devicetree.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2 0/2] drm: Add DRM driver for GlandaGPU (VHDL soft-IP GPU)
@ 2026-07-30 17:36 Leander Kieweg
  2026-07-30 17:36 ` [PATCH v2 1/2] dt-bindings: display: Add GlandaGPU binding Leander Kieweg
  2026-07-30 17:36 ` [PATCH v2 2/2] drm/glanda: Add initial DRM driver for GlandaGPU Leander Kieweg
  0 siblings, 2 replies; 4+ messages in thread
From: Leander Kieweg @ 2026-07-30 17:36 UTC (permalink / raw)
  To: dri-devel, devicetree
  Cc: airlied, simona, maarten.lankhorst, mripard, tzimmermann, robh,
	krzk+dt, conor+dt, u.kleine-koenig, Leander Kieweg

This is v2 of the GlandaGPU DRM driver series [1], addressing review
feedback from Thomas Zimmermann, Conor Dooley, Uwe Kleine-König, and
the automated review bot on v1.

GlandaGPU is a small VHDL soft-IP 2D display controller, currently
targeting a Terasic DE10-Standard (Cyclone V SoC). This series has
been tested both against a QEMU digital twin and on real hardware.

Hardware/VHDL:    https://github.com/stiangglanda/GlandaGPU
QEMU fork:        https://github.com/stiangglanda/qemu-glandagpu
Userspace tests:  https://github.com/stiangglanda/GlandaGPU-userspace-tests

Changes since v1:

dt-bindings:
- add a link to the GlandaGPU project in the binding description
- add clocks to the required properties
- fix the example to use interrupt-parent and the GIC_SPI/
  IRQ_TYPE_LEVEL_HIGH macros instead of raw numbers
- fix missing trailing newline

driver core:
- drop the struct device *dev field, use drm_device.dev instead
- open-code drm_encoder_init() instead of drm_simple_encoder_init(),
  which is being phased out
- switch the plane update path from manual dma_resv_lock()/
  drm_gem_shmem_vmap_locked() to DRM_GEM_SHADOW_PLANE_HELPER_FUNCS/
  DRM_GEM_SHADOW_PLANE_FUNCS. This also fixes sleeping calls being
  made from atomic-commit context and a raw map.vaddr dereference,
  both flagged by automated review
- use drm_gem_fb_create_with_dirty() instead of a custom fb_create
  implementation
- remove the redundant new_state == NULL check in the CRTC flush
  helper
- remove the ioctl-based UAPI (CLEAR/RECT/LINE) entirely. As Thomas
  pointed out in v1, fixed-function 2D ioctls aren't a good fit for
  mainline DRM, and userspace rendering into the shadow-plane
  framebuffer covers the same functionality
- fix a double drm_mode_config_cleanup() call in the probe and
  remove error paths (devres already handles this)
- call drm_atomic_helper_shutdown() on remove
- fix a teardown race where in-flight work could touch already
  unmapped MMIO, using drm_dev_unplug()/drm_dev_enter()/
  drm_dev_exit()
- move IRQ registration to after CRTC initialization, avoiding a
  potential NULL pointer dereference from an early-firing shared IRQ
- fix platform_get_irq() error handling. Negative error codes such
  as -EPROBE_DEFER were previously misread as "no IRQ available"

new in v2:
- add PCI probe support alongside the existing platform_driver/
  devicetree path, backed by a matching QEMU device model, so the
  driver can be tested against a virtual device without needing
  devicetree or real hardware. Real hardware continues to use the
  platform_driver path unchanged. This replaces the old x86 test
  device patch 3/3, reducing the series from 3 to 2 patches.

Known open item: the QEMU test device currently uses a placeholder
ID from the range QEMU reserves for experimental, unregistered use
(1af4:10f0, see [2]). I've requested a permanent
ID from Gerd Hoffmann and will post a follow-up once it's assigned.

