00900 5.5" MIPI-DSI panel driver + * + * Copyright (C) Purism SPC 2019 + */ + +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> +#include <drm/drm_print.h> +#include <linux/backlight.h> +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/media-bus-format.h> +#include <linux/module.h> +#include <video/display_timing.h> +#include <video/mipi_display.h> + +#define DRV_NAME "panel-rocktech-jh057n00900" + +/* Manufacturer specific Commands send via DSI */ +#define ST7703_CMD_ALL_PIXEL_OFF 0x22 +#define ST7703_CMD_ALL_PIXEL_ON 0x23 +#define ST7703_CMD_SETDISP 0xB2 +#define ST7703_CMD_SETRGBIF 0xB3 +#define ST7703_CMD_SETCYC 0xB4 +#define ST7703_CMD_SETBGP 0xB5 +#define ST7703_CMD_SETVCOM 0xB6 +#define ST7703_CMD_SETOTP 0xB7 +#define ST7703_CMD_SETPOWER_EXT 0xB8 +#define ST7703_CMD_SETEXTC 0xB9 +#define ST7703_CMD_SETMIPI 0xBA +#define ST7703_CMD_SETVDC 0xBC +#define ST7703_CMD_SETSCR 0xC0 +#define ST7703_CMD_SETPOWER 0xC1 +#define ST7703_CMD_SETPANEL 0xCC +#define ST7703_CMD_SETGAMMA 0xE0 +#define ST7703_CMD_SETEQ 0xE3 +#define ST7703_CMD_SETGIP1 0xE9 +#define ST7703_CMD_SETGIP2 0xEA + +struct jh057n { + struct device *dev; + struct drm_panel panel; + struct gpio_desc *reset_gpio; + struct backlight_device *backlight; + bool prepared; + + struct dentry *debugfs; +}; + +static inline struct jh057n *panel_to_jh057n(struct drm_panel *panel) +{ + return container_of(panel, struct jh057n, panel); +} + +#define dsi_generic_write_seq(dsi, seq...) do { \ + static const u8 d[] = { seq }; \ + int ret; \ + ret = mipi_dsi_generic_write(dsi, d, ARRAY_SIZE(d)); \ + if (ret < 0) \ + return ret; \ + } while (0) + +static int jh057n_init_sequence(struct jh057n *ctx) +{ + struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev); + struct device *dev = ctx->dev; + int ret; + + /* + * Init sequence was supplied by the panel vendor. Most of the commands + * resemble the ST7703 but the number of parameters often don't match + * so it's likely a clone. + */ + dsi_generic_write_seq(dsi, ST7703_CMD_SETEXTC, + 0xF1, 0x12, 0x83); + dsi_generic_write_seq(dsi, ST7703_CMD_SETRGBIF, + 0x10, 0x10, 0x05, 0x05, 0x03, 0xFF, 0x00, 0x00, + 0x00, 0x00); + dsi_generic_write_seq(dsi, ST7703_CMD_SETSCR, + 0x73, 0x73, 0x50, 0x50, 0x00, 0x00, 0x08, 0x70, + 0x00); + dsi_generic_write_seq(dsi, ST7703_CMD_SETVDC, 0x4E); + dsi_generic_write_seq(dsi, ST7703_CMD_SETPANEL, 0x0B); + dsi_generic_write_seq(dsi, ST7703_CMD_SETCYC, 0x80); + dsi_generic_write_seq(dsi, ST7703_CMD_SETDISP, 0xF0, 0x12, 0x30); + dsi_generic_write_seq(dsi, ST7703_CMD_SETEQ, + 0x07, 0x07, 0x0B, 0x0B, 0x03, 0x0B, 0x00, 0x00, + 0x00, 0x00, 0xFF, 0x00, 0xC0, 0x10); + dsi_generic_write_seq(dsi, ST7703_CMD_SETBGP, 0x08, 0x08); + msleep(20); + + dsi_generic_write_seq(dsi, ST7703_CMD_SETVCOM, 0x3F, 0x3F); + dsi_generic_write_seq(dsi, 0xBF, 0x02, 0x11, 0x00); + dsi_generic_write_seq(dsi, ST7703_CMD_SETGIP1, + 0x82, 0x10, 0x06, 0x05, 0x9E, 0x0A, 0xA5, 0x12, + 0x31, 0x23, 0x37, 0x83, 0x04, 0xBC, 0x27, 0x38, + 0x0C, 0x00, 0x03, 0x00, 0x00, 0x00, 0x0C, 0x00, + 0x03, 0x00, 0x00, 0x00, 0x75, 0x75, 0x31, 0x88, + 0x88, 0x88, 0x88, 0x88, 0x88, 0x13, 0x88, 0x64, + 0x64, 0x20, 0x88, 0x88, 0x88, 0x88, 0x88, 0x88, + 0x02, 0x88, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00); + dsi_generic_write_seq(dsi, ST7703_CMD_SETGIP2, + 0x02, 0x21, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0x46, 0x02, 0x88, + 0x88, 0x88, 0x88, 0x88, 0x88, 0x64, 0x88, 0x13, + 0x57, 0x13, 0x88, 0x88, 0x88, 0x88, 0x88, 0x88, + 0x75, 0x88, 0x23, 0x14, 0x00, 0x00, 0x02, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x0A, + 0xA5, 0x00, 0x00, 0x00, 0x00); + dsi_generic_write_seq(dsi, ST7703_CMD_SETGAMMA, + 0x00, 0x09, 0x0E, 0x29, 0x2D, 0x3C, 0x41, 0x37, + 0x07, 0x0B, 0x0D, 0x10, 0x11, 0x0F, 0x10, 0x11, + 0x18, 0x00, 0x09, 0x0E, 0x29, 0x2D, 0x3C, 0x41, + 0x37, 0x07, 0x0B, 0x0D, 0x10, 0x11, 0x0F, 0x10, + 0x11, 0x18); + msleep(20); + + ret = mipi_dsi_dcs_exit_sleep_mode(dsi); + if (ret < 0) { + DRM_DEV_ERROR(dev, "Failed to exit sleep mode"); + return ret; + } + /* Panel is operational 120 msec after reset */ + msleep(60); + ret = mipi_dsi_dcs_set_display_on(dsi); + if (ret) + return ret; + + DRM_DEV_DEBUG_DRIVER(dev, "Panel init sequence done"); + return 0; +} + +static int jh057n_enable(struct drm_panel *panel) +{ + struct jh057n *ctx = panel_to_jh057n(panel); + + return backlight_enable(ctx->backlight); +} + +static int jh057n_disable(struct drm_panel *panel) +{ + struct jh057n *ctx = panel_to_jh057n(panel); + + return backlight_disable(ctx->backlight); +} + +static int jh057n_unprepare(struct drm_panel *panel) +{ + struct jh057n *ctx = panel_to_jh057n(panel); + struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev); + + if (!ctx->prepared) + return 0; + + mipi_dsi_dcs_set_display_off(dsi); + ctx->prepared = false; + + return 0; +} + +static int jh057n_prepare(struct drm_panel *panel) +{ + struct jh057n *ctx = panel_to_jh057n(panel); + int ret; + + if (ctx->prepared) + return 0; + + DRM_DEV_DEBUG_DRIVER(ctx->dev, "Resetting the panel."); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + usleep_range(20, 40); + gpiod_set_value_cansleep(ctx->reset_gpio, 0); + msleep(20); + + ret = jh057n_init_sequence(ctx); + if (ret < 0) { + DRM_DEV_ERROR(ctx->dev, "Panel init sequence failed: %d", ret); + return ret; + } + + ctx->prepared = true; + + return 0; +} + +static const struct drm_display_mode default_mode = { + .hdisplay = 720, + .hsync_start = 720 + 90, + .hsync_end = 720 + 90 + 20, + .htotal = 720 + 90 + 20 + 20, + .vdisplay = 1440, + .vsync_start = 1440 + 20, + .vsync_end = 1440 + 20 + 4, + .vtotal = 1440 + 20 + 4 + 12, + .vrefresh = 60, + .clock = 75276, + .flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC, + .width_mm = 65, + .height_mm = 130, +}; + +static int jh057n_get_modes(struct drm_panel *panel) +{ + struct jh057n *ctx = panel_to_jh057n(panel); + struct drm_display_mode *mode; + + mode = drm_mode_duplicate(panel->drm, &default_mode); + if (!mode) { + DRM_DEV_ERROR(ctx->dev, "Failed to add mode %ux%u@%u", + default_mode.hdisplay, default_mode.vdisplay, + default_mode.vrefresh); + return -ENOMEM; + } + + drm_mode_set_name(mode); + + mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; + panel->connector->display_info.width_mm = mode->width_mm; + panel->connector->display_info.height_mm = mode->height_mm; + drm_mode_probed_add(panel->connector, mode); + + return 1; +} + +static const struct drm_panel_funcs jh057n_drm_funcs = { + .disable = jh057n_disable, + .unprepare = jh057n_unprepare, + .prepare = jh057n_prepare, + .enable = jh057n_enable, + .get_modes = jh057n_get_modes, +}; + +static int allpixelson_set(void *data, u64 val) +{ + struct jh057n *ctx = data; + struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev); + + DRM_DEV_DEBUG_DRIVER(ctx->dev, "Setting all pixels on"); + dsi_generic_write_seq(dsi, ST7703_CMD_ALL_PIXEL_ON); + msleep(val * 1000); + /* Reset the panel to get video back */ + drm_panel_disable(&ctx->panel); + drm_panel_unprepare(&ctx->panel); + drm_panel_prepare(&ctx->panel); + drm_panel_enable(&ctx->panel); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(allpixelson_fops, NULL, + allpixelson_set, "%llu\n"); + +static int jh057n_debugfs_init(struct jh057n *ctx) +{ + struct dentry *f; + + ctx->debugfs = debugfs_create_dir(DRV_NAME, NULL); + if (!ctx->debugfs) + return -ENOMEM; + + f = debugfs_create_file("allpixelson", 0600, + ctx->debugfs, ctx, &allpixelson_fops); + if (!f) + return -ENOMEM; + + return 0; +} + +static void jh057n_debugfs_remove(struct jh057n *ctx) +{ + debugfs_remove_recursive(ctx->debugfs); + ctx->debugfs = NULL; +} + +static int jh057n_probe(struct mipi_dsi_device *dsi) +{ + struct device *dev = &dsi->dev; + struct jh057n *ctx; + int ret; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(ctx->reset_gpio)) { + DRM_DEV_ERROR(dev, "cannot get reset gpio"); + return PTR_ERR(ctx->reset_gpio); + } + + mipi_dsi_set_drvdata(dsi, ctx); + + ctx->dev = dev; + + dsi->lanes = 4; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | + MIPI_DSI_MODE_VIDEO_BURST | MIPI_DSI_MODE_VIDEO_SYNC_PULSE; + + ctx->backlight = devm_of_find_backlight(dev); + if (IS_ERR(ctx->backlight)) + return PTR_ERR(ctx->backlight); + + drm_panel_init(&ctx->panel); + ctx->panel.dev = dev; + ctx->panel.funcs = &jh057n_drm_funcs; + + drm_panel_add(&ctx->panel); + + ret = mipi_dsi_attach(dsi); + if (ret < 0) { + DRM_DEV_ERROR(dev, "mipi_dsi_attach failed. Is host ready?"); + drm_panel_remove(&ctx->panel); + return ret; + } + + DRM_DEV_INFO(dev, "%ux%u@%u %ubpp dsi %udl - ready", + default_mode.hdisplay, default_mode.vdisplay, + default_mode.vrefresh, + mipi_dsi_pixel_format_to_bpp(dsi->format), dsi->lanes); + + jh057n_debugfs_init(ctx); + return 0; +} + +static void jh057n_shutdown(struct mipi_dsi_device *dsi) +{ + struct jh057n *ctx = mipi_dsi_get_drvdata(dsi); + int ret; + + ret = jh057n_unprepare(&ctx->panel); + if (ret < 0) + DRM_DEV_ERROR(&dsi->dev, "Failed to unprepare panel: %d\n", + ret); + + ret = jh057n_disable(&ctx->panel); + if (ret < 0) + DRM_DEV_ERROR(&dsi->dev, "Failed to disable panel: %d\n", + ret); +} + +static int jh057n_remove(struct mipi_dsi_device *dsi) +{ + struct jh057n *ctx = mipi_dsi_get_drvdata(dsi); + int ret; + + jh057n_shutdown(dsi); + + ret = mipi_dsi_detach(dsi); + if (ret < 0) + DRM_DEV_ERROR(&dsi->dev, "Failed to detach from DSI host: %d\n", + ret); + + drm_panel_remove(&ctx->panel); + + jh057n_debugfs_remove(ctx); + + return 0; +} + +static const struct of_device_id jh057n_of_match[] = { + { .compatible = "rocktech,jh057n00900" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, jh057n_of_match); + +static struct mipi_dsi_driver jh057n_driver = { + .probe = jh057n_probe, + .remove = jh057n_remove, + .shutdown = jh057n_shutdown, + .driver = { + .name = DRV_NAME, + .of_match_table = jh057n_of_match, + }, +}; +module_mipi_dsi_driver(jh057n_driver); + +MODULE_AUTHOR("Guido Günther <agx@sigxcpu.org>"); +MODULE_DESCRIPTION("DRM driver for Rocktech JH057N00900 MIPI DSI panel"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig index 1e75196f9659..2cdf3b62d559 100644 --- a/drivers/gpu/drm/rockchip/Kconfig +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -77,4 +77,12 @@ config ROCKCHIP_RGB Some Rockchip CRTCs, like rv1108, can directly output parallel and serial RGB format to panel or connect to a conversion chip. say Y to enable its driver. + +config ROCKCHIP_RK3066_HDMI + bool "Rockchip specific extensions for RK3066 HDMI" + depends on DRM_ROCKCHIP + help + This selects support for Rockchip SoC specific extensions + for the RK3066 HDMI driver. If you want to enable + HDMI on RK3066 based SoC, you should select this option. endif diff --git a/drivers/gpu/drm/rockchip/Makefile b/drivers/gpu/drm/rockchip/Makefile index f6fc9d5dd0ad..524684ba7f6a 100644 --- a/drivers/gpu/drm/rockchip/Makefile +++ b/drivers/gpu/drm/rockchip/Makefile @@ -15,5 +15,6 @@ rockchipdrm-$(CONFIG_ROCKCHIP_DW_MIPI_DSI) += dw-mipi-dsi-rockchip.o rockchipdrm-$(CONFIG_ROCKCHIP_INNO_HDMI) += inno_hdmi.o rockchipdrm-$(CONFIG_ROCKCHIP_LVDS) += rockchip_lvds.o rockchipdrm-$(CONFIG_ROCKCHIP_RGB) += rockchip_rgb.o +rockchipdrm-$(CONFIG_ROCKCHIP_RK3066_HDMI) += rk3066_hdmi.o obj-$(CONFIG_DRM_ROCKCHIP) += rockchipdrm.o diff --git a/drivers/gpu/drm/rockchip/rk3066_hdmi.c b/drivers/gpu/drm/rockchip/rk3066_hdmi.c new file mode 100644 index 000000000000..85fc5f01f761 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rk3066_hdmi.c @@ -0,0 +1,876 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Zheng Yang <zhengyang@rock-chips.com> + */ + +#include <drm/drm_of.h> +#include <drm/drm_probe_helper.h> + +#include <linux/clk.h> +#include <linux/mfd/syscon.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> + +#include "rk3066_hdmi.h" + +#include "rockchip_drm_drv.h" +#include "rockchip_drm_vop.h" + +#define DEFAULT_PLLA_RATE 30000000 + +struct hdmi_data_info { + int vic; /* The CEA Video ID (VIC) of the current drm display mode. */ + bool sink_is_hdmi; + unsigned int enc_out_format; + unsigned int colorimetry; +}; + +struct rk3066_hdmi_i2c { + struct i2c_adapter adap; + + u8 ddc_addr; + u8 segment_addr; + u8 stat; + + struct mutex i2c_lock; /* For i2c operation. */ + struct completion cmpltn; +}; + +struct rk3066_hdmi { + struct device *dev; + struct drm_device *drm_dev; + struct regmap *grf_regmap; + int irq; + struct clk *hclk; + void __iomem *regs; + + struct drm_connector connector; + struct drm_encoder encoder; + + struct rk3066_hdmi_i2c *i2c; + struct i2c_adapter *ddc; + + unsigned int tmdsclk; + + struct hdmi_data_info hdmi_data; + struct drm_display_mode previous_mode; +}; + +#define to_rk3066_hdmi(x) container_of(x, struct rk3066_hdmi, x) + +static inline u8 hdmi_readb(struct rk3066_hdmi *hdmi, u16 offset) +{ + return readl_relaxed(hdmi->regs + offset); +} + +static inline void hdmi_writeb(struct rk3066_hdmi *hdmi, u16 offset, u32 val) +{ + writel_relaxed(val, hdmi->regs + offset); +} + +static inline void hdmi_modb(struct rk3066_hdmi *hdmi, u16 offset, + u32 msk, u32 val) +{ + u8 temp = hdmi_readb(hdmi, offset) & ~msk; + + temp |= val & msk; + hdmi_writeb(hdmi, offset, temp); +} + +static void rk3066_hdmi_i2c_init(struct rk3066_hdmi *hdmi) +{ + int ddc_bus_freq; + + ddc_bus_freq = (hdmi->tmdsclk >> 2) / HDMI_SCL_RATE; + + hdmi_writeb(hdmi, HDMI_DDC_BUS_FREQ_L, ddc_bus_freq & 0xFF); + hdmi_writeb(hdmi, HDMI_DDC_BUS_FREQ_H, (ddc_bus_freq >> 8) & 0xFF); + + /* Clear the EDID interrupt flag and mute the interrupt. */ + hdmi_modb(hdmi, HDMI_INTR_MASK1, HDMI_INTR_EDID_MASK, 0); + hdmi_writeb(hdmi, HDMI_INTR_STATUS1, HDMI_INTR_EDID_MASK); +} + +static inline u8 rk3066_hdmi_get_power_mode(struct rk3066_hdmi *hdmi) +{ + return hdmi_readb(hdmi, HDMI_SYS_CTRL) & HDMI_SYS_POWER_MODE_MASK; +} + +static void rk3066_hdmi_set_power_mode(struct rk3066_hdmi *hdmi, int mode) +{ + u8 current_mode, next_mode; + u8 i = 0; + + current_mode = rk3066_hdmi_get_power_mode(hdmi); + + DRM_DEV_DEBUG(hdmi->dev, "mode :%d\n", mode); + DRM_DEV_DEBUG(hdmi->dev, "current_mode :%d\n", current_mode); + + if (current_mode == mode) + return; + + do { + if (current_mode > mode) { + next_mode = current_mode / 2; + } else { + if (current_mode < HDMI_SYS_POWER_MODE_A) + next_mode = HDMI_SYS_POWER_MODE_A; + else + next_mode = current_mode * 2; + } + + DRM_DEV_DEBUG(hdmi->dev, "%d: next_mode :%d\n", i, next_mode); + + if (next_mode != HDMI_SYS_POWER_MODE_D) { + hdmi_modb(hdmi, HDMI_SYS_CTRL, + HDMI_SYS_POWER_MODE_MASK, next_mode); + } else { + hdmi_writeb(hdmi, HDMI_SYS_CTRL, + HDMI_SYS_POWER_MODE_D | + HDMI_SYS_PLL_RESET_MASK); + usleep_range(90, 100); + hdmi_writeb(hdmi, HDMI_SYS_CTRL, + HDMI_SYS_POWER_MODE_D | + HDMI_SYS_PLLB_RESET); + usleep_range(90, 100); + hdmi_writeb(hdmi, HDMI_SYS_CTRL, + HDMI_SYS_POWER_MODE_D); + } + current_mode = next_mode; + i = i + 1; + } while ((next_mode != mode) && (i < 5)); + + /* + * When the IP controller isn't configured with accurate video timing, + * DDC_CLK should be equal to the PLLA frequency, which is 30MHz, + * so we need to init the TMDS rate to the PCLK rate and reconfigure + * the DDC clock. + */ + if (mode < HDMI_SYS_POWER_MODE_D) + hdmi->tmdsclk = DEFAULT_PLLA_RATE; +} + +static int +rk3066_hdmi_upload_frame(struct rk3066_hdmi *hdmi, int setup_rc, + union hdmi_infoframe *frame, u32 frame_index, + u32 mask, u32 disable, u32 enable) +{ + if (mask) + hdmi_modb(hdmi, HDMI_CP_AUTO_SEND_CTRL, mask, disable); + + hdmi_writeb(hdmi, HDMI_CP_BUF_INDEX, frame_index); + + if (setup_rc >= 0) { + u8 packed_frame[HDMI_MAXIMUM_INFO_FRAME_SIZE]; + ssize_t rc, i; + + rc = hdmi_infoframe_pack(frame, packed_frame, + sizeof(packed_frame)); + if (rc < 0) + return rc; + + for (i = 0; i < rc; i++) + hdmi_writeb(hdmi, HDMI_CP_BUF_ACC_HB0 + i * 4, + packed_frame[i]); + + if (mask) + hdmi_modb(hdmi, HDMI_CP_AUTO_SEND_CTRL, mask, enable); + } + + return setup_rc; +} + +static int rk3066_hdmi_config_avi(struct rk3066_hdmi *hdmi, + struct drm_display_mode *mode) +{ + union hdmi_infoframe frame; + int rc; + + rc = drm_hdmi_avi_infoframe_from_display_mode(&frame.avi, + &hdmi->connector, mode); + + if (hdmi->hdmi_data.enc_out_format == HDMI_COLORSPACE_YUV444) + frame.avi.colorspace = HDMI_COLORSPACE_YUV444; + else if (hdmi->hdmi_data.enc_out_format == HDMI_COLORSPACE_YUV422) + frame.avi.colorspace = HDMI_COLORSPACE_YUV422; + else + frame.avi.colorspace = HDMI_COLORSPACE_RGB; + + frame.avi.colorimetry = hdmi->hdmi_data.colorimetry; + frame.avi.scan_mode = HDMI_SCAN_MODE_NONE; + + return rk3066_hdmi_upload_frame(hdmi, rc, &frame, + HDMI_INFOFRAME_AVI, 0, 0, 0); +} + +static int rk3066_hdmi_config_video_timing(struct rk3066_hdmi *hdmi, + struct drm_display_mode *mode) +{ + int value, vsync_offset; + + /* Set the details for the external polarity and interlace mode. */ + value = HDMI_EXT_VIDEO_SET_EN; + value |= mode->flags & DRM_MODE_FLAG_PHSYNC ? + HDMI_VIDEO_HSYNC_ACTIVE_HIGH : HDMI_VIDEO_HSYNC_ACTIVE_LOW; + value |= mode->flags & DRM_MODE_FLAG_PVSYNC ? + HDMI_VIDEO_VSYNC_ACTIVE_HIGH : HDMI_VIDEO_VSYNC_ACTIVE_LOW; + value |= mode->flags & DRM_MODE_FLAG_INTERLACE ? + HDMI_VIDEO_MODE_INTERLACE : HDMI_VIDEO_MODE_PROGRESSIVE; + + if (hdmi->hdmi_data.vic == 2 || hdmi->hdmi_data.vic == 3) + vsync_offset = 6; + else + vsync_offset = 0; + + value |= vsync_offset << HDMI_VIDEO_VSYNC_OFFSET_SHIFT; + hdmi_writeb(hdmi, HDMI_EXT_VIDEO_PARA, value); + + /* Set the details for the external video timing. */ + value = mode->htotal; + hdmi_writeb(hdmi, HDMI_EXT_HTOTAL_L, value & 0xFF); + hdmi_writeb(hdmi, HDMI_EXT_HTOTAL_H, (value >> 8) & 0xFF); + + value = mode->htotal - mode->hdisplay; + hdmi_writeb(hdmi, HDMI_EXT_HBLANK_L, value & 0xFF); + hdmi_writeb(hdmi, HDMI_EXT_HBLANK_H, (value >> 8) & 0xFF); + + value = mode->htotal - mode->hsync_start; + hdmi_writeb(hdmi, HDMI_EXT_HDELAY_L, value & 0xFF); + hdmi_writeb(hdmi, HDMI_EXT_HDELAY_H, (value >> 8) & 0xFF); + + value = mode->hsync_end - mode->hsync_start; + hdmi_writeb(hdmi, HDMI_EXT_HDURATION_L, value & 0xFF); + hdmi_writeb(hdmi, HDMI_EXT_HDURATION_H, (value >> 8) & 0xFF); + + value = mode->vtotal; + hdmi_writeb(hdmi, HDMI_EXT_VTOTAL_L, value & 0xFF); + hdmi_writeb(hdmi, HDMI_EXT_VTOTAL_H, (value >> 8) & 0xFF); + + value = mode->vtotal - mode->vdisplay; + hdmi_writeb(hdmi, HDMI_EXT_VBLANK_L, value & 0xFF); + + value = mode->vtotal - mode->vsync_start + vsync_offset; + hdmi_writeb(hdmi, HDMI_EXT_VDELAY, value & 0xFF); + + value = mode->vsync_end - mode->vsync_start; + hdmi_writeb(hdmi, HDMI_EXT_VDURATION, value & 0xFF); + + return 0; +} + +static void +rk3066_hdmi_phy_write(struct rk3066_hdmi *hdmi, u16 offset, u8 value) +{ + hdmi_writeb(hdmi, offset, value); + hdmi_modb(hdmi, HDMI_SYS_CTRL, + HDMI_SYS_PLL_RESET_MASK, HDMI_SYS_PLL_RESET); + usleep_range(90, 100); + hdmi_modb(hdmi, HDMI_SYS_CTRL, HDMI_SYS_PLL_RESET_MASK, 0); + usleep_range(900, 1000); +} + +static void rk3066_hdmi_config_phy(struct rk3066_hdmi *hdmi) +{ + /* TMDS uses the same frequency as dclk. */ + hdmi_writeb(hdmi, HDMI_DEEP_COLOR_MODE, 0x22); + + /* + * The semi-public documentation does not describe the hdmi registers + * used by the function rk3066_hdmi_phy_write(), so we keep using + * these magic values for now. + */ + if (hdmi->tmdsclk > 100000000) { + rk3066_hdmi_phy_write(hdmi, 0x158, 0x0E); + rk3066_hdmi_phy_write(hdmi, 0x15c, 0x00); + rk3066_hdmi_phy_write(hdmi, 0x160, 0x60); + rk3066_hdmi_phy_write(hdmi, 0x164, 0x00); + rk3066_hdmi_phy_write(hdmi, 0x168, 0xDA); + rk3066_hdmi_phy_write(hdmi, 0x16c, 0xA1); + rk3066_hdmi_phy_write(hdmi, 0x170, 0x0e); + rk3066_hdmi_phy_write(hdmi, 0x174, 0x22); + rk3066_hdmi_phy_write(hdmi, 0x178, 0x00); + } else if (hdmi->tmdsclk > 50000000) { + rk3066_hdmi_phy_write(hdmi, 0x158, 0x06); + rk3066_hdmi_phy_write(hdmi, 0x15c, 0x00); + rk3066_hdmi_phy_write(hdmi, 0x160, 0x60); + rk3066_hdmi_phy_write(hdmi, 0x164, 0x00); + rk3066_hdmi_phy_write(hdmi, 0x168, 0xCA); + rk3066_hdmi_phy_write(hdmi, 0x16c, 0xA3); + rk3066_hdmi_phy_write(hdmi, 0x170, 0x0e); + rk3066_hdmi_phy_write(hdmi, 0x174, 0x20); + rk3066_hdmi_phy_write(hdmi, 0x178, 0x00); + } else { + rk3066_hdmi_phy_write(hdmi, 0x158, 0x02); + rk3066_hdmi_phy_write(hdmi, 0x15c, 0x00); + rk3066_hdmi_phy_write(hdmi, 0x160, 0x60); + rk3066_hdmi_phy_write(hdmi, 0x164, 0x00); + rk3066_hdmi_phy_write(hdmi, 0x168, 0xC2); + rk3066_hdmi_phy_write(hdmi, 0x16c, 0xA2); + rk3066_hdmi_phy_write(hdmi, 0x170, 0x0e); + rk3066_hdmi_phy_write(hdmi, 0x174, 0x20); + rk3066_hdmi_phy_write(hdmi, 0x178, 0x00); + } +} + +static int rk3066_hdmi_setup(struct rk3066_hdmi *hdmi, + struct drm_display_mode *mode) +{ + hdmi->hdmi_data.vic = drm_match_cea_mode(mode); + hdmi->hdmi_data.enc_out_format = HDMI_COLORSPACE_RGB; + + if (hdmi->hdmi_data.vic == 6 || hdmi->hdmi_data.vic == 7 || + hdmi->hdmi_data.vic == 21 || hdmi->hdmi_data.vic == 22 || + hdmi->hdmi_data.vic == 2 || hdmi->hdmi_data.vic == 3 || + hdmi->hdmi_data.vic == 17 || hdmi->hdmi_data.vic == 18) + hdmi->hdmi_data.colorimetry = HDMI_COLORIMETRY_ITU_601; + else + hdmi->hdmi_data.colorimetry = HDMI_COLORIMETRY_ITU_709; + + hdmi->tmdsclk = mode->clock * 1000; + + /* Mute video and audio output. */ + hdmi_modb(hdmi, HDMI_VIDEO_CTRL2, HDMI_VIDEO_AUDIO_DISABLE_MASK, + HDMI_AUDIO_DISABLE | HDMI_VIDEO_DISABLE); + + /* Set power state to mode B. */ + if (rk3066_hdmi_get_power_mode(hdmi) != HDMI_SYS_POWER_MODE_B) + rk3066_hdmi_set_power_mode(hdmi, HDMI_SYS_POWER_MODE_B); + + /* Input video mode is RGB 24 bit. Use external data enable signal. */ + hdmi_modb(hdmi, HDMI_AV_CTRL1, + HDMI_VIDEO_DE_MASK, HDMI_VIDEO_EXTERNAL_DE); + hdmi_writeb(hdmi, HDMI_VIDEO_CTRL1, + HDMI_VIDEO_OUTPUT_RGB444 | + HDMI_VIDEO_INPUT_DATA_DEPTH_8BIT | + HDMI_VIDEO_INPUT_COLOR_RGB); + hdmi_writeb(hdmi, HDMI_DEEP_COLOR_MODE, 0x20); + + rk3066_hdmi_config_video_timing(hdmi, mode); + + if (hdmi->hdmi_data.sink_is_hdmi) { + hdmi_modb(hdmi, HDMI_HDCP_CTRL, HDMI_VIDEO_MODE_MASK, + HDMI_VIDEO_MODE_HDMI); + rk3066_hdmi_config_avi(hdmi, mode); + } else { + hdmi_modb(hdmi, HDMI_HDCP_CTRL, HDMI_VIDEO_MODE_MASK, 0); + } + + rk3066_hdmi_config_phy(hdmi); + + rk3066_hdmi_set_power_mode(hdmi, HDMI_SYS_POWER_MODE_E); + + /* + * When the IP controller is configured with accurate video + * timing, the TMDS clock source should be switched to + * DCLK_LCDC, so we need to init the TMDS rate to the pixel mode + * clock rate and reconfigure the DDC clock. + */ + rk3066_hdmi_i2c_init(hdmi); + + /* Unmute video output. */ + hdmi_modb(hdmi, HDMI_VIDEO_CTRL2, + HDMI_VIDEO_AUDIO_DISABLE_MASK, HDMI_AUDIO_DISABLE); + return 0; +} + +static void +rk3066_hdmi_encoder_mode_set(struct drm_encoder *encoder, + struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) +{ + struct rk3066_hdmi *hdmi = to_rk3066_hdmi(encoder); + + /* Store the display mode for plugin/DPMS poweron events. */ + memcpy(&hdmi->previous_mode, adj_mode, sizeof(hdmi->previous_mode)); +} + +static void rk3066_hdmi_encoder_enable(struct drm_encoder *encoder) +{ + struct rk3066_hdmi *hdmi = to_rk3066_hdmi(encoder); + int mux, val; + + mux = drm_of_encoder_active_endpoint_id(hdmi->dev->of_node, encoder); + if (mux) + val = (HDMI_VIDEO_SEL << 16) | HDMI_VIDEO_SEL; + else + val = HDMI_VIDEO_SEL << 16; + + regmap_write(hdmi->grf_regmap, GRF_SOC_CON0, val); + + DRM_DEV_DEBUG(hdmi->dev, "hdmi encoder enable select: vop%s\n", + (mux) ? "1" : "0"); + + rk3066_hdmi_setup(hdmi, &hdmi->previous_mode); +} + +static void rk3066_hdmi_encoder_disable(struct drm_encoder *encoder) +{ + struct rk3066_hdmi *hdmi = to_rk3066_hdmi(encoder); + + DRM_DEV_DEBUG(hdmi->dev, "hdmi encoder disable\n"); + + if (rk3066_hdmi_get_power_mode(hdmi) == HDMI_SYS_POWER_MODE_E) { + hdmi_writeb(hdmi, HDMI_VIDEO_CTRL2, + HDMI_VIDEO_AUDIO_DISABLE_MASK); + hdmi_modb(hdmi, HDMI_VIDEO_CTRL2, + HDMI_AUDIO_CP_LOGIC_RESET_MASK, + HDMI_AUDIO_CP_LOGIC_RESET); + usleep_range(500, 510); + } + rk3066_hdmi_set_power_mode(hdmi, HDMI_SYS_POWER_MODE_A); +} + +static bool +rk3066_hdmi_encoder_mode_fixup(struct drm_encoder *encoder, + const struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) +{ + return true; +} + +static int +rk3066_hdmi_encoder_atomic_check(struct drm_encoder *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state); + + s->output_mode = ROCKCHIP_OUT_MODE_P888; + s->output_type = DRM_MODE_CONNECTOR_HDMIA; + + return 0; +} + +static const +struct drm_encoder_helper_funcs rk3066_hdmi_encoder_helper_funcs = { + .enable = rk3066_hdmi_encoder_enable, + .disable = rk3066_hdmi_encoder_disable, + .mode_fixup = rk3066_hdmi_encoder_mode_fixup, + .mode_set = rk3066_hdmi_encoder_mode_set, + .atomic_check = rk3066_hdmi_encoder_atomic_check, +}; + +static const struct drm_encoder_funcs rk3066_hdmi_encoder_funcs = { + .destroy = drm_encoder_cleanup, +}; + +static enum drm_connector_status +rk3066_hdmi_connector_detect(struct drm_connector *connector, bool force) +{ + struct rk3066_hdmi *hdmi = to_rk3066_hdmi(connector); + + return (hdmi_readb(hdmi, HDMI_HPG_MENS_STA) & HDMI_HPG_IN_STATUS_HIGH) ? + connector_status_connected : connector_status_disconnected; +} + +static int rk3066_hdmi_connector_get_modes(struct drm_connector *connector) +{ + struct rk3066_hdmi *hdmi = to_rk3066_hdmi(connector); + struct edid *edid; + int ret = 0; + + if (!hdmi->ddc) + return 0; + + edid = drm_get_edid(connector, hdmi->ddc); + if (edid) { + hdmi->hdmi_data.sink_is_hdmi = drm_detect_hdmi_monitor(edid); + drm_connector_update_edid_property(connector, edid); + ret = drm_add_edid_modes(connector, edid); + kfree(edid); + } + + return ret; +} + +static enum drm_mode_status +rk3066_hdmi_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + u32 vic = drm_match_cea_mode(mode); + + if (vic > 1) + return MODE_OK; + else + return MODE_BAD; +} + +static struct drm_encoder * +rk3066_hdmi_connector_best_encoder(struct drm_connector *connector) +{ + struct rk3066_hdmi *hdmi = to_rk3066_hdmi(connector); + + return &hdmi->encoder; +} + +static int +rk3066_hdmi_probe_single_connector_modes(struct drm_connector *connector, + uint32_t maxX, uint32_t maxY) +{ + if (maxX > 1920) + maxX = 1920; + if (maxY > 1080) + maxY = 1080; + + return drm_helper_probe_single_connector_modes(connector, maxX, maxY); +} + +static void rk3066_hdmi_connector_destroy(struct drm_connector *connector) +{ + drm_connector_unregister(connector); + drm_connector_cleanup(connector); +} + +static const struct drm_connector_funcs rk3066_hdmi_connector_funcs = { + .fill_modes = rk3066_hdmi_probe_single_connector_modes, + .detect = rk3066_hdmi_connector_detect, + .destroy = rk3066_hdmi_connector_destroy, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static const +struct drm_connector_helper_funcs rk3066_hdmi_connector_helper_funcs = { + .get_modes = rk3066_hdmi_connector_get_modes, + .mode_valid = rk3066_hdmi_connector_mode_valid, + .best_encoder = rk3066_hdmi_connector_best_encoder, +}; + +static int +rk3066_hdmi_register(struct drm_device *drm, struct rk3066_hdmi *hdmi) +{ + struct drm_encoder *encoder = &hdmi->encoder; + struct device *dev = hdmi->dev; + + encoder->possible_crtcs = + drm_of_find_possible_crtcs(drm, dev->of_node); + + /* + * If we failed to find the CRTC(s) which this encoder is + * supposed to be connected to, it's because the CRTC has + * not been registered yet. Defer probing, and hope that + * the required CRTC is added later. + */ + if (encoder->possible_crtcs == 0) + return -EPROBE_DEFER; + + drm_encoder_helper_add(encoder, &rk3066_hdmi_encoder_helper_funcs); + drm_encoder_init(drm, encoder, &rk3066_hdmi_encoder_funcs, + DRM_MODE_ENCODER_TMDS, NULL); + + hdmi->connector.polled = DRM_CONNECTOR_POLL_HPD; + + drm_connector_helper_add(&hdmi->connector, + &rk3066_hdmi_connector_helper_funcs); + drm_connector_init(drm, &hdmi->connector, + &rk3066_hdmi_connector_funcs, + DRM_MODE_CONNECTOR_HDMIA); + + drm_connector_attach_encoder(&hdmi->connector, encoder); + + return 0; +} + +static irqreturn_t rk3066_hdmi_hardirq(int irq, void *dev_id) +{ + struct rk3066_hdmi *hdmi = dev_id; + irqreturn_t ret = IRQ_NONE; + u8 interrupt; + + if (rk3066_hdmi_get_power_mode(hdmi) == HDMI_SYS_POWER_MODE_A) + hdmi_writeb(hdmi, HDMI_SYS_CTRL, HDMI_SYS_POWER_MODE_B); + + interrupt = hdmi_readb(hdmi, HDMI_INTR_STATUS1); + if (interrupt) + hdmi_writeb(hdmi, HDMI_INTR_STATUS1, interrupt); + + if (interrupt & HDMI_INTR_EDID_MASK) { + hdmi->i2c->stat = interrupt; + complete(&hdmi->i2c->cmpltn); + } + + if (interrupt & (HDMI_INTR_HOTPLUG | HDMI_INTR_MSENS)) + ret = IRQ_WAKE_THREAD; + + return ret; +} + +static irqreturn_t rk3066_hdmi_irq(int irq, void *dev_id) +{ + struct rk3066_hdmi *hdmi = dev_id; + + drm_helper_hpd_irq_event(hdmi->connector.dev); + + return IRQ_HANDLED; +} + +static int rk3066_hdmi_i2c_read(struct rk3066_hdmi *hdmi, struct i2c_msg *msgs) +{ + int length = msgs->len; + u8 *buf = msgs->buf; + int ret; + + ret = wait_for_completion_timeout(&hdmi->i2c->cmpltn, HZ / 10); + if (!ret || hdmi->i2c->stat & HDMI_INTR_EDID_ERR) + return -EAGAIN; + + while (length--) + *buf++ = hdmi_readb(hdmi, HDMI_DDC_READ_FIFO_ADDR); + + return 0; +} + +static int rk3066_hdmi_i2c_write(struct rk3066_hdmi *hdmi, struct i2c_msg *msgs) +{ + /* + * The DDC module only supports read EDID message, so + * we assume that each word write to this i2c adapter + * should be the offset of the EDID word address. + */ + if (msgs->len != 1 || + (msgs->addr != DDC_ADDR && msgs->addr != DDC_SEGMENT_ADDR)) + return -EINVAL; + + reinit_completion(&hdmi->i2c->cmpltn); + + if (msgs->addr == DDC_SEGMENT_ADDR) + hdmi->i2c->segment_addr = msgs->buf[0]; + if (msgs->addr == DDC_ADDR) + hdmi->i2c->ddc_addr = msgs->buf[0]; + + /* Set edid word address 0x00/0x80. */ + hdmi_writeb(hdmi, HDMI_EDID_WORD_ADDR, hdmi->i2c->ddc_addr); + + /* Set edid segment pointer. */ + hdmi_writeb(hdmi, HDMI_EDID_SEGMENT_POINTER, hdmi->i2c->segment_addr); + + return 0; +} + +static int rk3066_hdmi_i2c_xfer(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num) +{ + struct rk3066_hdmi *hdmi = i2c_get_adapdata(adap); + struct rk3066_hdmi_i2c *i2c = hdmi->i2c; + int i, ret = 0; + + mutex_lock(&i2c->i2c_lock); + + rk3066_hdmi_i2c_init(hdmi); + + /* Unmute HDMI EDID interrupt. */ + hdmi_modb(hdmi, HDMI_INTR_MASK1, + HDMI_INTR_EDID_MASK, HDMI_INTR_EDID_MASK); + i2c->stat = 0; + + for (i = 0; i < num; i++) { + DRM_DEV_DEBUG(hdmi->dev, + "xfer: num: %d/%d, len: %d, flags: %#x\n", + i + 1, num, msgs[i].len, msgs[i].flags); + + if (msgs[i].flags & I2C_M_RD) + ret = rk3066_hdmi_i2c_read(hdmi, &msgs[i]); + else + ret = rk3066_hdmi_i2c_write(hdmi, &msgs[i]); + + if (ret < 0) + break; + } + + if (!ret) + ret = num; + + /* Mute HDMI EDID interrupt. */ + hdmi_modb(hdmi, HDMI_INTR_MASK1, HDMI_INTR_EDID_MASK, 0); + + mutex_unlock(&i2c->i2c_lock); + + return ret; +} + +static u32 rk3066_hdmi_i2c_func(struct i2c_adapter *adapter) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; +} + +static const struct i2c_algorithm rk3066_hdmi_algorithm = { + .master_xfer = rk3066_hdmi_i2c_xfer, + .functionality = rk3066_hdmi_i2c_func, +}; + +static struct i2c_adapter *rk3066_hdmi_i2c_adapter(struct rk3066_hdmi *hdmi) +{ + struct i2c_adapter *adap; + struct rk3066_hdmi_i2c *i2c; + int ret; + + i2c = devm_kzalloc(hdmi->dev, sizeof(*i2c), GFP_KERNEL); + if (!i2c) + return ERR_PTR(-ENOMEM); + + mutex_init(&i2c->i2c_lock); + init_completion(&i2c->cmpltn); + + adap = &i2c->adap; + adap->class = I2C_CLASS_DDC; + adap->owner = THIS_MODULE; + adap->dev.parent = hdmi->dev; + adap->dev.of_node = hdmi->dev->of_node; + adap->algo = &rk3066_hdmi_algorithm; + strlcpy(adap->name, "RK3066 HDMI", sizeof(adap->name)); + i2c_set_adapdata(adap, hdmi); + + ret = i2c_add_adapter(adap); + if (ret) { + DRM_DEV_ERROR(hdmi->dev, "cannot add %s I2C adapter\n", + adap->name); + devm_kfree(hdmi->dev, i2c); + return ERR_PTR(ret); + } + + hdmi->i2c = i2c; + + DRM_DEV_DEBUG(hdmi->dev, "registered %s I2C bus driver\n", adap->name); + + return adap; +} + +static int