[1] https://lore.kernel.org/dri-devel/20260714101146.200416-1-kieweg.leander@gmail.com/T/#t
[2] https://www.qemu.org/docs/master/specs/pci-ids.html

Leander Kieweg (2):
  dt-bindings: display: Add GlandaGPU binding
  drm/glanda: Add initial DRM driver for GlandaGPU

 .../bindings/display/glanda,gpu.yaml          |  55 ++
 .../devicetree/bindings/vendor-prefixes.yaml  |   2 +
 MAINTAINERS                                   |   6 +
 drivers/gpu/drm/tiny/Kconfig                  |  11 +
 drivers/gpu/drm/tiny/Makefile                 |   1 +
 drivers/gpu/drm/tiny/glandagpu.c              | 579 ++++++++++++++++++
 6 files changed, 654 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/glanda,gpu.yaml
 create mode 100644 drivers/gpu/drm/tiny/glandagpu.c

-- 
2.43.0


^ permalink raw reply	[flat|nested] 4+ messages in thread

* [PATCH v2 1/2] dt-bindings: display: Add GlandaGPU binding
  2026-07-30 17:36 [PATCH v2 0/2] drm: Add DRM driver for GlandaGPU (VHDL soft-IP GPU) Leander Kieweg
@ 2026-07-30 17:36 ` Leander Kieweg
  2026-07-30 17:36 ` [PATCH v2 2/2] drm/glanda: Add initial DRM driver for GlandaGPU Leander Kieweg
  1 sibling, 0 replies; 4+ messages in thread
From: Leander Kieweg @ 2026-07-30 17:36 UTC (permalink / raw)
  To: dri-devel, devicetree
  Cc: airlied, simona, maarten.lankhorst, mripard, tzimmermann, robh,
	krzk+dt, conor+dt, u.kleine-koenig, Leander Kieweg

Add Device Tree binding documentation for GlandaGPU, a custom
FPGA-based 2D display controller.

For hardware designs and RTL sources, see:
https://github.com/stiangglanda/GlandaGPU

Signed-off-by: Leander Kieweg <kieweg.leander@gmail.com>
---
 .../bindings/display/glanda,gpu.yaml          | 55 +++++++++++++++++++
 .../devicetree/bindings/vendor-prefixes.yaml  |  2 +
 2 files changed, 57 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/glanda,gpu.yaml

diff --git a/Documentation/devicetree/bindings/display/glanda,gpu.yaml b/Documentation/devicetree/bindings/display/glanda,gpu.yaml
new file mode 100644
index 000000000..988a30946
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/glanda,gpu.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/glanda,gpu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: GlandaGPU 2D Hardware Accelerated Display Controller
+
+maintainers:
+  - Leander Kieweg <kieweg.leander@gmail.com>
+
+description: |
+  GlandaGPU is a custom FPGA soft-IP core providing a simple
+  2D hardware-accelerated drawing engine with a VGA-compatible
+  display output. The register window covers a combined VRAM + MMIO
+  region, with MMIO registers at a fixed offset within it.
+
+  For hardware designs and RTL sources, see:
+  https://github.com/stiangglanda/GlandaGPU
+
+properties:
+  compatible:
+    const: glanda,gpu-1.0
+
+  reg:
+    maxItems: 1
+    description:
+      Combined VRAM + MMIO register window (VRAM at offset 0,
+      MMIO registers at offset 0x00200000 within this range).
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+    description: Bus and pixel clock provided to the FPGA IP.
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    gpu@c0000000 {
+        compatible = "glanda,gpu-1.0";
+        reg = <0xc0000000 0x1000000>;
+        interrupt-parent = <&intc>;
+        interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&osc1>;
+    };
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index b1af9deac..b8b7a5401 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -666,6 +666,8 @@ patternProperties:
     description: Giantplus Technology Co., Ltd.
   "^gira,.*":
     description: Gira Giersiepen GmbH & Co. KG
+  "^glanda,.*":
+    description: GlandaGPU
   "^glinet,.*":
     description: GL Intelligence, Inc.
   "^globalscale,.*":
-- 
2.43.0


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* [PATCH v2 2/2] drm/glanda: Add initial DRM driver for GlandaGPU
  2026-07-30 17:36 [PATCH v2 0/2] drm: Add DRM driver for GlandaGPU (VHDL soft-IP GPU) Leander Kieweg
  2026-07-30 17:36 ` [PATCH v2 1/2] dt-bindings: display: Add GlandaGPU binding Leander Kieweg
@ 2026-07-30 17:36 ` Leander Kieweg
  2026-07-30 17:52   ` sashiko-bot
  1 sibling, 1 reply; 4+ messages in thread
From: Leander Kieweg @ 2026-07-30 17:36 UTC (permalink / raw)
  To: dri-devel, devicetree
  Cc: airlied, simona, maarten.lankhorst, mripard, tzimmermann, robh,
	krzk+dt, conor+dt, u.kleine-koenig, Leander Kieweg

Introduce the core DRM/KMS driver for GlandaGPU. This driver
supports basic modesetting, atomic updates via shadow plane helpers,
and optional QEMU PCI probing alongside the platform driver.

Signed-off-by: Leander Kieweg <kieweg.leander@gmail.com>
---
 MAINTAINERS                      |   6 +
 drivers/gpu/drm/tiny/Kconfig     |  11 +
 drivers/gpu/drm/tiny/Makefile    |   1 +
 drivers/gpu/drm/tiny/glandagpu.c | 579 +++++++++++++++++++++++++++++++
 4 files changed, 597 insertions(+)
 create mode 100644 drivers/gpu/drm/tiny/glandagpu.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 6dea93a41..8bb0513eb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8076,6 +8076,12 @@ T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
 F:	drivers/gpu/drm/gud/
 F:	include/drm/gud.h
 
+DRM DRIVER FOR GLANDAGPU
+M:	Leander Kieweg <kieweg.leander@gmail.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/display/glanda,gpu.yaml
+F:	drivers/gpu/drm/tiny/glandagpu.c
+
 DRM DRIVER FOR GRAIN MEDIA GM12U320 PROJECTORS
 M:	Hans de Goede <hansg@kernel.org>
 S:	Maintained
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index f0e72d4b6..f5aaf499e 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -56,6 +56,17 @@ config DRM_CIRRUS_QEMU
 	   - qxl (DRM_QXL, qemu -vga qxl, works best with spice)
 	   - virtio (DRM_VIRTIO_GPU), qemu -vga virtio)
 