rk3066_hdmi_bind(struct device *dev, struct device *master, + void *data) +{ + struct platform_device *pdev = to_platform_device(dev); + struct drm_device *drm = data; + struct rk3066_hdmi *hdmi; + struct resource *iores; + int irq; + int ret; + + hdmi = devm_kzalloc(dev, sizeof(*hdmi), GFP_KERNEL); + if (!hdmi) + return -ENOMEM; + + hdmi->dev = dev; + hdmi->drm_dev = drm; + + iores = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!iores) + return -ENXIO; + + hdmi->regs = devm_ioremap_resource(dev, iores); + if (IS_ERR(hdmi->regs)) + return PTR_ERR(hdmi->regs); + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + hdmi->hclk = devm_clk_get(dev, "hclk"); + if (IS_ERR(hdmi->hclk)) { + DRM_DEV_ERROR(dev, "unable to get HDMI hclk clock\n"); + return PTR_ERR(hdmi->hclk); + } + + ret = clk_prepare_enable(hdmi->hclk); + if (ret) { + DRM_DEV_ERROR(dev, "cannot enable HDMI hclk clock: %d\n", ret); + return ret; + } + + hdmi->grf_regmap = syscon_regmap_lookup_by_phandle(dev->of_node, + "rockchip,grf"); + if (IS_ERR(hdmi->grf_regmap)) { + DRM_DEV_ERROR(dev, "unable to get rockchip,grf\n"); + ret = PTR_ERR(hdmi->grf_regmap); + goto err_disable_hclk; + } + + /* internal hclk = hdmi_hclk / 25 */ + hdmi_writeb(hdmi, HDMI_INTERNAL_CLK_DIVIDER, 25); + + hdmi->ddc = rk3066_hdmi_i2c_adapter(hdmi); + if (IS_ERR(hdmi->ddc)) { + ret = PTR_ERR(hdmi->ddc); + hdmi->ddc = NULL; + goto err_disable_hclk; + } + + rk3066_hdmi_set_power_mode(hdmi, HDMI_SYS_POWER_MODE_B); + usleep_range(999, 1000); + hdmi_writeb(hdmi, HDMI_INTR_MASK1, HDMI_INTR_HOTPLUG); + hdmi_writeb(hdmi, HDMI_INTR_MASK2, 0); + hdmi_writeb(hdmi, HDMI_INTR_MASK3, 0); + hdmi_writeb(hdmi, HDMI_INTR_MASK4, 0); + rk3066_hdmi_set_power_mode(hdmi, HDMI_SYS_POWER_MODE_A); + + ret = rk3066_hdmi_register(drm, hdmi); + if (ret) + goto err_disable_i2c; + + dev_set_drvdata(dev, hdmi); + + ret = devm_request_threaded_irq(dev, irq, rk3066_hdmi_hardirq, + rk3066_hdmi_irq, IRQF_SHARED, + dev_name(dev), hdmi); + if (ret) { + DRM_DEV_ERROR(dev, "failed to request hdmi irq: %d\n", ret); + goto err_cleanup_hdmi; + } + + return 0; + +err_cleanup_hdmi: + hdmi->connector.funcs->destroy(&hdmi->connector); + hdmi->encoder.funcs->destroy(&hdmi->encoder); +err_disable_i2c: + i2c_put_adapter(hdmi->ddc); +err_disable_hclk: + clk_disable_unprepare(hdmi->hclk); + + return ret; +} + +static void rk3066_hdmi_unbind(struct device *dev, struct device *master, + void *data) +{ + struct rk3066_hdmi *hdmi = dev_get_drvdata(dev); + + hdmi->connector.funcs->destroy(&hdmi->connector); + hdmi->encoder.funcs->destroy(&hdmi->encoder); + + i2c_put_adapter(hdmi->ddc); + clk_disable_unprepare(hdmi->hclk); +} + +static const struct component_ops rk3066_hdmi_ops = { + .bind = rk3066_hdmi_bind, + .unbind = rk3066_hdmi_unbind, +}; + +static int rk3066_hdmi_probe(struct platform_device *pdev) +{ + return component_add(&pdev->dev, &rk3066_hdmi_ops); +} + +static int rk3066_hdmi_remove(struct platform_device *pdev) +{ + component_del(&pdev->dev, &rk3066_hdmi_ops); + + return 0; +} + +static const struct of_device_id rk3066_hdmi_dt_ids[] = { + { .compatible = "rockchip,rk3066-hdmi" }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, rk3066_hdmi_dt_ids); + +struct platform_driver rk3066_hdmi_driver = { + .probe = rk3066_hdmi_probe, + .remove = rk3066_hdmi_remove, + .driver = { + .name = "rockchip-rk3066-hdmi", + .of_match_table = rk3066_hdmi_dt_ids, + }, +}; diff --git a/drivers/gpu/drm/rockchip/rk3066_hdmi.h b/drivers/gpu/drm/rockchip/rk3066_hdmi.h new file mode 100644 index 000000000000..39a31c62a428 --- /dev/null +++ b/drivers/gpu/drm/rockchip/rk3066_hdmi.h @@ -0,0 +1,229 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Zheng Yang <zhengyang@rock-chips.com> + */ + +#ifndef __RK3066_HDMI_H__ +#define __RK3066_HDMI_H__ + +#define GRF_SOC_CON0 0x150 +#define HDMI_VIDEO_SEL BIT(14) + +#define DDC_SEGMENT_ADDR 0x30 +#define HDMI_SCL_RATE (50 * 1000) +#define HDMI_MAXIMUM_INFO_FRAME_SIZE 0x11 + +#define N_32K 0x1000 +#define N_441K 0x1880 +#define N_882K 0x3100 +#define N_1764K 0x6200 +#define N_48K 0x1800 +#define N_96K 0x3000 +#define N_192K 0x6000 + +#define HDMI_SYS_CTRL 0x000 +#define HDMI_LR_SWAP_N3 0x004 +#define HDMI_N2 0x008 +#define HDMI_N1 0x00c +#define HDMI_SPDIF_FS_CTS_INT3 0x010 +#define HDMI_CTS_INT2 0x014 +#define HDMI_CTS_INT1 0x018 +#define HDMI_CTS_EXT3 0x01c +#define HDMI_CTS_EXT2 0x020 +#define HDMI_CTS_EXT1 0x024 +#define HDMI_AUDIO_CTRL1 0x028 +#define HDMI_AUDIO_CTRL2 0x02c +#define HDMI_I2S_AUDIO_CTRL 0x030 +#define HDMI_I2S_SWAP 0x040 +#define HDMI_AUDIO_STA_BIT_CTRL1 0x044 +#define HDMI_AUDIO_STA_BIT_CTRL2 0x048 +#define HDMI_AUDIO_SRC_NUM_AND_LENGTH 0x050 +#define HDMI_AV_CTRL1 0x054 +#define HDMI_VIDEO_CTRL1 0x058 +#define HDMI_DEEP_COLOR_MODE 0x05c + +#define HDMI_EXT_VIDEO_PARA 0x0c0 +#define HDMI_EXT_HTOTAL_L 0x0c4 +#define HDMI_EXT_HTOTAL_H 0x0c8 +#define HDMI_EXT_HBLANK_L 0x0cc +#define HDMI_EXT_HBLANK_H 0x0d0 +#define HDMI_EXT_HDELAY_L 0x0d4 +#define HDMI_EXT_HDELAY_H 0x0d8 +#define HDMI_EXT_HDURATION_L 0x0dc +#define HDMI_EXT_HDURATION_H 0x0e0 +#define HDMI_EXT_VTOTAL_L 0x0e4 +#define HDMI_EXT_VTOTAL_H 0x0e8 +#define HDMI_AV_CTRL2 0x0ec +#define HDMI_EXT_VBLANK_L 0x0f4 +#define HDMI_EXT_VBLANK_H 0x10c +#define HDMI_EXT_VDELAY 0x0f8 +#define HDMI_EXT_VDURATION 0x0fc + +#define HDMI_CP_MANU_SEND_CTRL 0x100 +#define HDMI_CP_AUTO_SEND_CTRL 0x104 +#define HDMI_AUTO_CHECKSUM_OPT 0x108 + +#define HDMI_VIDEO_CTRL2 0x114 + +#define HDMI_PHY_OPTION 0x144 + +#define HDMI_CP_BUF_INDEX 0x17c +#define HDMI_CP_BUF_ACC_HB0 0x180 +#define HDMI_CP_BUF_ACC_HB1 0x184 +#define HDMI_CP_BUF_ACC_HB2 0x188 +#define HDMI_CP_BUF_ACC_PB0 0x18c + +#define HDMI_DDC_READ_FIFO_ADDR 0x200 +#define HDMI_DDC_BUS_FREQ_L 0x204 +#define HDMI_DDC_BUS_FREQ_H 0x208 +#define HDMI_DDC_BUS_CTRL 0x2dc +#define HDMI_DDC_I2C_LEN 0x278 +#define HDMI_DDC_I2C_OFFSET 0x280 +#define HDMI_DDC_I2C_CTRL 0x284 +#define HDMI_DDC_I2C_READ_BUF0 0x288 +#define HDMI_DDC_I2C_READ_BUF1 0x28c +#define HDMI_DDC_I2C_READ_BUF2 0x290 +#define HDMI_DDC_I2C_READ_BUF3 0x294 +#define HDMI_DDC_I2C_WRITE_BUF0 0x298 +#define HDMI_DDC_I2C_WRITE_BUF1 0x29c +#define HDMI_DDC_I2C_WRITE_BUF2 0x2a0 +#define HDMI_DDC_I2C_WRITE_BUF3 0x2a4 +#define HDMI_DDC_I2C_WRITE_BUF4 0x2ac +#define HDMI_DDC_I2C_WRITE_BUF5 0x2b0 +#define HDMI_DDC_I2C_WRITE_BUF6 0x2b4 + +#define HDMI_INTR_MASK1 0x248 +#define HDMI_INTR_MASK2 0x24c +#define HDMI_INTR_STATUS1 0x250 +#define HDMI_INTR_STATUS2 0x254 +#define HDMI_INTR_MASK3 0x258 +#define HDMI_INTR_MASK4 0x25c +#define HDMI_INTR_STATUS3 0x260 +#define HDMI_INTR_STATUS4 0x264 + +#define HDMI_HDCP_CTRL 0x2bc + +#define HDMI_EDID_SEGMENT_POINTER 0x310 +#define HDMI_EDID_WORD_ADDR 0x314 +#define HDMI_EDID_FIFO_ADDR 0x318 + +#define HDMI_HPG_MENS_STA 0x37c + +#define HDMI_INTERNAL_CLK_DIVIDER 0x800 + +enum { + /* HDMI_SYS_CTRL */ + HDMI_SYS_POWER_MODE_MASK = 0xf0, + HDMI_SYS_POWER_MODE_A = 0x10, + HDMI_SYS_POWER_MODE_B = 0x20, + HDMI_SYS_POWER_MODE_D = 0x40, + HDMI_SYS_POWER_MODE_E = 0x80, + HDMI_SYS_PLL_RESET_MASK = 0x0c, + HDMI_SYS_PLL_RESET = 0x0c, + HDMI_SYS_PLLB_RESET = 0x08, + + /* HDMI_LR_SWAP_N3 */ + HDMI_AUDIO_LR_SWAP_MASK = 0xf0, + HDMI_AUDIO_LR_SWAP_SUBPACKET0 = 0x10, + HDMI_AUDIO_LR_SWAP_SUBPACKET1 = 0x20, + HDMI_AUDIO_LR_SWAP_SUBPACKET2 = 0x40, + HDMI_AUDIO_LR_SWAP_SUBPACKET3 = 0x80, + HDMI_AUDIO_N_19_16_MASK = 0x0f, + + /* HDMI_AUDIO_CTRL1 */ + HDMI_AUDIO_EXTERNAL_CTS = BIT(7), + HDMI_AUDIO_INPUT_IIS = 0, + HDMI_AUDIO_INPUT_SPDIF = 0x08, + HDMI_AUDIO_INPUT_MCLK_ACTIVE = 0x04, + HDMI_AUDIO_INPUT_MCLK_DEACTIVE = 0, + HDMI_AUDIO_INPUT_MCLK_RATE_128X = 0, + HDMI_AUDIO_INPUT_MCLK_RATE_256X = 1, + HDMI_AUDIO_INPUT_MCLK_RATE_384X = 2, + HDMI_AUDIO_INPUT_MCLK_RATE_512X = 3, + + /* HDMI_I2S_AUDIO_CTRL */ + HDMI_AUDIO_I2S_FORMAT_STANDARD = 0, + HDMI_AUDIO_I2S_CHANNEL_1_2 = 0x04, + HDMI_AUDIO_I2S_CHANNEL_3_4 = 0x0c, + HDMI_AUDIO_I2S_CHANNEL_5_6 = 0x1c, + HDMI_AUDIO_I2S_CHANNEL_7_8 = 0x3c, + + /* HDMI_AV_CTRL1 */ + HDMI_AUDIO_SAMPLE_FRE_MASK = 0xf0, + HDMI_AUDIO_SAMPLE_FRE_32000 = 0x30, + HDMI_AUDIO_SAMPLE_FRE_44100 = 0, + HDMI_AUDIO_SAMPLE_FRE_48000 = 0x20, + HDMI_AUDIO_SAMPLE_FRE_88200 = 0x80, + HDMI_AUDIO_SAMPLE_FRE_96000 = 0xa0, + HDMI_AUDIO_SAMPLE_FRE_176400 = 0xc0, + HDMI_AUDIO_SAMPLE_FRE_192000 = 0xe0, + HDMI_AUDIO_SAMPLE_FRE_768000 = 0x90, + + HDMI_VIDEO_INPUT_FORMAT_MASK = 0x0e, + HDMI_VIDEO_INPUT_RGB_YCBCR444 = 0, + HDMI_VIDEO_INPUT_YCBCR422 = 0x02, + HDMI_VIDEO_DE_MASK = 0x1, + HDMI_VIDEO_INTERNAL_DE = 0, + HDMI_VIDEO_EXTERNAL_DE = 0x01, + + /* HDMI_VIDEO_CTRL1 */ + HDMI_VIDEO_OUTPUT_FORMAT_MASK = 0xc0, + HDMI_VIDEO_OUTPUT_RGB444 = 0, + HDMI_VIDEO_OUTPUT_YCBCR444 = 0x40, + HDMI_VIDEO_OUTPUT_YCBCR422 = 0x80, + HDMI_VIDEO_INPUT_DATA_DEPTH_MASK = 0x30, + HDMI_VIDEO_INPUT_DATA_DEPTH_12BIT = 0, + HDMI_VIDEO_INPUT_DATA_DEPTH_10BIT = 0x10, + HDMI_VIDEO_INPUT_DATA_DEPTH_8BIT = 0x30, + HDMI_VIDEO_INPUT_COLOR_MASK = 1, + HDMI_VIDEO_INPUT_COLOR_RGB = 0, + HDMI_VIDEO_INPUT_COLOR_YCBCR = 1, + + /* HDMI_EXT_VIDEO_PARA */ + HDMI_VIDEO_VSYNC_OFFSET_SHIFT = 4, + HDMI_VIDEO_VSYNC_ACTIVE_HIGH = BIT(3), + HDMI_VIDEO_VSYNC_ACTIVE_LOW = 0, + HDMI_VIDEO_HSYNC_ACTIVE_HIGH = BIT(2), + HDMI_VIDEO_HSYNC_ACTIVE_LOW = 0, + HDMI_VIDEO_MODE_INTERLACE = BIT(1), + HDMI_VIDEO_MODE_PROGRESSIVE = 0, + HDMI_EXT_VIDEO_SET_EN = BIT(0), + + /* HDMI_CP_AUTO_SEND_CTRL */ + + /* HDMI_VIDEO_CTRL2 */ + HDMI_VIDEO_AV_MUTE_MASK = 0xc0, + HDMI_VIDEO_CLR_AV_MUTE = BIT(7), + HDMI_VIDEO_SET_AV_MUTE = BIT(6), + HDMI_AUDIO_CP_LOGIC_RESET_MASK = BIT(2), + HDMI_AUDIO_CP_LOGIC_RESET = BIT(2), + HDMI_VIDEO_AUDIO_DISABLE_MASK = 0x3, + HDMI_AUDIO_DISABLE = BIT(1), + HDMI_VIDEO_DISABLE = BIT(0), + + /* HDMI_CP_BUF_INDEX */ + HDMI_INFOFRAME_VSI = 0x05, + HDMI_INFOFRAME_AVI = 0x06, + HDMI_INFOFRAME_AAI = 0x08, + + /* HDMI_INTR_MASK1 */ + /* HDMI_INTR_STATUS1 */ + HDMI_INTR_HOTPLUG = BIT(7), + HDMI_INTR_MSENS = BIT(6), + HDMI_INTR_VSYNC = BIT(5), + HDMI_INTR_AUDIO_FIFO_FULL = BIT(4), + HDMI_INTR_EDID_MASK = 0x6, + HDMI_INTR_EDID_READY = BIT(2), + HDMI_INTR_EDID_ERR = BIT(1), + + /* HDMI_HDCP_CTRL */ + HDMI_VIDEO_MODE_MASK = BIT(1), + HDMI_VIDEO_MODE_HDMI = BIT(1), + + /* HDMI_HPG_MENS_STA */ + HDMI_HPG_IN_STATUS_HIGH = BIT(7), + HDMI_MSENS_IN_STATUS_HIGH = BIT(6), +}; + +#endif /* __RK3066_HDMI_H__ */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index d7fa17f12769..8d7a634c12c2 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -486,6 +486,8 @@ static int __init rockchip_drm_init(void) ADD_ROCKCHIP_SUB_DRIVER(dw_mipi_dsi_rockchip_driver, CONFIG_ROCKCHIP_DW_MIPI_DSI); ADD_ROCKCHIP_SUB_DRIVER(inno_hdmi_driver, CONFIG_ROCKCHIP_INNO_HDMI); + ADD_ROCKCHIP_SUB_DRIVER(rk3066_hdmi_driver, + CONFIG_ROCKCHIP_RK3066_HDMI); ret = platform_register_drivers(rockchip_sub_drivers, num_rockchip_sub_drivers); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h index ce48568ec8a0..e4bc4322bc3f 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.h @@ -73,4 +73,5 @@ extern struct platform_driver inno_hdmi_driver; extern struct platform_driver rockchip_dp_driver; extern struct platform_driver rockchip_lvds_driver; extern struct platform_driver vop_platform_driver; +extern struct platform_driver rk3066_hdmi_driver; #endif /* _ROCKCHIP_DRM_DRV_H_ */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index c7d4c6073ea5..a7cbf6c9a153 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -1029,6 +1029,7 @@ static void vop_crtc_atomic_enable(struct drm_crtc *crtc, u16 vact_st = adjusted_mode->vtotal - adjusted_mode->vsync_start; u16 vact_end = vact_st + vdisplay; uint32_t pin_pol, val; + int dither_bpc = s->output_bpc ? s->output_bpc : 10; int ret; mutex_lock(&vop->vop_lock); @@ -1086,11 +1087,19 @@ static void vop_crtc_atomic_enable(struct drm_crtc *crtc, !(vop_data->feature & VOP_FEATURE_OUTPUT_RGB10)) s->output_mode = ROCKCHIP_OUT_MODE_P888; - if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA && s->output_bpc == 8) + if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA && dither_bpc <= 8) VOP_REG_SET(vop, common, pre_dither_down, 1); else VOP_REG_SET(vop, common, pre_dither_down, 0); + if (dither_bpc == 6) { + VOP_REG_SET(vop, common, dither_down_sel, DITHER_DOWN_ALLEGRO); + VOP_REG_SET(vop, common, dither_down_mode, RGB888_TO_RGB666); + VOP_REG_SET(vop, common, dither_down_en, 1); + } else { + VOP_REG_SET(vop, common, dither_down_en, 0); + } + VOP_REG_SET(vop, common, out_mode, s->output_mode); VOP_REG_SET(vop, modeset, htotal_pw, (htotal << 16) | hsync_len); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h index 04ed401d2325..e64351dab610 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h @@ -71,7 +71,9 @@ struct vop_common { struct vop_reg dsp_blank; struct vop_reg data_blank; struct vop_reg pre_dither_down; - struct vop_reg dither_down; + struct vop_reg dither_down_sel; + struct vop_reg dither_down_mode; + struct vop_reg dither_down_en; struct vop_reg dither_up; struct vop_reg gate_en; struct vop_reg mmu_en; @@ -287,6 +289,16 @@ enum scale_down_mode { SCALE_DOWN_AVG = 0x1 }; +enum dither_down_mode { + RGB888_TO_RGB565 = 0x0, + RGB888_TO_RGB666 = 0x1 +}; + +enum dither_down_mode_sel { + DITHER_DOWN_ALLEGRO = 0x0, + DITHER_DOWN_FRC = 0x1 +}; + enum vop_pol { HSYNC_POSITIVE = 0, VSYNC_POSITIVE = 1, diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c index bd76328c0fdb..e732b73033c8 100644 --- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c +++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c @@ -137,6 +137,9 @@ static const struct vop_common rk3036_common = { .standby = VOP_REG_SYNC(RK3036_SYS_CTRL, 0x1, 30), .out_mode = VOP_REG(RK3036_DSP_CTRL0, 0xf, 0), .dsp_blank = VOP_REG(RK3036_DSP_CTRL1, 0x1, 24), + .dither_down_sel = VOP_REG(RK3036_DSP_CTRL0, 0x1, 27), + .dither_down_en = VOP_REG(RK3036_DSP_CTRL0, 0x1, 11), + .dither_down_mode = VOP_REG(RK3036_DSP_CTRL0, 0x1, 10), .cfg_done = VOP_REG_SYNC(RK3036_REG_CFG_DONE, 0x1, 0), }; @@ -200,6 +203,9 @@ static const struct vop_common px30_common = { .standby = VOP_REG_SYNC(PX30_SYS_CTRL2, 0x1, 1), .out_mode = VOP_REG(PX30_DSP_CTRL2, 0xf, 16), .dsp_blank = VOP_REG(PX30_DSP_CTRL2, 0x1, 14), + .dither_down_en = VOP_REG(PX30_DSP_CTRL2, 0x1, 8), + .dither_down_sel = VOP_REG(PX30_DSP_CTRL2, 0x1, 7), + .dither_down_mode = VOP_REG(PX30_DSP_CTRL2, 0x1, 6), .cfg_done = VOP_REG_SYNC(PX30_REG_CFG_DONE, 0x1, 0), }; @@ -365,6 +371,8 @@ static const struct vop_common rk3066_common = { .standby = VOP_REG(RK3066_SYS_CTRL0, 0x1, 1), .out_mode = VOP_REG(RK3066_DSP_CTRL0, 0xf, 0), .cfg_done = VOP_REG(RK3066_REG_CFG_DONE, 0x1, 0), + .dither_down_en = VOP_REG(RK3066_DSP_CTRL0, 0x1, 11), + .dither_down_mode = VOP_REG(RK3066_DSP_CTRL0, 0x1, 10), .dsp_blank = VOP_REG(RK3066_DSP_CTRL1, 0x1, 24), }; @@ -458,6 +466,9 @@ static const struct vop_common rk3188_common = { .standby = VOP_REG(RK3188_SYS_CTRL, 0x1, 30), .out_mode = VOP_REG(RK3188_DSP_CTRL0, 0xf, 0), .cfg_done = VOP_REG(RK3188_REG_CFG_DONE, 0x1, 0), + .dither_down_sel = VOP_REG(RK3188_DSP_CTRL0, 0x1, 27), + .dither_down_en = VOP_REG(RK3188_DSP_CTRL0, 0x1, 11), + .dither_down_mode = VOP_REG(RK3188_DSP_CTRL0, 0x1, 10), .dsp_blank = VOP_REG(RK3188_DSP_CTRL1, 0x3, 24), }; @@ -585,8 +596,10 @@ static const struct vop_common rk3288_common = { .standby = VOP_REG_SYNC(RK3288_SYS_CTRL, 0x1, 22), .gate_en = VOP_REG(RK3288_SYS_CTRL, 0x1, 23), .mmu_en = VOP_REG(RK3288_SYS_CTRL, 0x1, 20), + .dither_down_sel = VOP_REG(RK3288_DSP_CTRL1, 0x1, 4), + .dither_down_mode = VOP_REG(RK3288_DSP_CTRL1, 0x1, 3), + .dither_down_en = VOP_REG(RK3288_DSP_CTRL1, 0x1, 2), .pre_dither_down = VOP_REG(RK3288_DSP_CTRL1, 0x1, 1), - .dither_down = VOP_REG(RK3288_DSP_CTRL1, 0xf, 1), .dither_up = VOP_REG(RK3288_DSP_CTRL1, 0x1, 6), .data_blank = VOP_REG(RK3288_DSP_CTRL0, 0x1, 19), .dsp_blank = VOP_REG(RK3288_DSP_CTRL0, 0x3, 18), @@ -878,7 +891,10 @@ static const struct vop_misc rk3328_misc = { static const struct vop_common rk3328_common = { .standby = VOP_REG_SYNC(RK3328_SYS_CTRL, 0x1, 22), - .dither_down = VOP_REG(RK3328_DSP_CTRL1, 0xf, 1), + .dither_down_sel = VOP_REG(RK3328_DSP_CTRL1, 0x1, 4), + .dither_down_mode = VOP_REG(RK3328_DSP_CTRL1, 0x1, 3), + .dither_down_en = VOP_REG(RK3328_DSP_CTRL1, 0x1, 2), + .pre_dither_down = VOP_REG(RK3328_DSP_CTRL1, 0x1, 1), .dither_up = VOP_REG(RK3328_DSP_CTRL1, 0x1, 6), .dsp_blank = VOP_REG(RK3328_DSP_CTRL0, 0x3, 18), .out_mode = VOP_REG(RK3328_DSP_CTRL0, 0xf, 0), diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index 0a7f933ab007..5834ef56fbaa 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -129,6 +129,40 @@ static void drv_unload(struct drm_device *ddev) drm_mode_config_cleanup(ddev); } +static __maybe_unused int drv_suspend(struct device *dev) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct ltdc_device *ldev = ddev->dev_private; + struct drm_atomic_state *state; + + drm_kms_helper_poll_disable(ddev); + state = drm_atomic_helper_suspend(ddev); + if (IS_ERR(state)) { + drm_kms_helper_poll_enable(ddev); + return PTR_ERR(state); + } + ldev->suspend_state = state; + ltdc_suspend(ddev); + + return 0; +} + +static __maybe_unused int drv_resume(struct device *dev) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct ltdc_device *ldev = ddev->dev_private; + + ltdc_resume(ddev); + drm_atomic_helper_resume(ddev, ldev->suspend_state); + drm_kms_helper_poll_enable(ddev); + + return 0; +} + +static const struct dev_pm_ops drv_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(drv_suspend, drv_resume) +}; + static int stm_drm_platform_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -186,6 +220,7 @@ static struct platform_driver stm_drm_platform_driver = { .driver = { .name = "stm32-display", .of_match_table = drv_dt_ids, + .pm = &drv_pm_ops, }, }; diff --git a/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c b/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c index a672b59a2226..1bef73e8c8fe 100644 --- a/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c +++ b/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c @@ -356,12 +356,40 @@ static int dw_mipi_dsi_stm_remove(struct platform_device *pdev) return 0; } +static int __maybe_unused dw_mipi_dsi_stm_suspend(struct device *dev) +{ + struct dw_mipi_dsi_stm *dsi = dw_mipi_dsi_stm_plat_data.priv_data; + + DRM_DEBUG_DRIVER("\n"); + + clk_disable_unprepare(dsi->pllref_clk); + + return 0; +} + +static int __maybe_unused dw_mipi_dsi_stm_resume(struct device *dev) +{ + struct dw_mipi_dsi_stm *dsi = dw_mipi_dsi_stm_plat_data.priv_data; + + DRM_DEBUG_DRIVER("\n"); + + clk_prepare_enable(dsi->pllref_clk); + + return 0; +} + +static const struct dev_pm_ops dw_mipi_dsi_stm_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(dw_mipi_dsi_stm_suspend, + dw_mipi_dsi_stm_resume) +}; + static struct platform_driver dw_mipi_dsi_stm_driver = { .probe = dw_mipi_dsi_stm_probe, .remove = dw_mipi_dsi_stm_remove, .driver = { .of_match_table = dw_mipi_dsi_stm_dt_ids, .name = "stm32-display-dsi", + .pm = &dw_mipi_dsi_stm_pm_ops, }, }; diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index b1741a9d5be2..32fd6a3b37fb 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -1062,6 +1062,30 @@ static int ltdc_get_caps(struct drm_device *ddev) return 0; } +void ltdc_suspend(struct drm_device *ddev) +{ + struct ltdc_device *ldev = ddev->dev_private; + + DRM_DEBUG_DRIVER("\n"); + clk_disable_unprepare(ldev->pixel_clk); +} + +int ltdc_resume(struct drm_device *ddev) +{ + struct ltdc_device *ldev = ddev->dev_private; + int ret; + + DRM_DEBUG_DRIVER("\n"); + + ret = clk_prepare_enable(ldev->pixel_clk); + if (ret) { + DRM_ERROR("failed to enable pixel clock (%d)\n", ret); + return ret; + } + + return 0; +} + int ltdc_load(struct drm_device *ddev) { struct platform_device *pdev = to_platform_device(ddev->dev); diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h index e46f477a8494..a1ad0ae3b006 100644 --- a/drivers/gpu/drm/stm/ltdc.h +++ b/drivers/gpu/drm/stm/ltdc.h @@ -36,6 +36,7 @@ struct ltdc_device { u32 error_status; u32 irq_status; struct fps_info plane_fpsi[LTDC_MAX_LAYER]; + struct drm_atomic_state *suspend_state; }; bool ltdc_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, @@ -45,5 +46,7 @@ bool ltdc_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, int ltdc_load(struct drm_device *ddev); void ltdc_unload(struct drm_device *ddev); +void ltdc_suspend(struct drm_device *ddev); +int ltdc_resume(struct drm_device *ddev); #endif diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h index b685ee11623d..b08c4453d47c 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h @@ -269,6 +269,7 @@ struct sun4i_hdmi { struct clk *tmds_clk; struct i2c_adapter *i2c; + struct i2c_adapter *ddc_i2c; /* Regmap fields for I2C adapter */ struct regmap_field *field_ddc_en; diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index d18862629301..8c122e637697 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -217,7 +217,7 @@ static int sun4i_hdmi_get_modes(struct drm_connector *connector) struct edid *edid; int ret; - edid = drm_get_edid(connector, hdmi->i2c); + edid = drm_get_edid(connector, hdmi->ddc_i2c ?: hdmi->i2c); if (!edid) return 0; @@ -233,6 +233,28 @@ static int sun4i_hdmi_get_modes(struct drm_connector *connector) return ret; } +static struct i2c_adapter *sun4i_hdmi_get_ddc(struct device *dev) +{ + struct device_node *phandle, *remote; + struct i2c_adapter *ddc; + + remote = of_graph_get_remote_node(dev->of_node, 1, -1); + if (!remote) + return ERR_PTR(-EINVAL); + + phandle = of_parse_phandle(remote, "ddc-i2c-bus", 0); + of_node_put(remote); + if (!phandle) + return ERR_PTR(-ENODEV); + + ddc = of_get_i2c_adapter_by_node(phandle); + of_node_put(phandle); + if (!ddc) + return ERR_PTR(-EPROBE_DEFER); + + return ddc; +} + static const struct drm_connector_helper_funcs sun4i_hdmi_connector_helper_funcs = { .get_modes = sun4i_hdmi_get_modes, }; @@ -580,6 +602,15 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, goto err_disable_mod_clk; } + hdmi->ddc_i2c = sun4i_hdmi_get_ddc(dev); + if (IS_ERR(hdmi->ddc_i2c)) { + ret = PTR_ERR(hdmi->ddc_i2c); + if (ret == -ENODEV) + hdmi->ddc_i2c = NULL; + else + goto err_del_i2c_adapter; + } + drm_encoder_helper_add(&hdmi->encoder, &sun4i_hdmi_helper_funcs); ret = drm_encoder_init(drm, @@ -589,14 +620,14 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, NULL); if (ret) { dev_err(dev, "Couldn't initialise the HDMI encoder\n"); - goto err_del_i2c_adapter; + goto err_put_ddc_i2c; } hdmi->encoder.possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node); if (!hdmi->encoder.possible_crtcs) { ret = -EPROBE_DEFER; - goto err_del_i2c_adapter; + goto err_put_ddc_i2c; } #ifdef CONFIG_DRM_SUN4I_HDMI_CEC @@ -635,6 +666,8 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master, err_cleanup_connector: cec_delete_adapter(hdmi->cec_adap); drm_encoder_cleanup(&hdmi->encoder); +err_put_ddc_i2c: + i2c_put_adapter(hdmi->ddc_i2c); err_del_i2c_adapter: i2c_del_adapter(hdmi->i2c); err_disable_mod_clk: @@ -655,6 +688,7 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master, drm_connector_cleanup(&hdmi->connector); drm_encoder_cleanup(&hdmi->encoder); i2c_del_adapter(hdmi->i2c); + i2c_put_adapter(hdmi->ddc_i2c); clk_disable_unprepare(hdmi->mod_clk); clk_disable_unprepare(hdmi->bus_clk); } diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c index c0219ebb4284..a22b75a3a533 100644 --- a/drivers/gpu/drm/v3d/v3d_bo.c +++ b/drivers/gpu/drm/v3d/v3d_bo.c @@ -130,8 +130,8 @@ struct v3d_bo *v3d_bo_create(struct drm_device *dev, struct drm_file *file_priv, int ret; shmem_obj = drm_gem_shmem_create(dev, unaligned_size); - if (!shmem_obj) - return NULL; + if (IS_ERR(shmem_obj)) + return ERR_CAST(shmem_obj); bo = to_v3d_bo(&shmem_obj->base); ret = v3d_bo_create_finish(&shmem_obj->base); diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index d600628bb5c1..a06b05f714a5 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -102,6 +102,8 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data, return -EINVAL; ret = pm_runtime_get_sync(v3d->dev); + if (ret < 0) + return ret; if (args->param >= DRM_V3D_PARAM_V3D_CORE0_IDENT0 && args->param <= DRM_V3D_PARAM_V3D_CORE0_IDENT2) { args->value = V3D_CORE_READ(0, offset); diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 7b0fe6240f7d..e9d4a2fdcf44 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -163,7 +163,7 @@ struct v3d_job { struct dma_fence *in_fence; /* v3d fence to be signaled by IRQ handler when the job is complete. */ - struct dma_fence *done_fence; + struct dma_fence *irq_fence; /* GPU virtual addresses of the start/end of the CL job. */ u32 start, end; @@ -210,7 +210,7 @@ struct v3d_tfu_job { struct dma_fence *in_fence; /* v3d fence to be signaled by IRQ handler when the job is complete. */ - struct dma_fence *done_fence; + struct dma_fence *irq_fence; struct v3d_dev *v3d; diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index b84d89c7b3fb..93ff8fcbe475 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -340,8 +340,8 @@ v3d_exec_cleanup(struct kref *ref) dma_fence_put(exec->bin.in_fence); dma_fence_put(exec->render.in_fence); - dma_fence_put(exec->bin.done_fence); - dma_fence_put(exec->render.done_fence); + dma_fence_put(exec->bin.irq_fence); + dma_fence_put(exec->render.irq_fence); dma_fence_put(exec->bin_done_fence); dma_fence_put(exec->render_done_fence); @@ -374,7 +374,7 @@ v3d_tfu_job_cleanup(struct kref *ref) unsigned int i; dma_fence_put(job->in_fence); - dma_fence_put(job->done_fence); + dma_fence_put(job->irq_fence); for (i = 0; i < ARRAY_SIZE(job->bo); i++) { if (job->bo[i]) diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c index b4d6ae81186d..aa0a180ae700 100644 --- a/drivers/gpu/drm/v3d/v3d_irq.c +++ b/drivers/gpu/drm/v3d/v3d_irq.c @@ -87,7 +87,8 @@ v3d_irq(int irq, void *arg) if (intsts & V3D_INT_OUTOMEM) { /* Note that the OOM status is edge signaled, so the * interrupt won't happen again until the we actually - * add more memory. + * add more memory. Also, as of V3D 4.1, FLDONE won't + * be reported until any OOM state has been cleared. */ schedule_work(&v3d->overflow_mem_work); status = IRQ_HANDLED; @@ -95,7 +96,7 @@ v3d_irq(int irq, void *arg) if (intsts & V3D_INT_FLDONE) { struct v3d_fence *fence = - to_v3d_fence(v3d->bin_job->bin.done_fence); + to_v3d_fence(v3d->bin_job->bin.irq_fence); trace_v3d_bcl_irq(&v3d->drm, fence->seqno); dma_fence_signal(&fence->base); @@ -104,7 +105,7 @@ v3d_irq(int irq, void *arg) if (intsts & V3D_INT_FRDONE) { struct v3d_fence *fence = - to_v3d_fence(v3d->render_job->render.done_fence); + to_v3d_fence(v3d->render_job->render.irq_fence); trace_v3d_rcl_irq(&v3d->drm, fence->seqno); dma_fence_signal(&fence->base); @@ -140,7 +141,7 @@ v3d_hub_irq(int irq, void *arg) if (intsts & V3D_HUB_INT_TFUC) { struct v3d_fence *fence = - to_v3d_fence(v3d->tfu_job->done_fence); + to_v3d_fence(v3d->tfu_job->irq_fence); trace_v3d_tfu_irq(&v3d->drm, fence->seqno); dma_fence_signal(&fence->base); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index d0c68b7c8b41..e740f3b99aa5 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -156,9 +156,9 @@ static struct dma_fence *v3d_job_run(struct drm_sched_job *sched_job) if (IS_ERR(fence)) return NULL; - if (job->done_fence) - dma_fence_put(job->done_fence); - job->done_fence = dma_fence_get(fence); + if (job->irq_fence) + dma_fence_put(job->irq_fence); + job->irq_fence = dma_fence_get(fence); trace_v3d_submit_cl(dev, q == V3D_RENDER, to_v3d_fence(fence)->seqno, job->start, job->end); @@ -199,9 +199,9 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job) return NULL; v3d->tfu_job = job; - if (job->done_fence) - dma_fence_put(job->done_fence); - job->done_fence = dma_fence_get(fence); + if (job->irq_fence) + dma_fence_put(job->irq_fence); + job->irq_fence = dma_fence_get(fence); trace_v3d_submit_tfu(dev, to_v3d_fence(fence)->seqno); diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 92e3f98d8478..88ebd681d7eb 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -40,7 +40,7 @@ static bool is_user_label(int label) return label >= VC4_BO_TYPE_COUNT; } -static void vc4_bo_stats_dump(struct vc4_dev *vc4) +static void vc4_bo_stats_print(struct drm_printer *p, struct vc4_dev *vc4) { int i; @@ -48,58 +48,35 @@ static void vc4_bo_stats_dump(struct vc4_dev *vc4) if (!vc4->bo_labels[i].num_allocated) continue; - DRM_INFO("%30s: %6dkb BOs (%d)\n", - vc4->bo_labels[i].name, - vc4->bo_labels[i].size_allocated / 1024, - vc4->bo_labels[i].num_allocated); + drm_printf(p, "%30s: %6dkb BOs (%d)\n", + vc4->bo_labels[i].name, + vc4->bo_labels[i].size_allocated / 1024, + vc4->bo_labels[i].num_allocated); } mutex_lock(&vc4->purgeable.lock); if (vc4->purgeable.num) - DRM_INFO("%30s: %6zdkb BOs (%d)\n", "userspace BO cache", - vc4->purgeable.size / 1024, vc4->purgeable.num); + drm_printf(p, "%30s: %6zdkb BOs (%d)\n", "userspace BO cache", + vc4->purgeable.size / 1024, vc4->purgeable.num); if (vc4->purgeable.purged_num) - DRM_INFO("%30s: %6zdkb BOs (%d)\n", "total purged BO", - vc4->purgeable.purged_size / 1024, - vc4->purgeable.purged_num); + drm_printf(p, "%30s: %6zdkb BOs (%d)\n", "total purged BO", + vc4->purgeable.purged_size / 1024, + vc4->purgeable.purged_num); mutex_unlock(&vc4->purgeable.lock); } -#ifdef CONFIG_DEBUG_FS -int vc4_bo_stats_debugfs(struct seq_file *m, void *unused) +static int vc4_bo_stats_debugfs(struct seq_file *m, void *unused) { struct drm_info_node *node = (struct drm_info_node *)m->private; struct drm_device *dev = node->minor->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); - int i; + struct drm_printer p = drm_seq_file_printer(m); - mutex_lock(&vc4->bo_lock); - for (i = 0; i < vc4->num_labels; i++) { - if (!vc4->bo_labels[i].num_allocated) - continue; - - seq_printf(m, "%30s: %6dkb BOs (%d)\n", - vc4->bo_labels[i].name, - vc4->bo_labels[i].size_allocated / 1024, - vc4->bo_labels[i].num_allocated); - } - mutex_unlock(&vc4->bo_lock); - - mutex_lock(&vc4->purgeable.lock); - if (vc4->purgeable.num) - seq_printf(m, "%30s: %6zdkb BOs (%d)\n", "userspace BO cache", - vc4->purgeable.size / 1024, vc4->purgeable.num); - - if (vc4->purgeable.purged_num) - seq_printf(m, "%30s: %6zdkb BOs (%d)\n", "total purged BO", - vc4->purgeable.purged_size / 1024, - vc4->purgeable.purged_num); - mutex_unlock(&vc4->purgeable.lock); + vc4_bo_stats_print(&p, vc4); return 0; } -#endif /* Takes ownership of *name and returns the appropriate slot for it in * the bo_labels[] array, extending it as necessary. @@ -475,8 +452,9 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size, } if (IS_ERR(cma_obj)) { + struct drm_printer p = drm_info_printer(vc4->dev->dev); DRM_ERROR("Failed to allocate from CMA:\n"); - vc4_bo_stats_dump(vc4); + vc4_bo_stats_print(&p, vc4); return ERR_PTR(-ENOMEM); } bo = to_vc4_bo(&cma_obj->base); @@ -1025,6 +1003,8 @@ int vc4_bo_cache_init(struct drm_device *dev) mutex_init(&vc4->bo_lock); + vc4_debugfs_add_file(dev, "bo_stats", vc4_bo_stats_debugfs, NULL); + INIT_LIST_HEAD(&vc4->bo_cache.time_list); INIT_WORK(&vc4->bo_cache.time_work, vc4_bo_cache_time_work); diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 64c964b7c577..b2891ca0e7f4 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -35,6 +35,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_atomic_uapi.h> +#include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include <linux/clk.h> #include <drm/drm_fb_cma_helper.h> @@ -67,67 +68,22 @@ to_vc4_crtc_state(struct drm_crtc_state *crtc_state) #define CRTC_WRITE(offset, val) writel(val, vc4_crtc->regs + (offset)) #define CRTC_READ(offset) readl(vc4_crtc->regs + (offset)) -#define CRTC_REG(reg) { reg, #reg } -static const struct { - u32 reg; - const char *name; -} crtc_regs[] = { - CRTC_REG(PV_CONTROL), - CRTC_REG(PV_V_CONTROL), - CRTC_REG(PV_VSYNCD_EVEN), - CRTC_REG(PV_HORZA), - CRTC_REG(PV_HORZB), - CRTC_REG(PV_VERTA), - CRTC_REG(PV_VERTB), - CRTC_REG(PV_VERTA_EVEN), - CRTC_REG(PV_VERTB_EVEN), - CRTC_REG(PV_INTEN), - CRTC_REG(PV_INTSTAT), - CRTC_REG(PV_STAT), - CRTC_REG(PV_HACT_ACT), +static