+config DRM_GLANDA
+	tristate "GlandaGPU DRM driver"
+	depends on DRM
+	select DRM_KMS_HELPER
+	select DRM_GEM_SHMEM_HELPER
+	help
+	  DRM/KMS driver for the GlandaGPU display controller
+	  (FPGA soft IP). This driver supports basic modesetting,
+	  dumb buffers, and atomic updates via shadow planes.
+	  It also provides PCI probing for QEMU testing.
+
 config DRM_GM12U320
 	tristate "GM12U320 driver for USB projectors"
 	depends on DRM && USB && MMU
diff --git a/drivers/gpu/drm/tiny/Makefile b/drivers/gpu/drm/tiny/Makefile
index 48d30bf61..b4fa1554a 100644
--- a/drivers/gpu/drm/tiny/Makefile
+++ b/drivers/gpu/drm/tiny/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_DRM_APPLETBDRM)		+= appletbdrm.o
 obj-$(CONFIG_DRM_ARCPGU)		+= arcpgu.o
 obj-$(CONFIG_DRM_BOCHS)			+= bochs.o
 obj-$(CONFIG_DRM_CIRRUS_QEMU)		+= cirrus-qemu.o
+obj-$(CONFIG_DRM_GLANDA) 			+= glandagpu.o
 obj-$(CONFIG_DRM_GM12U320)		+= gm12u320.o
 obj-$(CONFIG_DRM_PANEL_MIPI_DBI)	+= panel-mipi-dbi.o
 obj-$(CONFIG_DRM_PIXPAPER)              += pixpaper.o
diff --git a/drivers/gpu/drm/tiny/glandagpu.c b/drivers/gpu/drm/tiny/glandagpu.c
new file mode 100644
index 000000000..e4dfddaba
--- /dev/null
+++ b/drivers/gpu/drm/tiny/glandagpu.c
@@ -0,0 +1,579 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/pci.h>
+#include <linux/io.h>
+#include <linux/delay.h>	/* udelay (polling) */
+#include <linux/of.h>
+#include <linux/slab.h>		/* GFP_KERNEL */
+#include <linux/fs.h>
+#include <linux/cdev.h>
+#include <linux/uaccess.h>
+#include <linux/interrupt.h>
+#include <linux/wait.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/iosys-map.h>
+
+#include <drm/drm_drv.h>
+#include <drm/drm_device.h>
+#include <drm/drm_file.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_ioctl.h>
+#include <drm/drm_gem_shmem_helper.h>
+#include <drm/drm_gem_atomic_helper.h>
+#include <drm/drm_framebuffer.h>
+#include <drm/drm_vblank.h>
+
+#include <drm/drm_connector.h>
+#include <drm/drm_encoder.h>
+#include <drm/drm_modeset_helper.h>
+#include <drm/drm_probe_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_modeset_helper_vtables.h>
+#include <drm/drm_plane.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_print.h>
+
+/* Hardware Constants */
+#define GLANDA_WIDTH      640
+#define GLANDA_HEIGHT     480
+#define GLANDA_VRAM_SIZE  (GLANDA_WIDTH * GLANDA_HEIGHT * 4)
+#define GLANDA_MMIO_SIZE  32
+#define GLANDA_MMIO_OFFSET 0x00200000
+
+/* QEMU test device ID, from the range reserved for experimental use (docs/specs/pci-ids.rst). */
+#define PCI_DEVICE_ID_GLANDA_GPU 0x10f0
+
+/* Register Offsets */
+#define REG_STATUS  0x00
+#define REG_CTRL    0x04
+#define REG_COORD0  0x08
+#define REG_COORD1  0x0C
+#define REG_COLOR   0x10
+#define REG_ISR     0x14
+#define REG_IER     0x18
+
+/* Bit Masks */
+#define INT_DONE    BIT(0)
+#define INT_VSYNC   BIT(1)
+
+#define STATUS_BUSY BIT(0)
+#define CMD_CLEAR   (0x1)
+#define CMD_RECT    (0x2)
+#define CMD_LINE    (0x3)
+#define CTRL_START  BIT(4)
+
+struct glanda_device {
+	struct drm_device drm;
+
+	/* hw */
+	void __iomem *mmio_base;
+	void __iomem *vram_base;
+	phys_addr_t vram_phys;
+
+	int irq;
+
+	/* drm */
+	struct drm_plane primary_plane;
+	struct drm_crtc crtc;
+	struct drm_encoder encoder;
+	struct drm_connector connector;
+};
+
+#define to_glanda(dev) container_of(dev, struct glanda_device, drm)
+
+static const u32 glanda_plane_formats[] = {
+	DRM_FORMAT_XRGB8888,
+};
+
+static void glanda_plane_atomic_update(struct drm_plane *plane,
+				       struct drm_atomic_commit *state)
+{
+	struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane);
+	struct drm_shadow_plane_state *shadow_state = to_drm_shadow_plane_state(new_state);
+	struct drm_framebuffer *fb = new_state->fb;
+	struct glanda_device *gdev = to_glanda(plane->dev);
+	u32 src_pitch, width, height, x, y;
+	int idx;
+
+	if (!fb)
+		return;
+
+	if (!drm_dev_enter(plane->dev, &idx))
+		return;
+
+	src_pitch = fb->pitches[0];
+	width = min_t(u32, fb->width, GLANDA_WIDTH);
+	height = min_t(u32, fb->height, GLANDA_HEIGHT);
+
+	for (y = 0; y < height; y++) {
+		size_t offset = y * GLANDA_WIDTH * sizeof(u32);
+		u32 __iomem *dst = (u32 __iomem *)(gdev->vram_base + offset);
+
+		for (x = 0; x < width; x++) {
+			u32 pixel = iosys_map_rd(&shadow_state->data[0],
+						 y * src_pitch + x * sizeof(u32), u32);
+			u32 packed = ((pixel >> 12) & 0x0F00) |
+				((pixel >> 8) & 0x00F0) |
+				((pixel >> 4) & 0x000F);
+
+			writel_relaxed(packed, &dst[x]);
+		}
+	}
+
+	drm_dev_exit(idx);
+}
+
+static int glanda_plane_atomic_check(struct drm_plane *plane,
+				     struct drm_atomic_commit *state)
+{
+	struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state, plane);
+	struct drm_crtc_state *crtc_state;
+
+	if (!new_plane_state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(state, new_plane_state->crtc);
+
+	return drm_atomic_helper_check_plane_state(new_plane_state, crtc_state,
+		DRM_PLANE_NO_SCALING, DRM_PLANE_NO_SCALING,
+		false,	/* can_position */
+		false	/* can_update_disabled */);
+}
+
+static const struct drm_plane_helper_funcs glanda_plane_helper_funcs = {
+	DRM_GEM_SHADOW_PLANE_HELPER_FUNCS,
+	.atomic_update = glanda_plane_atomic_update,
+	.atomic_check = glanda_plane_atomic_check,
+};
+
+static const struct drm_plane_funcs glanda_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = drm_plane_cleanup,
+	DRM_GEM_SHADOW_PLANE_FUNCS,
+};
+
+static int glanda_connector_get_modes(struct drm_connector *connector)
+{
+	struct drm_display_mode *mode;
+
+	mode = drm_mode_create(connector->dev);
+	if (!mode) {
+		dev_err(connector->dev->dev, "GlandaGPU: failed to create display mode\n");
+		return 0;
+	}
+
+	/* Standard VGA timing: 640x480 @ 60 Hz. */
+	mode->hdisplay = 640;
+	mode->hsync_start = 656;
+	mode->hsync_end = 752;
+	mode->htotal = 800;
+
+	mode->vdisplay = 480;
+	mode->vsync_start = 490;
+	mode->vsync_end = 492;
+	mode->vtotal = 525;
+
+	mode->clock = 25175;	/* 25.175 MHz pixel clock */
+
+	mode->flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC;
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+
+	drm_mode_set_name(mode);
+	drm_mode_probed_add(connector, mode);
+
+	return 1;
+}
+
+static enum drm_connector_status glanda_connector_detect(struct drm_connector
+							 *connector, bool force)
+{
+	return connector_status_connected;
+}
+
+static int glanda_crtc_enable_vblank(struct drm_crtc *crtc)
+{
+	struct glanda_device *gdev = to_glanda(crtc->dev);
+	u32 ier;
+
+	ier = readl(gdev->mmio_base + REG_IER);
+	writel(ier | INT_VSYNC, gdev->mmio_base + REG_IER);
+
+	return 0;
+}
+
+static void glanda_crtc_disable_vblank(struct drm_crtc *crtc)
+{
+	struct glanda_device *gdev = to_glanda(crtc->dev);
+	u32 ier = readl(gdev->mmio_base + REG_IER);
+
+	writel(ier & ~INT_VSYNC, gdev->mmio_base + REG_IER);
+}
+
+static void glanda_crtc_atomic_enable(struct drm_crtc *crtc,
+				      struct drm_atomic_commit *state)
+{
+	drm_crtc_vblank_on(crtc);
+}
+
+static void glanda_crtc_atomic_disable(struct drm_crtc *crtc,
+				       struct drm_atomic_commit *state)
+{
+	drm_crtc_vblank_off(crtc);
+}
+
+static void glanda_crtc_atomic_flush(struct drm_crtc *crtc,
+				     struct drm_atomic_commit *state)
+{
+	struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc);
+	struct drm_pending_vblank_event *event;
+
+	if (new_state->event) {
+		event = new_state->event;
+
+		new_state->event = NULL;
+
+		spin_lock_irq(&crtc->dev->event_lock);
+
+		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);
+	}
+}
+
+static const struct drm_crtc_funcs glanda_crtc_funcs = {
+	.destroy = drm_crtc_cleanup,
+	.set_config = drm_atomic_helper_set_config,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = drm_atomic_helper_crtc_reset,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
+	.enable_vblank = glanda_crtc_enable_vblank,
+	.disable_vblank = glanda_crtc_disable_vblank,
+};
+
+static const struct drm_crtc_helper_funcs glanda_crtc_helper_funcs = {
+	.atomic_enable = glanda_crtc_atomic_enable,