const struct debugfs_reg32 crtc_regs[] = { + VC4_REG32(PV_CONTROL), + VC4_REG32(PV_V_CONTROL), + VC4_REG32(PV_VSYNCD_EVEN), + VC4_REG32(PV_HORZA), + VC4_REG32(PV_HORZB), + VC4_REG32(PV_VERTA), + VC4_REG32(PV_VERTB), + VC4_REG32(PV_VERTA_EVEN), + VC4_REG32(PV_VERTB_EVEN), + VC4_REG32(PV_INTEN), + VC4_REG32(PV_INTSTAT), + VC4_REG32(PV_STAT), + VC4_REG32(PV_HACT_ACT), }; -static void vc4_crtc_dump_regs(struct vc4_crtc *vc4_crtc) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(crtc_regs); i++) { - DRM_INFO("0x%04x (%s): 0x%08x\n", - crtc_regs[i].reg, crtc_regs[i].name, - CRTC_READ(crtc_regs[i].reg)); - } -} - -#ifdef CONFIG_DEBUG_FS -int vc4_crtc_debugfs_regs(struct seq_file *m, void *unused) -{ - struct drm_info_node *node = (struct drm_info_node *)m->private; - struct drm_device *dev = node->minor->dev; - int crtc_index = (uintptr_t)node->info_ent->data; - struct drm_crtc *crtc; - struct vc4_crtc *vc4_crtc; - int i; - - i = 0; - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - if (i == crtc_index) - break; - i++; - } - if (!crtc) - return 0; - vc4_crtc = to_vc4_crtc(crtc); - - for (i = 0; i < ARRAY_SIZE(crtc_regs); i++) { - seq_printf(m, "%s (0x%04x): 0x%08x\n", - crtc_regs[i].name, crtc_regs[i].reg, - CRTC_READ(crtc_regs[i].reg)); - } - - return 0; -} -#endif - bool vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id, bool in_vblank_irq, int *vpos, int *hpos, ktime_t *stime, ktime_t *etime, @@ -434,8 +390,10 @@ static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc) bool debug_dump_regs = false; if (debug_dump_regs) { - DRM_INFO("CRTC %d regs before:\n", drm_crtc_index(crtc)); - vc4_crtc_dump_regs(vc4_crtc); + struct drm_printer p = drm_info_printer(&vc4_crtc->pdev->dev); + dev_info(&vc4_crtc->pdev->dev, "CRTC %d regs before:\n", + drm_crtc_index(crtc)); + drm_print_regset32(&p, &vc4_crtc->regset); } if (vc4_crtc->channel == 2) { @@ -476,8 +434,10 @@ static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc) vc4_crtc_lut_load(crtc); if (debug_dump_regs) { - DRM_INFO("CRTC %d regs after:\n", drm_crtc_index(crtc)); - vc4_crtc_dump_regs(vc4_crtc); + struct drm_printer p = drm_info_printer(&vc4_crtc->pdev->dev); + dev_info(&vc4_crtc->pdev->dev, "CRTC %d regs after:\n", + drm_crtc_index(crtc)); + drm_print_regset32(&p, &vc4_crtc->regset); } } @@ -1083,6 +1043,7 @@ static const struct drm_crtc_helper_funcs vc4_crtc_helper_funcs = { static const struct vc4_crtc_data pv0_data = { .hvs_channel = 0, + .debugfs_name = "crtc0_regs", .encoder_types = { [PV_CONTROL_CLK_SELECT_DSI] = VC4_ENCODER_TYPE_DSI0, [PV_CONTROL_CLK_SELECT_DPI_SMI_HDMI] = VC4_ENCODER_TYPE_DPI, @@ -1091,6 +1052,7 @@ static const struct vc4_crtc_data pv0_data = { static const struct vc4_crtc_data pv1_data = { .hvs_channel = 2, + .debugfs_name = "crtc1_regs", .encoder_types = { [PV_CONTROL_CLK_SELECT_DSI] = VC4_ENCODER_TYPE_DSI1, [PV_CONTROL_CLK_SELECT_DPI_SMI_HDMI] = VC4_ENCODER_TYPE_SMI, @@ -1099,6 +1061,7 @@ static const struct vc4_crtc_data pv1_data = { static const struct vc4_crtc_data pv2_data = { .hvs_channel = 1, + .debugfs_name = "crtc2_regs", .encoder_types = { [PV_CONTROL_CLK_SELECT_DPI_SMI_HDMI] = VC4_ENCODER_TYPE_HDMI, [PV_CONTROL_CLK_SELECT_VEC] = VC4_ENCODER_TYPE_VEC, @@ -1177,11 +1140,16 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data) if (!match) return -ENODEV; vc4_crtc->data = match->data; + vc4_crtc->pdev = pdev; vc4_crtc->regs = vc4_ioremap_regs(pdev, 0); if (IS_ERR(vc4_crtc->regs)) return PTR_ERR(vc4_crtc->regs); + vc4_crtc->regset.base = vc4_crtc->regs; + vc4_crtc->regset.regs = crtc_regs; + vc4_crtc->regset.nregs = ARRAY_SIZE(crtc_regs); + /* For now, we create just the primary and the legacy cursor * planes. We should be able to stack more planes on easily, * but to do that we would need to compute the bandwidth @@ -1255,6 +1223,9 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data) platform_set_drvdata(pdev, vc4_crtc); + vc4_debugfs_add_regset32(drm, vc4_crtc->data->debugfs_name, + &vc4_crtc->regset); + return 0; err_destroy_planes: diff --git a/drivers/gpu/drm/vc4/vc4_debugfs.c b/drivers/gpu/drm/vc4/vc4_debugfs.c index 59cdad89f844..69df84bdf904 100644 --- a/drivers/gpu/drm/vc4/vc4_debugfs.c +++ b/drivers/gpu/drm/vc4/vc4_debugfs.c @@ -15,28 +15,20 @@ #include "vc4_drv.h" #include "vc4_regs.h" -static const struct drm_info_list vc4_debugfs_list[] = { - {"bo_stats", vc4_bo_stats_debugfs, 0}, - {"dpi_regs", vc4_dpi_debugfs_regs, 0}, - {"dsi1_regs", vc4_dsi_debugfs_regs, 0, (void *)(uintptr_t)1}, - {"hdmi_regs", vc4_hdmi_debugfs_regs, 0}, - {"vec_regs", vc4_vec_debugfs_regs, 0}, - {"txp_regs", vc4_txp_debugfs_regs, 0}, - {"hvs_regs", vc4_hvs_debugfs_regs, 0}, - {"hvs_underrun", vc4_hvs_debugfs_underrun, 0}, - {"crtc0_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)0}, - {"crtc1_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)1}, - {"crtc2_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)2}, - {"v3d_ident", vc4_v3d_debugfs_ident, 0}, - {"v3d_regs", vc4_v3d_debugfs_regs, 0}, +struct vc4_debugfs_info_entry { + struct list_head link; + struct drm_info_list info; }; -#define VC4_DEBUGFS_ENTRIES ARRAY_SIZE(vc4_debugfs_list) - +/** + * Called at drm_dev_register() time on each of the minors registered + * by the DRM device, to attach the debugfs files. + */ int vc4_debugfs_init(struct drm_minor *minor) { struct vc4_dev *vc4 = to_vc4_dev(minor->dev); + struct vc4_debugfs_info_entry *entry; struct dentry *dentry; dentry = debugfs_create_bool("hvs_load_tracker", S_IRUGO | S_IWUSR, @@ -45,6 +37,60 @@ vc4_debugfs_init(struct drm_minor *minor) if (!dentry) return -ENOMEM; - return drm_debugfs_create_files(vc4_debugfs_list, VC4_DEBUGFS_ENTRIES, - minor->debugfs_root, minor); + list_for_each_entry(entry, &vc4->debugfs_list, link) { + int ret = drm_debugfs_create_files(&entry->info, 1, + minor->debugfs_root, minor); + + if (ret) + return ret; + } + + return 0; +} + +int vc4_debugfs_regset32(struct seq_file *m, void *unused) +{ + struct drm_info_node *node = (struct drm_info_node *)m->private; + struct debugfs_regset32 *regset = node->info_ent->data; + struct drm_printer p = drm_seq_file_printer(m); + + drm_print_regset32(&p, regset); + + return 0; +} + +/** + * Registers a debugfs file with a callback function for a vc4 component. + * + * This is like drm_debugfs_create_files(), but that can only be + * called a given DRM minor, while the various VC4 components want to + * register their debugfs files during the component bind process. We + * track the request and delay it to be called on each minor during + * vc4_debugfs_init(). + */ +void vc4_debugfs_add_file(struct drm_device *dev, + const char *name, + int (*show)(struct seq_file*, void*), + void *data) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + struct vc4_debugfs_info_entry *entry = + devm_kzalloc(dev->dev, sizeof(*entry), GFP_KERNEL); + + if (!entry) + return; + + entry->info.name = name; + entry->info.show = show; + entry->info.data = data; + + list_add(&entry->link, &vc4->debugfs_list); +} + +void vc4_debugfs_add_regset32(struct drm_device *drm, + const char *name, + struct debugfs_regset32 *regset) +{ + vc4_debugfs_add_file(drm, name, vc4_debugfs_regset32, regset); } diff --git a/drivers/gpu/drm/vc4/vc4_dpi.c b/drivers/gpu/drm/vc4/vc4_dpi.c index 169521e547ba..34f90ca8f479 100644 --- a/drivers/gpu/drm/vc4/vc4_dpi.c +++ b/drivers/gpu/drm/vc4/vc4_dpi.c @@ -101,6 +101,8 @@ struct vc4_dpi { struct clk *pixel_clock; struct clk *core_clock; + + struct debugfs_regset32 regset; }; #define DPI_READ(offset) readl(dpi->regs + (offset)) @@ -118,37 +120,11 @@ to_vc4_dpi_encoder(struct drm_encoder *encoder) return container_of(encoder, struct vc4_dpi_encoder, base.base); } -#define DPI_REG(reg) { reg, #reg } -static const struct { - u32 reg; - const char *name; -} dpi_regs[] = { - DPI_REG(DPI_C), - DPI_REG(DPI_ID), +static const struct debugfs_reg32 dpi_regs[] = { + VC4_REG32(DPI_C), + VC4_REG32(DPI_ID), }; -#ifdef CONFIG_DEBUG_FS -int vc4_dpi_debugfs_regs(struct seq_file *m, void *unused) -{ - struct drm_info_node *node = (struct drm_info_node *)m->private; - struct drm_device *dev = node->minor->dev; - struct vc4_dev *vc4 = to_vc4_dev(dev); - struct vc4_dpi *dpi = vc4->dpi; - int i; - - if (!dpi) - return 0; - - for (i = 0; i < ARRAY_SIZE(dpi_regs); i++) { - seq_printf(m, "%s (0x%04x): 0x%08x\n", - dpi_regs[i].name, dpi_regs[i].reg, - DPI_READ(dpi_regs[i].reg)); - } - - return 0; -} -#endif - static const struct drm_encoder_funcs vc4_dpi_encoder_funcs = { .destroy = drm_encoder_cleanup, }; @@ -314,6 +290,9 @@ static int vc4_dpi_bind(struct device *dev, struct device *master, void *data) dpi->regs = vc4_ioremap_regs(pdev, 0); if (IS_ERR(dpi->regs)) return PTR_ERR(dpi->regs); + dpi->regset.base = dpi->regs; + dpi->regset.regs = dpi_regs; + dpi->regset.nregs = ARRAY_SIZE(dpi_regs); if (DPI_READ(DPI_ID) != DPI_ID_VALUE) { dev_err(dev, "Port returned 0x%08x for ID instead of 0x%08x\n", @@ -352,6 +331,8 @@ static int vc4_dpi_bind(struct device *dev, struct device *master, void *data) vc4->dpi = dpi; + vc4_debugfs_add_regset32(drm, "dpi_regs", &dpi->regset); + return 0; err_destroy_encoder: diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 4daf44fd4548..6d9be20a32be 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -72,30 +72,30 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data, if (args->pad != 0) return -EINVAL; + if (!vc4->v3d) + return -ENODEV; + switch (args->param) { case DRM_VC4_PARAM_V3D_IDENT0: - ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); - if (ret < 0) + ret = vc4_v3d_pm_get(vc4); + if (ret) return ret; args->value = V3D_READ(V3D_IDENT0); - pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev); - pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev); + vc4_v3d_pm_put(vc4); break; case DRM_VC4_PARAM_V3D_IDENT1: - ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); - if (ret < 0) + ret = vc4_v3d_pm_get(vc4); + if (ret) return ret; args->value = V3D_READ(V3D_IDENT1); - pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev); - pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev); + vc4_v3d_pm_put(vc4); break; case DRM_VC4_PARAM_V3D_IDENT2: - ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); - if (ret < 0) + ret = vc4_v3d_pm_get(vc4); + if (ret) return ret; args->value = V3D_READ(V3D_IDENT2); - pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev); - pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev); + vc4_v3d_pm_put(vc4); break; case DRM_VC4_PARAM_SUPPORTS_BRANCHES: case DRM_VC4_PARAM_SUPPORTS_ETC1: @@ -251,6 +251,7 @@ static int vc4_drm_bind(struct device *dev) struct platform_device *pdev = to_platform_device(dev); struct drm_device *drm; struct vc4_dev *vc4; + struct device_node *node; int ret = 0; dev->coherent_dma_mask = DMA_BIT_MASK(32); @@ -259,12 +260,19 @@ static int vc4_drm_bind(struct device *dev) if (!vc4) return -ENOMEM; + /* If VC4 V3D is missing, don't advertise render nodes. */ + node = of_find_matching_node_and_match(NULL, vc4_v3d_dt_match, NULL); + if (!node || !of_device_is_available(node)) + vc4_drm_driver.driver_features &= ~DRIVER_RENDER; + of_node_put(node); + drm = drm_dev_alloc(&vc4_drm_driver, dev); if (IS_ERR(drm)) return PTR_ERR(drm); platform_set_drvdata(pdev, drm); vc4->dev = drm; drm->dev_private = vc4; + INIT_LIST_HEAD(&vc4->debugfs_list); ret = vc4_bo_cache_init(drm); if (ret) @@ -280,11 +288,13 @@ static int vc4_drm_bind(struct device *dev) drm_fb_helper_remove_conflicting_framebuffers(NULL, "vc4drmfb", false); - ret = drm_dev_register(drm, 0); + ret = vc4_kms_load(drm); if (ret < 0) goto unbind_all; - vc4_kms_load(drm); + ret = drm_dev_register(drm, 0); + if (ret < 0) + goto unbind_all; drm_fbdev_generic_setup(drm, 16); diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 7a3c093e7443..4f13f6262491 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -211,6 +211,11 @@ struct vc4_dev { struct drm_modeset_lock ctm_state_lock; struct drm_private_obj ctm_manager; struct drm_private_obj load_tracker; + + /* List of vc4_debugfs_info_entry for adding to debugfs once + * the minor is available (after drm_dev_register()). + */ + struct list_head debugfs_list; }; static inline struct vc4_dev * @@ -296,6 +301,7 @@ struct vc4_v3d { struct platform_device *pdev; void __iomem *regs; struct clk *clk; + struct debugfs_regset32 regset; }; struct vc4_hvs { @@ -312,6 +318,7 @@ struct vc4_hvs { spinlock_t mm_lock; struct drm_mm_node mitchell_netravali_filter; + struct debugfs_regset32 regset; }; struct vc4_plane { @@ -427,10 +434,12 @@ struct vc4_crtc_data { int hvs_channel; enum vc4_encoder_type encoder_types[4]; + const char *debugfs_name; }; struct vc4_crtc { struct drm_crtc base; + struct platform_device *pdev; const struct vc4_crtc_data *data; void __iomem *regs; @@ -447,6 +456,8 @@ struct vc4_crtc { u32 cob_size; struct drm_pending_vblank_event *event; + + struct debugfs_regset32 regset; }; static inline struct vc4_crtc * @@ -460,6 +471,8 @@ to_vc4_crtc(struct drm_crtc *crtc) #define HVS_READ(offset) readl(vc4->hvs->regs + offset) #define HVS_WRITE(offset, val) writel(val, vc4->hvs->regs + offset) +#define VC4_REG32(reg) { .name = #reg, .offset = reg } + struct vc4_exec_info { /* Sequence number for this bin/render job. */ uint64_t seqno; @@ -708,7 +721,6 @@ struct drm_gem_object *vc4_prime_import_sg_table(struct drm_device *dev, void *vc4_prime_vmap(struct drm_gem_object *obj); int vc4_bo_cache_init(struct drm_device *dev); void vc4_bo_cache_destroy(struct drm_device *dev); -int vc4_bo_stats_debugfs(struct seq_file *m, void *arg); int vc4_bo_inc_usecnt(struct vc4_bo *bo); void vc4_bo_dec_usecnt(struct vc4_bo *bo); void vc4_bo_add_to_purgeable_pool(struct vc4_bo *bo); @@ -716,7 +728,6 @@ void vc4_bo_remove_from_purgeable_pool(struct vc4_bo *bo); /* vc4_crtc.c */ extern struct platform_driver vc4_crtc_driver; -int vc4_crtc_debugfs_regs(struct seq_file *m, void *arg); bool vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id, bool in_vblank_irq, int *vpos, int *hpos, ktime_t *stime, ktime_t *etime, @@ -729,17 +740,37 @@ void vc4_crtc_get_margins(struct drm_crtc_state *state, /* vc4_debugfs.c */ int vc4_debugfs_init(struct drm_minor *minor); +#ifdef CONFIG_DEBUG_FS +void vc4_debugfs_add_file(struct drm_device *drm, + const char *filename, + int (*show)(struct seq_file*, void*), + void *data); +void vc4_debugfs_add_regset32(struct drm_device *drm, + const char *filename, + struct debugfs_regset32 *regset); +#else +static inline void vc4_debugfs_add_file(struct drm_device *drm, + const char *filename, + int (*show)(struct seq_file*, void*), + void *data) +{ +} + +static inline void vc4_debugfs_add_regset32(struct drm_device *drm, + const char *filename, + struct debugfs_regset32 *regset) +{ +} +#endif /* vc4_drv.c */ void __iomem *vc4_ioremap_regs(struct platform_device *dev, int index); /* vc4_dpi.c */ extern struct platform_driver vc4_dpi_driver; -int vc4_dpi_debugfs_regs(struct seq_file *m, void *unused); /* vc4_dsi.c */ extern struct platform_driver vc4_dsi_driver; -int vc4_dsi_debugfs_regs(struct seq_file *m, void *unused); /* vc4_fence.c */ extern const struct dma_fence_ops vc4_fence_ops; @@ -767,15 +798,12 @@ int vc4_gem_madvise_ioctl(struct drm_device *dev, void *data, /* vc4_hdmi.c */ extern struct platform_driver vc4_hdmi_driver; -int vc4_hdmi_debugfs_regs(struct seq_file *m, void *unused); /* vc4_vec.c */ extern struct platform_driver vc4_vec_driver; -int vc4_vec_debugfs_regs(struct seq_file *m, void *unused); /* vc4_txp.c */ extern struct platform_driver vc4_txp_driver; -int vc4_txp_debugfs_regs(struct seq_file *m, void *unused); /* vc4_irq.c */ irqreturn_t vc4_irq(int irq, void *arg); @@ -787,8 +815,6 @@ void vc4_irq_reset(struct drm_device *dev); /* vc4_hvs.c */ extern struct platform_driver vc4_hvs_driver; void vc4_hvs_dump_state(struct drm_device *dev); -int vc4_hvs_debugfs_regs(struct seq_file *m, void *unused); -int vc4_hvs_debugfs_underrun(struct seq_file *m, void *unused); void vc4_hvs_unmask_underrun(struct drm_device *dev, int channel); void vc4_hvs_mask_underrun(struct drm_device *dev, int channel); @@ -805,9 +831,10 @@ void vc4_plane_async_set_fb(struct drm_plane *plane, /* vc4_v3d.c */ extern struct platform_driver vc4_v3d_driver; -int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused); -int vc4_v3d_debugfs_regs(struct seq_file *m, void *unused); +extern const struct of_device_id vc4_v3d_dt_match[]; int vc4_v3d_get_bin_slot(struct vc4_dev *vc4); +int vc4_v3d_pm_get(struct vc4_dev *vc4); +void vc4_v3d_pm_put(struct vc4_dev *vc4); /* vc4_validate.c */ int diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c index 11702e1d9011..9412709067f5 100644 --- a/drivers/gpu/drm/vc4/vc4_dsi.c +++ b/drivers/gpu/drm/vc4/vc4_dsi.c @@ -545,6 +545,8 @@ struct vc4_dsi { struct completion xfer_completion; int xfer_result; + + struct debugfs_regset32 regset; }; #define host_to_dsi(host) container_of(host, struct vc4_dsi, dsi_host) @@ -605,113 +607,56 @@ to_vc4_dsi_encoder(struct drm_encoder *encoder) return container_of(encoder, struct vc4_dsi_encoder, base.base); } -#define DSI_REG(reg) { reg, #reg } -static const struct { - u32 reg; - const char *name; -} dsi0_regs[] = { - DSI_REG(DSI0_CTRL), - DSI_REG(DSI0_STAT), - DSI_REG(DSI0_HSTX_TO_CNT), - DSI_REG(DSI0_LPRX_TO_CNT), - DSI_REG(DSI0_TA_TO_CNT), - DSI_REG(DSI0_PR_TO_CNT), - DSI_REG(DSI0_DISP0_CTRL), - DSI_REG(DSI0_DISP1_CTRL), - DSI_REG(DSI0_INT_STAT), - DSI_REG(DSI0_INT_EN), - DSI_REG(DSI0_PHYC), - DSI_REG(DSI0_HS_CLT0), - DSI_REG(DSI0_HS_CLT1), - DSI_REG(DSI0_HS_CLT2), - DSI_REG(DSI0_HS_DLT3), - DSI_REG(DSI0_HS_DLT4), - DSI_REG(DSI0_HS_DLT5), - DSI_REG(DSI0_HS_DLT6), - DSI_REG(DSI0_HS_DLT7), - DSI_REG(DSI0_PHY_AFEC0), - DSI_REG(DSI0_PHY_AFEC1), - DSI_REG(DSI0_ID), +static const struct debugfs_reg32 dsi0_regs[] = { + VC4_REG32(DSI0_CTRL), + VC4_REG32(DSI0_STAT), + VC4_REG32(DSI0_HSTX_TO_CNT), + VC4_REG32(DSI0_LPRX_TO_CNT), + VC4_REG32(DSI0_TA_TO_CNT), + VC4_REG32(DSI0_PR_TO_CNT), + VC4_REG32(DSI0_DISP0_CTRL), + VC4_REG32(DSI0_DISP1_CTRL), + VC4_REG32(DSI0_INT_STAT), + VC4_REG32(DSI0_INT_EN), + VC4_REG32(DSI0_PHYC), + VC4_REG32(DSI0_HS_CLT0), + VC4_REG32(DSI0_HS_CLT1), + VC4_REG32(DSI0_HS_CLT2), + VC4_REG32(DSI0_HS_DLT3), + VC4_REG32(DSI0_HS_DLT4), + VC4_REG32(DSI0_HS_DLT5), + VC4_REG32(DSI0_HS_DLT6), + VC4_REG32(DSI0_HS_DLT7), + VC4_REG32(DSI0_PHY_AFEC0), + VC4_REG32(DSI0_PHY_AFEC1), + VC4_REG32(DSI0_ID), }; -static const struct { - u32 reg; - const char *name; -} dsi1_regs[] = { - DSI_REG(DSI1_CTRL), - DSI_REG(DSI1_STAT), - DSI_REG(DSI1_HSTX_TO_CNT), - DSI_REG(DSI1_LPRX_TO_CNT), - DSI_REG(DSI1_TA_TO_CNT), - DSI_REG(DSI1_PR_TO_CNT), - DSI_REG(DSI1_DISP0_CTRL), - DSI_REG(DSI1_DISP1_CTRL), - DSI_REG(DSI1_INT_STAT), - DSI_REG(DSI1_INT_EN), - DSI_REG(DSI1_PHYC), - DSI_REG(DSI1_HS_CLT0), - DSI_REG(DSI1_HS_CLT1), - DSI_REG(DSI1_HS_CLT2), - DSI_REG(DSI1_HS_DLT3), - DSI_REG(DSI1_HS_DLT4), - DSI_REG(DSI1_HS_DLT5), - DSI_REG(DSI1_HS_DLT6), - DSI_REG(DSI1_HS_DLT7), - DSI_REG(DSI1_PHY_AFEC0), - DSI_REG(DSI1_PHY_AFEC1), - DSI_REG(DSI1_ID), +static const struct debugfs_reg32 dsi1_regs[] = { + VC4_REG32(DSI1_CTRL), + VC4_REG32(DSI1_STAT), + VC4_REG32(DSI1_HSTX_TO_CNT), + VC4_REG32(DSI1_LPRX_TO_CNT), + VC4_REG32(DSI1_TA_TO_CNT), + VC4_REG32(DSI1_PR_TO_CNT), + VC4_REG32(DSI1_DISP0_CTRL), + VC4_REG32(DSI1_DISP1_CTRL), + VC4_REG32(DSI1_INT_STAT), + VC4_REG32(DSI1_INT_EN), + VC4_REG32(DSI1_PHYC), + VC4_REG32(DSI1_HS_CLT0), + VC4_REG32(DSI1_HS_CLT1), + VC4_REG32(DSI1_HS_CLT2), + VC4_REG32(DSI1_HS_DLT3), + VC4_REG32(DSI1_HS_DLT4), + VC4_REG32(DSI1_HS_DLT5), + VC4_REG32(DSI1_HS_DLT6), + VC4_REG32(DSI1_HS_DLT7), + VC4_REG32(DSI1_PHY_AFEC0), + VC4_REG32(DSI1_PHY_AFEC1), + VC4_REG32(DSI1_ID), }; -static void vc4_dsi_dump_regs(struct vc4_dsi *dsi) -{ - int i; - - if (dsi->port == 0) { - for (i = 0; i < ARRAY_SIZE(dsi0_regs); i++) { - DRM_INFO("0x%04x (%s): 0x%08x\n", - dsi0_regs[i].reg, dsi0_regs[i].name, - DSI_READ(dsi0_regs[i].reg)); - } - } else { - for (i = 0; i < ARRAY_SIZE(dsi1_regs); i++) { - DRM_INFO("0x%04x (%s): 0x%08x\n", - dsi1_regs[i].reg, dsi1_regs[i].name, - DSI_READ(dsi1_regs[i].reg)); - } - } -} - -#ifdef CONFIG_DEBUG_FS -int vc4_dsi_debugfs_regs(struct seq_file *m, void *unused) -{ - struct drm_info_node *node = (struct drm_info_node *)m->private; - struct drm_device *drm = node->minor->dev; - struct vc4_dev *vc4 = to_vc4_dev(drm); - int dsi_index = (uintptr_t)node->info_ent->data; - struct vc4_dsi *dsi = (dsi_index == 1 ? vc4->dsi1 : NULL); - int i; - - if (!dsi) - return 0; - - if (dsi->port == 0) { - for (i = 0; i < ARRAY_SIZE(dsi0_regs); i++) { - seq_printf(m, "0x%04x (%s): 0x%08x\n", - dsi0_regs[i].reg, dsi0_regs[i].name, - DSI_READ(dsi0_regs[i].reg)); - } - } else { - for (i = 0; i < ARRAY_SIZE(dsi1_regs); i++) { - seq_printf(m, "0x%04x (%s): 0x%08x\n", - dsi1_regs[i].reg, dsi1_regs[i].name, - DSI_READ(dsi1_regs[i].reg)); - } - } - - return 0; -} -#endif - static void vc4_dsi_encoder_destroy(struct drm_encoder *encoder) { drm_encoder_cleanup(encoder); @@ -900,8 +845,9 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder) } if (debug_dump_regs) { - DRM_INFO("DSI regs before:\n"); - vc4_dsi_dump_regs(dsi); + struct drm_printer p = drm_info_printer(&dsi->pdev->dev); + dev_info(&dsi->pdev->dev, "DSI regs before:\n"); + drm_print_regset32(&p, &dsi->regset); } /* Round up the clk_set_rate() request slightly, since @@ -1135,8 +1081,9 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder) drm_bridge_enable(dsi->bridge); if (debug_dump_regs) { - DRM_INFO("DSI regs after:\n"); - vc4_dsi_dump_regs(dsi); + struct drm_printer p = drm_info_printer(&dsi->pdev->dev); + dev_info(&dsi->pdev->dev, "DSI regs after:\n"); + drm_print_regset32(&p, &dsi->regset); } } @@ -1527,6 +1474,15 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data) if (IS_ERR(dsi->regs)) return PTR_ERR(dsi->regs); + dsi->regset.base = dsi->regs; + if (dsi->port == 0) { + dsi->regset.regs = dsi0_regs; + dsi->regset.nregs = ARRAY_SIZE(dsi0_regs); + } else { + dsi->regset.regs = dsi1_regs; + dsi->regset.nregs = ARRAY_SIZE(dsi1_regs); + } + if (DSI_PORT_READ(ID) != DSI_ID_VALUE) { dev_err(dev, "Port returned 0x%08x for ID instead of 0x%08x\n", DSI_PORT_READ(ID), DSI_ID_VALUE); @@ -1662,6 +1618,11 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data) */ dsi->encoder->bridge = NULL; + if (dsi->port == 0) + vc4_debugfs_add_regset32(drm, "dsi0_regs", &dsi->regset); + else + vc4_debugfs_add_regset32(drm, "dsi1_regs", &dsi->regset); + pm_runtime_enable(dev); return 0; diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 5ee5bf7fedf7..d9311be32a4f 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -74,6 +74,11 @@ vc4_get_hang_state_ioctl(struct drm_device *dev, void *data, u32 i; int ret = 0; + if (!vc4->v3d) { + DRM_DEBUG("VC4_GET_HANG_STATE with no VC4 V3D probed\n"); + return -ENODEV; + } + spin_lock_irqsave(&vc4->job_lock, irqflags); kernel_state = vc4->hang_state; if (!kernel_state) { @@ -964,12 +969,7 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec) /* Release the reference we had on the perf monitor. */ vc4_perfmon_put(exec->perfmon); - mutex_lock(&vc4->power_lock); - if (--vc4->power_refcount == 0) { - pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev); - pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev); - } - mutex_unlock(&vc4->power_lock); + vc4_v3d_pm_put(vc4); kfree(exec); } @@ -1124,6 +1124,11 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data, struct dma_fence *in_fence; int ret = 0; + if (!vc4->v3d) { + DRM_DEBUG("VC4_SUBMIT_CL with no VC4 V3D probed\n"); + return -ENODEV; + } + if ((args->flags & ~(VC4_SUBMIT_CL_USE_CLEAR_COLOR | VC4_SUBMIT_CL_FIXED_RCL_ORDER | VC4_SUBMIT_CL_RCL_ORDER_INCREASING_X | @@ -1143,17 +1148,11 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data, return -ENOMEM; } - mutex_lock(&vc4->power_lock); - if (vc4->power_refcount++ == 0) { - ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); - if (ret < 0) { - mutex_unlock(&vc4->power_lock); - vc4->power_refcount--; - kfree(exec); - return ret; - } + ret = vc4_v3d_pm_get(vc4); + if (ret) { + kfree(exec); + return ret; } - mutex_unlock(&vc4->power_lock); exec->args = args; INIT_LIST_HEAD(&exec->unref_list); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 88fd5df7e7dc..99fc8569e0f5 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -97,6 +97,9 @@ struct vc4_hdmi { struct clk *pixel_clock; struct clk *hsm_clock; + + struct debugfs_regset32 hdmi_regset; + struct debugfs_regset32 hd_regset; }; #define HDMI_READ(offset) readl(vc4->hdmi->hdmicore_regs + offset) @@ -134,103 +137,69 @@ to_vc4_hdmi_connector(struct drm_connector *connector) return container_of(connector, struct vc4_hdmi_connector, base); } -#define HDMI_REG(reg) { reg, #reg } -static const struct { - u32 reg; - const char *name; -} hdmi_regs[] = { - HDMI_REG(VC4_HDMI_CORE_REV), - HDMI_REG(VC4_HDMI_SW_RESET_CONTROL), - HDMI_REG(VC4_HDMI_HOTPLUG_INT), - HDMI_REG(VC4_HDMI_HOTPLUG), - HDMI_REG(VC4_HDMI_MAI_CHANNEL_MAP), - HDMI_REG(VC4_HDMI_MAI_CONFIG), - HDMI_REG(VC4_HDMI_MAI_FORMAT), - HDMI_REG(VC4_HDMI_AUDIO_PACKET_CONFIG), - HDMI_REG(VC4_HDMI_RAM_PACKET_CONFIG), - HDMI_REG(VC4_HDMI_HORZA), - HDMI_REG(VC4_HDMI_HORZB), - HDMI_REG(VC4_HDMI_FIFO_CTL), - HDMI_REG(VC4_HDMI_SCHEDULER_CONTROL), - HDMI_REG(VC4_HDMI_VERTA0), - HDMI_REG(VC4_HDMI_VERTA1), - HDMI_REG(VC4_HDMI_VERTB0), - HDMI_REG(VC4_HDMI_VERTB1), - HDMI_REG(VC4_HDMI_TX_PHY_RESET_CTL), - HDMI_REG(VC4_HDMI_TX_PHY_CTL0), - - HDMI_REG(VC4_HDMI_CEC_CNTRL_1), - HDMI_REG(VC4_HDMI_CEC_CNTRL_2), - HDMI_REG(VC4_HDMI_CEC_CNTRL_3), - HDMI_REG(VC4_HDMI_CEC_CNTRL_4), - HDMI_REG(VC4_HDMI_CEC_CNTRL_5), - HDMI_REG(VC4_HDMI_CPU_STATUS), - HDMI_REG(VC4_HDMI_CPU_MASK_STATUS), - - HDMI_REG(VC4_HDMI_CEC_RX_DATA_1), - HDMI_REG(VC4_HDMI_CEC_RX_DATA_2), - HDMI_REG(VC4_HDMI_CEC_RX_DATA_3), - HDMI_REG(VC4_HDMI_CEC_RX_DATA_4), - HDMI_REG(VC4_HDMI_CEC_TX_DATA_1), - HDMI_REG(VC4_HDMI_CEC_TX_DATA_2), - HDMI_REG(VC4_HDMI_CEC_TX_DATA_3), - HDMI_REG(VC4_HDMI_CEC_TX_DATA_4), +static const struct debugfs_reg32 hdmi_regs[] = { + VC4_REG32(VC4_HDMI_CORE_REV), + VC4_REG32(VC4_HDMI_SW_RESET_CONTROL), + VC4_REG32(VC4_HDMI_HOTPLUG_INT), + VC4_REG32(VC4_HDMI_HOTPLUG), + VC4_REG32(VC4_HDMI_MAI_CHANNEL_MAP), + VC4_REG32(VC4_HDMI_MAI_CONFIG), + VC4_REG32(VC4_HDMI_MAI_FORMAT), + VC4_REG32(VC4_HDMI_AUDIO_PACKET_CONFIG), + VC4_REG32(VC4_HDMI_RAM_PACKET_CONFIG), + VC4_REG32(VC4_HDMI_HORZA), + VC4_REG32(VC4_HDMI_HORZB), + VC4_REG32(VC4_HDMI_FIFO_CTL), + VC4_REG32(VC4_HDMI_SCHEDULER_CONTROL), + VC4_REG32(VC4_HDMI_VERTA0), + VC4_REG32(VC4_HDMI_VERTA1), + VC4_REG32(VC4_HDMI_VERTB0), + VC4_REG32(VC4_HDMI_VERTB1), + VC4_REG32(VC4_HDMI_TX_PHY_RESET_CTL), + VC4_REG32(VC4_HDMI_TX_PHY_CTL0), + + VC4_REG32(VC4_HDMI_CEC_CNTRL_1), + VC4_REG32(VC4_HDMI_CEC_CNTRL_2), + VC4_REG32(VC4_HDMI_CEC_CNTRL_3), + VC4_REG32(VC4_HDMI_CEC_CNTRL_4), + VC4_REG32(VC4_HDMI_CEC_CNTRL_5), + VC4_REG32(VC4_HDMI_CPU_STATUS), + VC4_REG32(VC4_HDMI_CPU_MASK_STATUS), + + VC4_REG32(VC4_HDMI_CEC_RX_DATA_1), + VC4_REG32(VC4_HDMI_CEC_RX_DATA_2), + VC4_REG32(VC4_HDMI_CEC_RX_DATA_3), + VC4_REG32(VC4_HDMI_CEC_RX_DATA_4), + VC4_REG32(VC4_HDMI_CEC_TX_DATA_1), + VC4_REG32(VC4_HDMI_CEC_TX_DATA_2), + VC4_REG32(VC4_HDMI_CEC_TX_DATA_3), + VC4_REG32(VC4_HDMI_CEC_TX_DATA_4), }; -static const struct { - u32 reg; - const char *name; -} hd_regs[] = { - HDMI_REG(VC4_HD_M_CTL), - HDMI_REG(VC4_HD_MAI_CTL), - HDMI_REG(VC4_HD_MAI_THR), - HDMI_REG(VC4_HD_MAI_FMT), - HDMI_REG(VC4_HD_MAI_SMP), - HDMI_REG(VC4_HD_VID_CTL), - HDMI_REG(VC4_HD_CSC_CTL), - HDMI_REG(VC4_HD_FRAME_COUNT), +static const struct debugfs_reg32 hd_regs[] = { + VC4_REG32(VC4_HD_M_CTL), + VC4_REG32(VC4_HD_MAI_CTL), + VC4_REG32(VC4_HD_MAI_THR), + VC4_REG32(VC4_HD_MAI_FMT), + VC4_REG32(VC4_HD_MAI_SMP), + VC4_REG32(VC4_HD_VID_CTL), + VC4_REG32(VC4_HD_CSC_CTL), + VC4_REG32(VC4_HD_FRAME_COUNT), }; -#ifdef CONFIG_DEBUG_FS -int vc4_hdmi_debugfs_regs(struct seq_file *m, void *unused) +static int vc4_hdmi_debugfs_regs(struct seq_file *m, void *unused) { struct drm_info_node *node = (struct drm_info_node *)m->private; struct drm_device *dev = node->minor->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); - int i; - - for (i = 0; i < ARRAY_SIZE(hdmi_regs); i++) { - seq_printf(m, "%s (0x%04x): 0x%08x\n", - hdmi_regs[i].name, hdmi_regs[i].reg, - HDMI_READ(hdmi_regs[i].reg)); - } + struct vc4_hdmi *hdmi = vc4->hdmi; + struct drm_printer p = drm_seq_file_printer(m); - for (i = 0; i < ARRAY_SIZE(hd_regs); i++) { - seq_printf(m, "%s (0x%04x): 0x%08x\n", - hd_regs[i].name, hd_regs[i].reg, - HD_READ(hd_regs[i].reg)); - } + drm_print_regset32(&p, &hdmi->hdmi_regset); + drm_print_regset32(&p, &hdmi->hd_regset); return 0; } -#endif /* CONFIG_DEBUG_FS */ - -static void vc4_hdmi_dump_regs(struct drm_device *dev) -{ - struct vc4_dev *vc4 = to_vc4_dev(dev); - int i; - - for (i = 0; i < ARRAY_SIZE(hdmi_regs); i++) { - DRM_INFO("0x%04x (%s): 0x%08x\n", - hdmi_regs[i].reg, hdmi_regs[i].name, - HDMI_READ(hdmi_regs[i].reg)); - } - for (i = 0; i < ARRAY_SIZE(hd_regs); i++) { - DRM_INFO("0x%04x (%s): 0x%08x\n", - hd_regs[i].reg, hd_regs[i].name, - HD_READ(hd_regs[i].reg)); - } -} static enum drm_connector_status vc4_hdmi_connector_detect(struct drm_connector *connector, bool force) @@ -561,8 +530,11 @@ static void vc4_hdmi_encoder_enable(struct drm_encoder *encoder) HDMI_WRITE(VC4_HDMI_TX_PHY_RESET_CTL, 0); if (debug_dump_regs) { - DRM_INFO("HDMI regs before:\n"); - vc4_hdmi_dump_regs(dev); + struct drm_printer p = drm_info_printer(&hdmi->pdev->dev); + + dev_info(&hdmi->pdev->dev, "HDMI regs before:\n"); + drm_print_regset32(&p, &hdmi->hdmi_regset); + drm_print_regset32(&p, &hdmi->hd_regset); } HD_WRITE(VC4_HD_VID_CTL, 0); @@ -637,8 +609,11 @@ static void vc4_hdmi_encoder_enable(struct drm_encoder *encoder) HDMI_WRITE(VC4_HDMI_FIFO_CTL, VC4_HDMI_FIFO_CTL_MASTER_SLAVE_N); if (debug_dump_regs) { - DRM_INFO("HDMI regs after:\n"); - vc4_hdmi_dump_regs(dev); + struct drm_printer p = drm_info_printer(&hdmi->pdev->dev); + + dev_info(&hdmi->pdev->dev, "HDMI regs after:\n"); + drm_print_regset32(&p, &hdmi->hdmi_regset); + drm_print_regset32(&p, &hdmi->hd_regset); } HD_WRITE(VC4_HD_VID_CTL, @@ -1333,6 +1308,13 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) if (IS_ERR(hdmi->hd_regs)) return PTR_ERR(hdmi->hd_regs); + hdmi->hdmi_regset.base = hdmi->hdmicore_regs; + hdmi->hdmi_regset.regs = hdmi_regs; + hdmi->hdmi_regset.nregs = ARRAY_SIZE(hdmi_regs); + hdmi->hd_regset.base = hdmi->hd_regs; + hdmi->hd_regset.regs = hd_regs; + hdmi->hd_regset.nregs = ARRAY_SIZE(hd_regs); + hdmi->pixel_clock = devm_clk_get(dev, "pixel"); if (IS_ERR(hdmi->pixel_clock)) { DRM_ERROR("Failed to get pixel clock\n"); @@ -1448,6 +1430,8 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) if (ret) goto err_destroy_encoder; + vc4_debugfs_add_file(drm, "hdmi_regs", vc4_hdmi_debugfs_regs, hdmi); + return 0; #ifdef CONFIG_DRM_VC4_HDMI_CEC diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c index 918e71256ecc..f746e9a7a88c 100644 --- a/drivers/gpu/drm/vc4/vc4_hvs.c +++ b/drivers/gpu/drm/vc4/vc4_hvs.c @@ -27,54 +27,47 @@ #include "vc4_drv.h" #include "vc4_regs.h" -#define HVS_REG(reg) { reg, #reg } -static const struct { - u32 reg; - const char *name; -} hvs_regs[] = { - HVS_REG(SCALER_DISPCTRL), - HVS_REG(SCALER_DISPSTAT), - HVS_REG(SCALER_DISPID), - HVS_REG(SCALER_DISPECTRL), - HVS_REG(SCALER_DISPPROF), - HVS_REG(SCALER_DISPDITHER), - HVS_REG(SCALER_DISPEOLN), - HVS_REG(SCALER_DISPLIST0), - HVS_REG(SCALER_DISPLIST1), - HVS_REG(SCALER_DISPLIST2), - HVS_REG(SCALER_DISPLSTAT), - HVS_REG(SCALER_DISPLACT0), - HVS_REG(SCALER_DISPLACT1), - HVS_REG(SCALER_DISPLACT2), - HVS_REG(SCALER_DISPCTRL0), - HVS_REG(SCALER_DISPBKGND0), - HVS_REG(SCALER_DISPSTAT0), - HVS_REG(SCALER_DISPBASE0), - HVS_REG(SCALER_DISPCTRL1), - HVS_REG(SCALER_DISPBKGND1), - HVS_REG(SCALER_DISPSTAT1), - HVS_REG(SCALER_DISPBASE1), - HVS_REG(SCALER_DISPCTRL2), - HVS_REG(SCALER_DISPBKGND2), - HVS_REG(SCALER_DISPSTAT2), - HVS_REG(SCALER_DISPBASE2), - HVS_REG(SCALER_DISPALPHA2), - HVS_REG(SCALER_OLEDOFFS), - HVS_REG(SCALER_OLEDCOEF0), - HVS_REG(SCALER_OLEDCOEF1), - HVS_REG(SCALER_OLEDCOEF2), +static const struct debugfs_reg32 hvs_regs[] = { + VC4_REG32(SCALER_DISPCTRL), + VC4_REG32(SCALER_DISPSTAT), + VC4_REG32(SCALER_DISPID), + VC4_REG32(SCALER_DISPECTRL), + VC4_REG32(SCALER_DISPPROF), + VC4_REG32(SCALER_DISPDITHER), + VC4_REG32(SCALER_DISPEOLN), + VC4_REG32(SCALER_DISPLIST0), + VC4_REG32(SCALER_DISPLIST1), + VC4_REG32(SCALER_DISPLIST2), + VC4_REG32(SCALER_DISPLSTAT), + VC4_REG32(SCALER_DISPLACT0), + VC4_REG32(SCALER_DISPLACT1), + VC4_REG32(SCALER_DISPLACT2), + VC4_REG32(SCALER_DISPCTRL0), + VC4_REG32(SCALER_DISPBKGND0), + VC4_REG32(SCALER_DISPSTAT0), + VC4_REG32(SCALER_DISPBASE0), + VC4_REG32(SCALER_DISPCTRL1), + VC4_REG32(SCALER_DISPBKGND1), + VC4_REG32(SCALER_DISPSTAT1), + VC4_REG32(SCALER_DISPBASE1), + VC4_REG32(SCALER_DISPCTRL2), + VC4_REG32(SCALER_DISPBKGND2), + VC4_REG32(SCALER_DISPSTAT2), + VC4_REG32(SCALER_DISPBASE2), + VC4_REG32(SCALER_DISPALPHA2), + VC4_REG32(SCALER_OLEDOFFS), + VC4_REG32(SCALER_OLEDCOEF0), + VC4_REG32(SCALER_OLEDCOEF1), + VC4_REG32(SCALER_OLEDCOEF2), }; void vc4_hvs_dump_state(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); + struct drm_printer p = drm_info_printer(&vc4->hvs->pdev->dev); int i; - for (i = 0; i < ARRAY_SIZE(hvs_regs); i++) { - DRM_INFO("0x%04x (%s): 0x%08x\n", - hvs_regs[i].reg, hvs_regs[i].name, - HVS_READ(hvs_regs[i].reg)); - } + drm_print_regset32(&p, &vc4->hvs->regset); DRM_INFO("HVS ctx:\n"); for (i = 0; i < 64; i += 4) { @@ -87,24 +80,7 @@ void vc4_hvs_dump_state(struct drm_device *dev) } } -#ifdef CONFIG_DEBUG_FS -int vc4_hvs_debugfs_regs(struct seq_file *m, void *unused) -{ - struct drm_info_node *node = (struct drm_info_node *)m->private; - struct drm_device *dev = node->minor->dev; - struct vc4_dev *vc4 = to_vc4_dev(dev); - int i; - - for (i = 0; i < ARRAY_SIZE(hvs_regs); i++) { - seq_printf(m, "%s (0x%04x): 0x%08x\n", - hvs_regs[i].name, hvs_regs[i].reg, - HVS_READ(hvs_regs[i].reg)); - } - - return 0; -} - -int vc4_hvs_debugfs_underrun(struct seq_file *m, void *data) +static int vc4_hvs_debugfs_underrun(struct seq_file *m, void *data) { struct drm_info_node *node = m->private; struct drm_device *dev = node->minor->dev; @@ -115,7 +91,6 @@ int vc4_hvs_debugfs_underrun(struct seq_file *m, void *data) return 0; } -#endif /* The filter kernel is composed of dwords each containing 3 9-bit * signed integers packed next to each other. @@ -259,6 +234,10 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) if (IS_ERR(hvs->regs)) return PTR_ERR(hvs->regs); + hvs->regset.base = hvs->regs; + hvs->regset.regs = hvs_regs; + hvs->regset.nregs = ARRAY_SIZE(hvs_regs); + hvs->dlist = hvs->regs + SCALER_DLIST_START; spin_lock_init(&hvs->mm_lock); @@ -323,6 +302,10 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) if (ret) return ret; + vc4_debugfs_add_regset32(drm, "hvs_regs", &hvs->regset); + vc4_debugfs_add_file(drm, "hvs_underrun", vc4_hvs_debugfs_underrun, + NULL); + return 0; } diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index 4cd2ccfe15f4..ffd0a4388752 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -229,6 +229,9 @@ vc4_irq_preinstall(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); + if (!vc4->v3d) + return; + init_waitqueue_head(&vc4->job_wait_queue); INIT_WORK(&vc4->overflow_mem_work, vc4_overflow_mem_work); @@ -243,6 +246,9 @@ vc4_irq_postinstall(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); + if (!vc4->v3d) + return 0; + /* Enable both the render done and out of memory interrupts. */ V3D_WRITE(V3D_INTENA, V3D_DRIVER_IRQS); @@ -254,6 +260,9 @@ vc4_irq_uninstall(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); + if (!vc4->v3d) + return; + /* Disable sending interrupts for our driver's IRQs. */ V3D_WRITE(V3D_INTDIS, V3D_DRIVER_IRQS); diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 5160cad25fce..295dacc8bcb9 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -525,6 +525,7 @@ int vc4_kms_load(struct drm_device *dev) /* Set support for vblank irq fast disable, before drm_vblank_init() */ dev->vblank_disable_immediate = true; + dev->irq_enabled = true; ret = drm_vblank_init(dev, dev->mode_config.num_crtc); if (ret < 0) { dev_err(dev->dev, "failed to initialize vblank\n"); diff --git a/drivers/gpu/drm/vc4/vc4_perfmon.c b/drivers/gpu/drm/vc4/vc4_perfmon.c index 495150415020..f4aa75efd16b 100644 --- a/drivers/gpu/drm/vc4/vc4_perfmon.c +++ b/drivers/gpu/drm/vc4/vc4_perfmon.c @@ -100,12 +100,18 @@ void vc4_perfmon_close_file(struct vc4_file *vc4file) int vc4_perfmon_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_file *vc4file = file_priv->driver_priv; struct drm_vc4_perfmon_create *req = data; struct vc4_perfmon *perfmon; unsigned int i; int ret; + if (!vc4->v3d) { + DRM_DEBUG("Creating perfmon no VC4 V3D probed\n"); + return -ENODEV; + } + /* Number of monitored counters cannot exceed HW limits. */ if (req->ncounters > DRM_VC4_MAX_PERF_COUNTERS || !req->ncounters) @@ -146,10 +152,16 @@ int vc4_perfmon_create_ioctl(struct drm_device *dev, void *data, int vc4_perfmon_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_file *vc4file = file_priv->driver_priv; struct drm_vc4_perfmon_destroy *req = data; struct vc4_perfmon *perfmon; + if (!vc4->v3d) { + DRM_DEBUG("Destroying perfmon no VC4 V3D probed\n"); + return -ENODEV; + } + mutex_lock(&vc4file->perfmon.lock); perfmon = idr_remove(&vc4file->perfmon.idr, req->id); mutex_unlock(&vc4file->perfmon.lock); @@ -164,11 +176,17 @@ int vc4_perfmon_destroy_ioctl(struct drm_device *dev, void *data, int vc4_perfmon_get_values_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { + struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_file *vc4file = file_priv->driver_priv; struct drm_vc4_perfmon_get_values *req = data; struct vc4_perfmon *perfmon; int ret; + if (!vc4->v3d) { + DRM_DEBUG("Getting perfmon no VC4 V3D probed\n"); + return -ENODEV; + } + mutex_lock(&vc4file->perfmon.lock); perfmon = idr_find(&vc4file->perfmon.idr, req->id); vc4_perfmon_get(perfmon); diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c index 273984f71ae2..3c918eeaf56e 100644 --- a/drivers/gpu/drm/vc4/vc4_render_cl.c +++ b/drivers/gpu/drm/vc4/vc4_render_cl.c @@ -148,6 +148,12 @@ static void emit_tile(struct vc4_exec_info *exec, } if (setup->zs_read) { + if (setup->color_read) { + /* Exec previous load. */ + vc4_tile_coordinates(setup, x, y); + vc4_store_before_load(setup); + } + if (args->zs_read.flags & VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) { rcl_u8(setup, VC4_PACKET_LOAD_FULL_RES_TILE_BUFFER); @@ -156,12 +162,6 @@ static void emit_tile(struct vc4_exec_info *exec, &args->zs_read, x, y) | VC4_LOADSTORE_FULL_RES_DISABLE_COLOR); } else { - if (setup->color_read) { - /* Exec previous load. */ - vc4_tile_coordinates(setup, x, y); - vc4_store_before_load(setup); - } - rcl_u8(setup, VC4_PACKET_LOAD_TILE_BUFFER_GENERAL); rcl_u16(setup, args->zs_read.bits); rcl_u32(setup, setup->zs_read->paddr + @@ -291,16 +291,15 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec, } } if (setup->zs_read) { + if (setup->color_read) { + loop_body_size += VC4_PACKET_TILE_COORDINATES_SIZE; + loop_body_size += VC4_PACKET_STORE_TILE_BUFFER_GENERAL_SIZE; + } + if (args->zs_read.flags & VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES) { loop_body_size += VC4_PACKET_LOAD_FULL_RES_TILE_BUFFER_SIZE; } else { - if (setup->color_read && - !(args->color_read.flags & - VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES)) { - loop_body_size += VC4_PACKET_TILE_COORDINATES_SIZE; - loop_body_size += VC4_PACKET_STORE_TILE_BUFFER_GENERAL_SIZE; - } loop_body_size += VC4_PACKET_LOAD_TILE_BUFFER_GENERAL_SIZE; } } diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c index cc2888dd7171..c8b89a78f9f4 100644 --- a/drivers/gpu/drm/vc4/vc4_txp.c +++ b/drivers/gpu/drm/vc4/vc4_txp.c @@ -148,6 +148,7 @@ struct vc4_txp { struct drm_writeback_connector connector; void __iomem *regs; + struct debugfs_regset32 regset; }; static inline struct vc4_txp *encoder_to_vc4_txp(struct drm_encoder *encoder) @@ -160,40 +161,14 @@ static inline struct vc4_txp *connector_to_vc4_txp(struct drm_connector *conn) return container_of(conn, struct vc4_txp, connector.base); } -#define TXP_REG(reg) { reg, #reg } -static const struct { - u32 reg; - const char *name; -} txp_regs[] = { - TXP_REG(TXP_DST_PTR), - TXP_REG(TXP_DST_PITCH), - TXP_REG(TXP_DIM), - TXP_REG(TXP_DST_CTRL), - TXP_REG(TXP_PROGRESS), +static const struct debugfs_reg32 txp_regs[] = { + VC4_REG32(TXP_DST_PTR), + VC4_REG32(TXP_DST_PITCH), + VC4_REG32(TXP_DIM), + VC4_REG32(TXP_DST_CTRL), + VC4_REG32(TXP_PROGRESS), }; -#ifdef CONFIG_DEBUG_FS -int vc4_txp_debugfs_regs(struct seq_file *m, void *unused) -{ - struct drm_info_node *node = (struct drm_info_node *)m->private; - struct drm_device *dev = node->minor->dev; - struct vc4_dev *vc4 = to_vc4_dev(dev); - struct vc4_txp *txp = vc4->txp; - int i; - - if (!txp) - return 0; - - for (i = 0; i < ARRAY_SIZE(txp_regs); i++) { - seq_printf(m, "%s (0x%04x): 0x%08x\n", - txp_regs[i].name, txp_regs[i].reg, - TXP_READ(txp_regs[i].reg)); - } - - return 0; -} -#endif - static int vc4_txp_connector_get_modes(struct drm_connector *connector) { struct drm_device *dev = connector->dev; @@ -410,6 +385,9 @@ static int vc4_txp_bind(struct device *dev, struct device *master, void *data) txp->regs = vc4_ioremap_regs(pdev, 0); if (IS_ERR(txp->regs)) return PTR_ERR(txp->regs); + txp->regset.base = txp->regs; + txp->regset.regs = txp_regs; + txp->regset.nregs = ARRAY_SIZE(txp_regs); drm_connector_helper_add(&txp->connector.base, &vc4_txp_connector_helper_funcs); @@ -428,6 +406,8 @@ static int vc4_txp_bind(struct device *dev, struct device *master, void *data) dev_set_drvdata(dev, txp); vc4->txp = txp; + vc4_debugfs_add_regset32(drm, "txp_regs", &txp->regset); + return 0; } diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index e47e29426078..a4b6859e3af6 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -22,129 +22,145 @@ #include "vc4_drv.h" #include "vc4_regs.h" -#ifdef CONFIG_DEBUG_FS -#define REGDEF(reg) { reg, #reg } -static const struct { - uint32_t reg; - const char *name; -} vc4_reg_defs[] = { - REGDEF(V3D_IDENT0), - REGDEF(V3D_IDENT1), - REGDEF(V3D_IDENT2), - REGDEF(V3D_SCRATCH), - REGDEF(V3D_L2CACTL), - REGDEF(V3D_SLCACTL), - REGDEF(V3D_INTCTL), - REGDEF(V3D_INTENA), - REGDEF(V3D_INTDIS), - REGDEF(V3D_CT0CS), - REGDEF(V3D_CT1CS), - REGDEF(V3D_CT0EA), - REGDEF(V3D_CT1EA), - REGDEF(V3D_CT0CA), - REGDEF(V3D_CT1CA), - REGDEF(V3D_CT00RA0), - REGDEF(V3D_CT01RA0), - REGDEF(V3D_CT0LC), - REGDEF(V3D_CT1LC), - REGDEF(V3D_CT0PC), - REGDEF(V3D_CT1PC), - REGDEF(V3D_PCS), - REGDEF(V3D_BFC), - REGDEF(V3D_RFC), - REGDEF(V3D_BPCA), - REGDEF(V3D_BPCS), - REGDEF(V3D_BPOA), - REGDEF(V3D_BPOS), - REGDEF(V3D_BXCF), - REGDEF(V3D_SQRSV0), - REGDEF(V3D_SQRSV1), - REGDEF(V3D_SQCNTL), - REGDEF(V3D_SRQPC), - REGDEF(V3D_SRQUA), - REGDEF(V3D_SRQUL), - REGDEF(V3D_SRQCS), - REGDEF(V3D_VPACNTL), - REGDEF(V3D_VPMBASE), - REGDEF(V3D_PCTRC), - REGDEF(V3D_PCTRE), - REGDEF(V3D_PCTR(0)), - REGDEF(V3D_PCTRS(0)), - REGDEF(V3D_PCTR(1)), - REGDEF(V3D_PCTRS(1)), - REGDEF(V3D_PCTR(2)), - REGDEF(V3D_PCTRS(2)), - REGDEF(V3D_PCTR(3)), - REGDEF(V3D_PCTRS(3)), - REGDEF(V3D_PCTR(4)), - REGDEF(V3D_PCTRS(4)), - REGDEF(V3D_PCTR(5)), - REGDEF(V3D_PCTRS(5)), - REGDEF(V3D_PCTR(6)), - REGDEF(V3D_PCTRS(6)), - REGDEF(V3D_PCTR(7)), - REGDEF(V3D_PCTRS(7)), - REGDEF(V3D_PCTR(8)), - REGDEF(V3D_PCTRS(8)), - REGDEF(V3D_PCTR(9)), - REGDEF(V3D_PCTRS(9)), - REGDEF(V3D_PCTR(10)), - REGDEF(V3D_PCTRS(10)), - REGDEF(V3D_PCTR(11)), - REGDEF(V3D_PCTRS(11)), - REGDEF(V3D_PCTR(12)), - REGDEF(V3D_PCTRS(12)), - REGDEF(V3D_PCTR(13)), - REGDEF(V3D_PCTRS(13)), - REGDEF(V3D_PCTR(14)), - REGDEF(V3D_PCTRS(14)), - REGDEF(V3D_PCTR(15)), - REGDEF(V3D_PCTRS(15)), - REGDEF(V3D_DBGE), - REGDEF(V3D_FDBGO), - REGDEF(V3D_FDBGB), - REGDEF(V3D_FDBGR), - REGDEF(V3D_FDBGS), - REGDEF(V3D_ERRSTAT), +static const struct debugfs_reg32 v3d_regs[] = { + VC4_REG32(V3D_IDENT0), + VC4_REG32(V3D_IDENT1), + VC4_REG32(V3D_IDENT2), + VC4_REG32(V3D_SCRATCH), + VC4_REG32(V3D_L2CACTL), + VC4_REG32(V3D_SLCACTL), + VC4_REG32(V3D_INTCTL), + VC4_REG32(V3D_INTENA), + VC4_REG32(V3D_INTDIS), + VC4_REG32(V3D_CT0CS), + VC4_REG32(V3D_CT1CS), + VC4_REG32(V3D_CT0EA), + VC4_REG32(V3D_CT1EA), + VC4_REG32(V3D_CT0CA), + VC4_REG32(V3D_CT1CA), + VC4_REG32(V3D_CT00RA0), + VC4_REG32(V3D_CT01RA0), + VC4_REG32(V3D_CT0LC), + VC4_REG32(V3D_CT1LC), + VC4_REG32(V3D_CT0PC), + VC4_REG32(V3D_CT1PC), + VC4_REG32(V3D_PCS), + VC4_REG32(V3D_BFC), + VC4_REG32(V3D_RFC), + VC4_REG32(V3D_BPCA), + VC4_REG32(V3D_BPCS), + VC4_REG32(V3D_BPOA), + VC4_REG32(V3D_BPOS), + VC4_REG32(V3D_BXCF), + VC4_REG32(V3D_SQRSV0), + VC4_REG32(V3D_SQRSV1), + VC4_REG32(V3D_SQCNTL), + VC4_REG32(V3D_SRQPC), + VC4_REG32(V3D_SRQUA), + VC4_REG32(V3D_SRQUL), + VC4_REG32(V3D_SRQCS), + VC4_REG32(V3D_VPACNTL), + VC4_REG32(V3D_VPMBASE), + VC4_REG32(V3D_PCTRC), + VC4_REG32(V3D_PCTRE), + VC4_REG32(V3D_PCTR(0)), + VC4_REG32(V3D_PCTRS(0)), + VC4_REG32(V3D_PCTR(1)), + VC4_REG32(V3D_PCTRS(1)), + VC4_REG32(V3D_PCTR(2)), + VC4_REG32(V3D_PCTRS(2)), + VC4_REG32(V3D_PCTR(3)), + VC4_REG32(V3D_PCTRS(3)), + VC4_REG32(V3D_PCTR(4)), + VC4_REG32(V3D_PCTRS(4)), + VC4_REG32(V3D_PCTR(5)), + VC4_REG32(V3D_PCTRS(5)), + VC4_REG32(V3D_PCTR(6)), + VC4_REG32(V3D_PCTRS(6)), + VC4_REG32(V3D_PCTR(7)), + VC4_REG32(V3D_PCTRS(7)), + VC4_REG32(V3D_PCTR(8)), + VC4_REG32(V3D_PCTRS(8)), + VC4_REG32(V3D_PCTR(9)), + VC4_REG32(V3D_PCTRS(9)), + VC4_REG32(V3D_PCTR(10)), + VC4_REG32(V3D_PCTRS(10)), + VC4_REG32(V3D_PCTR(11)), + VC4_REG32(V3D_PCTRS(11)), + VC4_REG32(V3D_PCTR(12)), + VC4_REG32(V3D_PCTRS(12)), + VC4_REG32(V3D_PCTR(13)), + VC4_REG32(V3D_PCTRS(13)), + VC4_REG32(V3D_PCTR(14)), + VC4_REG32(V3D_PCTRS(14)), + VC4_REG32(V3D_PCTR(15)), + VC4_REG32(V3D_PCTRS(15)), + VC4_REG32(V3D_DBGE), + VC4_REG32(V3D_FDBGO), + VC4_REG32(V3D_FDBGB), + VC4_REG32(V3D_FDBGR), + VC4_REG32(V3D_FDBGS), + VC4_REG32(V3D_ERRSTAT), }; -int vc4_v3d_debugfs_regs(struct seq_file *m, void *unused) +static int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused) { struct drm_info_node *node = (struct drm_info_node *)m->private; struct drm_device *dev = node->minor->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); - int i; - - for (i = 0; i < ARRAY_SIZE(vc4_reg_defs); i++) { - seq_printf(m, "%s (0x%04x): 0x%08x\n", - vc4_reg_defs[i].name, vc4_reg_defs[i].reg, - V3D_READ(vc4_reg_defs[i].reg)); + int ret = vc4_v3d_pm_get(vc4); + + if (ret == 0) { + uint32_t ident1 = V3D_READ(V3D_IDENT1); + uint32_t nslc = VC4_GET_FIELD(ident1, V3D_IDENT1_NSLC); + uint32_t tups = VC4_GET_FIELD(ident1, V3D_IDENT1_TUPS); + uint32_t qups = VC4_GET_FIELD(ident1, V3D_IDENT1_QUPS); + + seq_printf(m, "Revision: %d\n", + VC4_GET_FIELD(ident1, V3D_IDENT1_REV)); + seq_printf(m, "Slices: %d\n", nslc); + seq_printf(m, "TMUs: %d\n", nslc * tups); + seq_printf(m, "QPUs: %d\n", nslc * qups); + seq_printf(m, "Semaphores: %d\n", + VC4_GET_FIELD(ident1, V3D_IDENT1_NSEM)); + vc4_v3d_pm_put(vc4); } return 0; } -int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused) +/** + * Wraps pm_runtime_get_sync() in a refcount, so that we can reliably + * get the pm_runtime refcount to 0 in vc4_reset(). + */ +int +vc4_v3d_pm_get(struct vc4_dev *vc4) { - struct drm_info_node *node = (struct drm_info_node *)m->private; - struct drm_device *dev = node->minor->dev; - struct vc4_dev *vc4 = to_vc4_dev(dev); - uint32_t ident1 = V3D_READ(V3D_IDENT1); - uint32_t nslc = VC4_GET_FIELD(ident1, V3D_IDENT1_NSLC); - uint32_t tups = VC4_GET_FIELD(ident1, V3D_IDENT1_TUPS); - uint32_t qups = VC4_GET_FIELD(ident1, V3D_IDENT1_QUPS); - - seq_printf(m, "Revision: %d\n", - VC4_GET_FIELD(ident1, V3D_IDENT1_REV)); - seq_printf(m, "Slices: %d\n", nslc); - seq_printf(m, "TMUs: %d\n", nslc * tups); - seq_printf(m, "QPUs: %d\n", nslc * qups); - seq_printf(m, "Semaphores: %d\n", - VC4_GET_FIELD(ident1, V3D_IDENT1_NSEM)); + mutex_lock(&vc4->power_lock); + if (vc4->power_refcount++ == 0) { + int ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); + + if (ret < 0) { + vc4->power_refcount--; + mutex_unlock(&vc4->power_lock); + return ret; + } + } + mutex_unlock(&vc4->power_lock); return 0; } -#endif /* CONFIG_DEBUG_FS */ + +void +vc4_v3d_pm_put(struct vc4_dev *vc4) +{ + mutex_lock(&vc4->power_lock); + if (--vc4->power_refcount == 0) { + pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev); + pm_runtime_put_autosuspend(&vc4->v3d->pdev->dev); + } + mutex_unlock(&vc4->power_lock); +} static void vc4_v3d_init_hw(struct drm_device *dev) { @@ -354,6 +370,9 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data) v3d->regs = vc4_ioremap_regs(pdev, 0); if (IS_ERR(v3d->regs)) return PTR_ERR(v3d->regs); + v3d->regset.base = v3d->regs; + v3d->regset.regs = v3d_regs; + v3d->regset.nregs = ARRAY_SIZE(v3d_regs); vc4->v3d = v3d; v3d->vc4 = vc4; @@ -409,6 +428,9 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data) pm_runtime_set_autosuspend_delay(dev, 40); /* a little over 2 frames. */ pm_runtime_enable(dev); + vc4_debugfs_add_file(drm, "v3d_ident", vc4_v3d_debugfs_ident, NULL); + vc4_debugfs_add_regset32(drm, "v3d_regs", &v3d->regset); + return 0; } @@ -452,7 +474,7 @@ static int vc4_v3d_dev_remove(struct platform_device *pdev) return 0; } -static const struct of_device_id vc4_v3d_dt_match[] = { +const struct of_device_id vc4_v3d_dt_match[] = { { .compatible = "brcm,bcm2835-v3d" }, { .compatible = "brcm,cygnus-v3d" }, { .compatible = "brcm,vc4-v3d" }, diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c index 858c3a483229..0a27e48fab31 100644 --- a/drivers/gpu/drm/vc4/vc4_vec.c +++ b/drivers/gpu/drm/vc4/vc4_vec.c @@ -176,6 +176,8 @@ struct vc4_vec { struct clk *clock; const struct vc4_vec_tv_mode *tv_mode; + + struct debugfs_regset32 regset; }; #define VEC_READ(offset) readl(vec->regs + (offset)) @@ -223,59 +225,33 @@ struct vc4_vec_tv_mode { void (*mode_set)(struct vc4_vec *vec); }; -#define VEC_REG(reg) { reg, #reg } -static const struct { - u32 reg; - const char *name; -} vec_regs[] = { - VEC_REG(VEC_WSE_CONTROL), - VEC_REG(VEC_WSE_WSS_DATA), - VEC_REG(VEC_WSE_VPS_DATA1), - VEC_REG(VEC_WSE_VPS_CONTROL), - VEC_REG(VEC_REVID), - VEC_REG(VEC_CONFIG0), - VEC_REG(VEC_SCHPH), - VEC_REG(VEC_CLMP0_START), - VEC_REG(VEC_CLMP0_END), - VEC_REG(VEC_FREQ3_2), - VEC_REG(VEC_FREQ1_0), - VEC_REG(VEC_CONFIG1), - VEC_REG(VEC_CONFIG2), - VEC_REG(VEC_INTERRUPT_CONTROL), - VEC_REG(VEC_INTERRUPT_STATUS), - VEC_REG(VEC_FCW_SECAM_B), - VEC_REG(VEC_SECAM_GAIN_VAL), - VEC_REG(VEC_CONFIG3), - VEC_REG(VEC_STATUS0), - VEC_REG(VEC_MASK0), - VEC_REG(VEC_CFG), - VEC_REG(VEC_DAC_TEST), - VEC_REG(VEC_DAC_CONFIG), - VEC_REG(VEC_DAC_MISC), +static const struct debugfs_reg32 vec_regs[] = { + VC4_REG32(VEC_WSE_CONTROL), + VC4_REG32(VEC_WSE_WSS_DATA), + VC4_REG32(VEC_WSE_VPS_DATA1), + VC4_REG32(VEC_WSE_VPS_CONTROL), + VC4_REG32(VEC_REVID), + VC4_REG32(VEC_CONFIG0), + VC4_REG32(VEC_SCHPH), + VC4_REG32(VEC_CLMP0_START), + VC4_REG32(VEC_CLMP0_END), + VC4_REG32(VEC_FREQ3_2), + VC4_REG32(VEC_FREQ1_0), + VC4_REG32(VEC_CONFIG1), + VC4_REG32(VEC_CONFIG2), + VC4_REG32(VEC_INTERRUPT_CONTROL), + VC4_REG32(VEC_INTERRUPT_STATUS), + VC4_REG32(VEC_FCW_SECAM_B), + VC4_REG32(VEC_SECAM_GAIN_VAL), + VC4_REG32(VEC_CONFIG3), + VC4_REG32(VEC_STATUS0), + VC4_REG32(VEC_MASK0), + VC4_REG32(VEC_CFG), + VC4_REG32(VEC_DAC_TEST), + VC4_REG32(VEC_DAC_CONFIG), + VC4_REG32(VEC_DAC_MISC), }; -#ifdef CONFIG_DEBUG_FS -int vc4_vec_debugfs_regs(struct seq_file *m, void *unused) -{ - struct drm_info_node *node = (struct drm_info_node *)m->private; - struct drm_device *dev = node->minor->dev; - struct vc4_dev *vc4 = to_vc4_dev(dev); - struct vc4_vec *vec = vc4->vec; - int i; - - if (!vec) - return 0; - - for (i = 0; i < ARRAY_SIZE(vec_regs); i++) { - seq_printf(m, "%s (0x%04x): 0x%08x\n", - vec_regs[i].name, vec_regs[i].reg, - VEC_READ(vec_regs[i].reg)); - } - - return 0; -} -#endif - static void vc4_vec_ntsc_mode_set(struct vc4_vec *vec) { VEC_WRITE(VEC_CONFIG0, VEC_CONFIG0_NTSC_STD | VEC_CONFIG0_PDEN); @@ -587,6 +563,9 @@ static int vc4_vec_bind(struct device *dev, struct device *master, void *data) vec->regs = vc4_ioremap_regs(pdev, 0); if (IS_ERR(vec->regs)) return PTR_ERR(vec->regs); + vec->regset.base = vec->regs; + vec->regset.regs = vec_regs; + vec->regset.nregs = ARRAY_SIZE(vec_regs); vec->clock = devm_clk_get(dev, NULL); if (IS_ERR(vec->clock)) { @@ -612,6 +591,8 @@ static int vc4_vec_bind(struct device *dev, struct device *master, void *data) vc4->vec = vec; + vc4_debugfs_add_regset32(drm, "vec_regs", &vec->regset); + return 0; err_destroy_encoder: diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 653ec7d0bf4d..86843a4d6102 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -385,5 +385,6 @@ void virtio_gpu_modeset_fini(struct virtio_gpu_device *vgdev) for (i = 0 ; i < vgdev->num_scanouts; ++i) kfree(vgdev->outputs[i].edid); + drm_atomic_helper_shutdown(vgdev->ddev); drm_mode_config_cleanup(vgdev->ddev); } diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index afbc3beef089..3a4247319e63 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -30,6 +30,7 @@ #include <linux/printk.h> #include <linux/seq_file.h> #include <linux/device.h> +#include <linux/debugfs.h> /** * DOC: print @@ -84,6 +85,7 @@ void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf); __printf(2, 3) void drm_printf(struct drm_printer *p, const char *f, ...); void drm_puts(struct drm_printer *p, const char *str); +void drm_print_regset32(struct drm_printer *p, struct debugfs_regset32 *regset); __printf(2, 0) /** diff --git a/include/drm/drm_syncobj.h b/include/drm/drm_syncobj.h index 0311c9fdbd2f..6cf7243a1dc5 100644 --- a/include/drm/drm_syncobj.h +++ b/include/drm/drm_syncobj.h @@ -27,6 +27,7 @@ #define __DRM_SYNCOBJ_H__ #include <linux/dma-fence.h> +#include <linux/dma-fence-chain.h> struct drm_file; @@ -112,6 +113,10 @@ drm_syncobj_fence_get(struct drm_syncobj *syncobj) struct drm_syncobj *drm_syncobj_find(struct drm_file *file_private, u32 handle); +void drm_syncobj_add_point(struct drm_syncobj *syncobj, + struct dma_fence_chain *chain, + struct dma_fence *fence, + uint64_t point); void drm_syncobj_replace_fence(struct drm_syncobj *syncobj, struct dma_fence *fence); int drm_syncobj_find_fence(struct drm_file *file_private, diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h new file mode 100644 index 000000000000..934a442db8ac --- /dev/null +++ b/include/linux/dma-fence-chain.h @@ -0,0 +1,81 @@ +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2018 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + * + * 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. + * + * 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 __LINUX_DMA_FENCE_CHAIN_H +#define __LINUX_DMA_FENCE_CHAIN_H + +#include <linux/dma-fence.h> +#include <linux/irq_work.h> + +/** + * struct dma_fence_chain - fence to represent an node of a fence chain + * @base: fence base class + * @lock: spinlock for fence handling + * @prev: previous fence of the chain + * @prev_seqno: original previous seqno before garbage collection + * @fence: encapsulated fence + * @cb: callback structure for signaling + * @work: irq work item for signaling + */ +struct dma_fence_chain { + struct dma_fence base; + spinlock_t lock; + struct dma_fence __rcu *prev; + u64 prev_seqno; + struct dma_fence *fence; + struct dma_fence_cb cb; + struct irq_work work; +}; + +extern const struct dma_fence_ops dma_fence_chain_ops; + +/** + * to_dma_fence_chain - cast a fence to a dma_fence_chain + * @fence: fence to cast to a dma_fence_array + * + * Returns NULL if the fence is not a dma_fence_chain, + * or the dma_fence_chain otherwise. + */ +static inline struct dma_fence_chain * +to_dma_fence_chain(struct dma_fence *fence) +{ + if (!fence || fence->ops != &dma_fence_chain_ops) + return NULL; + + return container_of(fence, struct dma_fence_chain, base); +} + +/** + * dma_fence_chain_for_each - iterate over all fences in chain + * @iter: current fence + * @head: starting point + * + * Iterate over all fences in the chain. We keep a reference to the current + * fence while inside the loop which must be dropped when breaking out. + */ +#define dma_fence_chain_for_each(iter, head) \ + for (iter = dma_fence_get(head); iter; \ + iter = dma_fence_chain_walk(iter)) + +struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence); +int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno); +void dma_fence_chain_init(struct dma_fence_chain *chain, + struct dma_fence *prev, + struct dma_fence *fence, + uint64_t seqno); + +#endif /* __LINUX_DMA_FENCE_CHAIN_H */ diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 300f336633f2..236b01a1fabf 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -735,8 +735,18 @@ struct drm_syncobj_handle { __u32 pad; }; +struct drm_syncobj_transfer { + __u32 src_handle; + __u32 dst_handle; + __u64 src_point; + __u64 dst_point; + __u32 flags; + __u32 pad; +}; + #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0) #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1) +#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */ struct drm_syncobj_wait { __u64 handles; /* absolute timeout */ @@ -747,12 +757,33 @@ struct drm_syncobj_wait { __u32 pad; }; +struct drm_syncobj_timeline_wait { + __u64 handles; + /* wait on specific timeline point for every handles*/ + __u64 points; + /* absolute timeout */ + __s64 timeout_nsec; + __u32 count_handles; + __u32 flags; + __u32 first_signaled; /* only valid when not waiting all */ + __u32 pad; +}; + + struct drm_syncobj_array { __u64 handles; __u32 count_handles; __u32 pad; }; +struct drm_syncobj_timeline_array { + __u64 handles; + __u64 points; + __u32 count_handles; + __u32 pad; +}; + + /* Query current scanout sequence number */ struct drm_crtc_get_sequence { __u32 crtc_id; /* requested crtc_id */ @@ -909,6 +940,11 @@ extern "C" { #define DRM_IOCTL_MODE_GET_LEASE DRM_IOWR(0xC8, struct drm_mode_get_lease) #define DRM_IOCTL_MODE_REVOKE_LEASE DRM_IOWR(0xC9, struct drm_mode_revoke_lease) +#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait) +#define DRM_IOCTL_SYNCOBJ_QUERY DRM_IOWR(0xCB, struct drm_syncobj_timeline_array) +#define DRM_IOCTL_SYNCOBJ_TRANSFER DRM_IOWR(0xCC, struct drm_syncobj_transfer) +#define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL DRM_IOWR(0xCD, struct drm_syncobj_timeline_array) + /** * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 09d72966899a..83cd1636b9be 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -621,7 +621,8 @@ struct drm_color_ctm { struct drm_color_lut { /* - * Data is U0.16 fixed point format. + * Values are mapped linearly to 0.0 - 1.0 range, with 0x0 == 0.0 and + * 0xffff == 1.0. */ __u16 red; __u16 green; diff --git a/include/uapi/drm/lima_drm.h b/include/uapi/drm/lima_drm.h new file mode 100644 index 000000000000..95a00fb867e6 --- /dev/null +++ b/include/uapi/drm/lima_drm.h @@ -0,0 +1,169 @@ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */ +/* Copyright 2017-2018 Qiang Yu <yuq825@gmail.com> */ + +#ifndef __LIMA_DRM_H__ +#define __LIMA_DRM_H__ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +enum drm_lima_param_gpu_id { + DRM_LIMA_PARAM_GPU_ID_UNKNOWN, + DRM_LIMA_PARAM_GPU_ID_MALI400, + DRM_LIMA_PARAM_GPU_ID_MALI450, +}; + +enum drm_lima_param { + DRM_LIMA_PARAM_GPU_ID, + DRM_LIMA_PARAM_NUM_PP, + DRM_LIMA_PARAM_GP_VERSION, + DRM_LIMA_PARAM_PP_VERSION, +}; + +/** + * get various information of the GPU + */ +struct drm_lima_get_param { + __u32 param; /* in, value in enum drm_lima_param */ + __u32 pad; /* pad, must be zero */ + __u64 value; /* out, parameter value */ +}; + +/** + * create a buffer for used by GPU + */ +struct drm_lima_gem_create { + __u32 size; /* in, buffer size */ + __u32 flags; /* in, currently no flags, must be zero */ + __u32 handle; /* out, GEM buffer handle */ + __u32 pad; /* pad, must be zero */ +}; + +/** + * get information of a buffer + */ +struct drm_lima_gem_info { + __u32 handle; /* in, GEM buffer handle */ + __u32 va; /* out, virtual address mapped into GPU MMU */ + __u64 offset; /* out, used to mmap this buffer to CPU */ +}; + +#define LIMA_SUBMIT_BO_READ 0x01 +#define LIMA_SUBMIT_BO_WRITE 0x02 + +/* buffer information used by one task */ +struct drm_lima_gem_submit_bo { + __u32 handle; /* in, GEM buffer handle */ + __u32 flags; /* in, buffer read/write by GPU */ +}; + +#define LIMA_GP_FRAME_REG_NUM 6 + +/* frame used to setup GP for each task */ +struct drm_lima_gp_frame { + __u32 frame[LIMA_GP_FRAME_REG_NUM]; +}; + +#define LIMA_PP_FRAME_REG_NUM 23 +#define LIMA_PP_WB_REG_NUM 12 + +/* frame used to setup mali400 GPU PP for each task */ +struct drm_lima_m400_pp_frame { + __u32 frame[LIMA_PP_FRAME_REG_NUM]; + __u32 num_pp; + __u32 wb[3 * LIMA_PP_WB_REG_NUM]; + __u32 plbu_array_address[4]; + __u32 fragment_stack_address[4]; +}; + +/* frame used to setup mali450 GPU PP for each task */ +struct drm_lima_m450_pp_frame { + __u32 frame[LIMA_PP_FRAME_REG_NUM]; + __u32 num_pp; + __u32 wb[3 * LIMA_PP_WB_REG_NUM]; + __u32 use_dlbu; + __u32 _pad; + union { + __u32 plbu_array_address[8]; + __u32 dlbu_regs[4]; + }; + __u32 fragment_stack_address[8]; +}; + +#define LIMA_PIPE_GP 0x00 +#define LIMA_PIPE_PP 0x01 + +#define LIMA_SUBMIT_FLAG_EXPLICIT_FENCE (1 << 0) + +/** + * submit a task to GPU + * + * User can always merge multi sync_file and drm_syncobj + * into one drm_syncobj as in_sync[0], but we reserve + * in_sync[1] for another task's out_sync to avoid the + * export/import/merge pass when explicit sync. + */ +struct drm_lima_gem_submit { + __u32 ctx; /* in, context handle task is submitted to */ + __u32 pipe; /* in, which pipe to use, GP/PP */ + __u32 nr_bos; /* in, array length of bos field */ + __u32 frame_size; /* in, size of frame field */ + __u64 bos; /* in, array of drm_lima_gem_submit_bo */ + __u64 frame; /* in, GP/PP frame */ + __u32 flags; /* in, submit flags */ + __u32 out_sync; /* in, drm_syncobj handle used to wait task finish after submission */ + __u32 in_sync[2]; /* in, drm_syncobj handle used to wait before start this task */ +}; + +#define LIMA_GEM_WAIT_READ 0x01 +#define LIMA_GEM_WAIT_WRITE 0x02 + +/** + * wait pending GPU task finish of a buffer + */ +struct drm_lima_gem_wait { + __u32 handle; /* in, GEM buffer handle */ + __u32 op; /* in, CPU want to read/write this buffer */ + __s64 timeout_ns; /* in, wait timeout in absulute time */ +}; + +/** + * create a context + */ +struct drm_lima_ctx_create { + __u32 id; /* out, context handle */ + __u32 _pad; /* pad, must be zero */ +}; + +/** + * free a context + */ +struct drm_lima_ctx_free { + __u32 id; /* in, context handle */ + __u32 _pad; /* pad, must be zero */ +}; + +#define DRM_LIMA_GET_PARAM 0x00 +#define DRM_LIMA_GEM_CREATE 0x01 +#define DRM_LIMA_GEM_INFO 0x02 +#define DRM_LIMA_GEM_SUBMIT 0x03 +#define DRM_LIMA_GEM_WAIT 0x04 +#define DRM_LIMA_CTX_CREATE 0x05 +#define DRM_LIMA_CTX_FREE 0x06 + +#define DRM_IOCTL_LIMA_GET_PARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_LIMA_GET_PARAM, struct drm_lima_get_param) +#define DRM_IOCTL_LIMA_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_LIMA_GEM_CREATE, struct drm_lima_gem_create) +#define DRM_IOCTL_LIMA_GEM_INFO DRM_IOWR(DRM_COMMAND_BASE + DRM_LIMA_GEM_INFO, struct drm_lima_gem_info) +#define DRM_IOCTL_LIMA_GEM_SUBMIT DRM_IOW(DRM_COMMAND_BASE + DRM_LIMA_GEM_SUBMIT, struct drm_lima_gem_submit) +#define DRM_IOCTL_LIMA_GEM_WAIT DRM_IOW(DRM_COMMAND_BASE + DRM_LIMA_GEM_WAIT, struct drm_lima_gem_wait) +#define DRM_IOCTL_LIMA_CTX_CREATE DRM_IOR(DRM_COMMAND_BASE + DRM_LIMA_CTX_CREATE, struct drm_lima_ctx_create) +#define DRM_IOCTL_LIMA_CTX_FREE DRM_IOW(DRM_COMMAND_BASE + DRM_LIMA_CTX_FREE, struct drm_lima_ctx_free) + +#if defined(__cplusplus) +} +#endif + +#endif /* __LIMA_DRM_H__ */ |