+	.atomic_disable = glanda_crtc_atomic_disable,
+	.atomic_flush = glanda_crtc_atomic_flush,
+};
+
+static const struct drm_connector_helper_funcs glanda_connector_helper_funcs = {
+	.get_modes = glanda_connector_get_modes,
+};
+
+static const struct drm_encoder_funcs glanda_encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+static const struct drm_connector_funcs glanda_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.detect = glanda_connector_detect,
+	.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_mode_config_funcs glanda_mode_config_funcs = {
+	.fb_create = drm_gem_fb_create_with_dirty,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+DEFINE_DRM_GEM_FOPS(glanda_drm_fops);
+
+static const struct drm_driver glanda_drm_driver = {
+	.driver_features =
+	    DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC,
+	.name = "glandagpu",
+	.desc = "GlandaGPU Hardware Accelerated DRM Driver",
+	.major = 1,
+	.minor = 0,
+	.fops = &glanda_drm_fops,
+	.dumb_create = drm_gem_shmem_dumb_create,
+};
+
+static irqreturn_t glanda_irq_handler(int irq, void *dev_id)
+{
+	struct glanda_device *gdev = dev_id;
+	u32 isr, ier;
+
+	if (!gdev || !gdev->mmio_base)
+		return IRQ_NONE;
+
+	isr = readl(gdev->mmio_base + REG_ISR);
+	ier = readl(gdev->mmio_base + REG_IER);
+
+	if (!(isr & ier))
+		return IRQ_NONE;
+
+	if (isr & INT_VSYNC)
+		drm_crtc_handle_vblank(&gdev->crtc);
+
+	/* Clear interrupt(W1C) */
+	writel(isr, gdev->mmio_base + REG_ISR);
+	return IRQ_HANDLED;
+}
+
+/* Common DRM setup once MMIO/VRAM/IRQ are known(used by both probe paths) */
+static int glanda_drm_init(struct glanda_device *gdev, int irq)
+{
+	int ret;
+
+	gdev->irq = -1;
+
+	writel(0, gdev->mmio_base + REG_IER);
+	writel(0xFFFFFFFF, gdev->mmio_base + REG_ISR);	/* clear flags */
+
+	/* DRM mode config */
+	drm_mode_config_init(&gdev->drm);
+	gdev->drm.mode_config.min_width = 640;
+	gdev->drm.mode_config.min_height = 480;
+	gdev->drm.mode_config.max_width = 640;
+	gdev->drm.mode_config.max_height = 480;
+	gdev->drm.mode_config.funcs = &glanda_mode_config_funcs;
+
+	ret = drm_universal_plane_init(&gdev->drm, &gdev->primary_plane, 1 << 0,
+				       &glanda_plane_funcs,
+				       glanda_plane_formats,
+				       ARRAY_SIZE(glanda_plane_formats), NULL,
+				       DRM_PLANE_TYPE_PRIMARY, NULL);
+	if (ret) {
+		drm_err(&gdev->drm, "Failed to initialize primary plane\n");
+		return ret;
+	}
+	drm_plane_helper_add(&gdev->primary_plane, &glanda_plane_helper_funcs);
+
+	/* VBlank init */
+	ret = drm_vblank_init(&gdev->drm, 1);
+	if (ret) {
+		drm_err(&gdev->drm, "Failed to initialize vblank\n");
+		return ret;
+	}
+
+	/* CRTC init */
+	ret = drm_crtc_init_with_planes(&gdev->drm, &gdev->crtc,
+					&gdev->primary_plane, NULL,
+					&glanda_crtc_funcs, NULL);
+	if (ret) {
+		drm_err(&gdev->drm, "Failed to initialize CRTC with planes\n");
+		return ret;
+	}
+	drm_crtc_helper_add(&gdev->crtc, &glanda_crtc_helper_funcs);
+
+	ret = drm_encoder_init(&gdev->drm, &gdev->encoder, &glanda_encoder_funcs,
+			       DRM_MODE_ENCODER_DAC, NULL);
+	if (ret) {
+		drm_err(&gdev->drm, "Failed to initialize encoder\n");
+		return ret;
+	}
+	gdev->encoder.possible_crtcs = 1;
+
+	ret = drm_connector_init(&gdev->drm, &gdev->connector,
+				 &glanda_connector_funcs, DRM_MODE_CONNECTOR_VGA);
+	if (ret) {
+		drm_err(&gdev->drm, "Failed to initialize connector\n");
+		return ret;
+	}
+	drm_connector_helper_add(&gdev->connector, &glanda_connector_helper_funcs);
+
+	drm_connector_attach_encoder(&gdev->connector, &gdev->encoder);
+
+	/* Populate connector state early so userspace can enumerate modes. */
+	mutex_lock(&gdev->drm.mode_config.mutex);
+	drm_helper_probe_single_connector_modes(&gdev->connector, 1024, 768);
+	mutex_unlock(&gdev->drm.mode_config.mutex);
+
+	drm_mode_config_reset(&gdev->drm);
+
+	if (irq > 0) {
+		gdev->irq = irq;
+		ret = devm_request_irq(gdev->drm.dev, gdev->irq, glanda_irq_handler,
+				       IRQF_SHARED, "glandagpu", gdev);
+		if (ret) {
+			drm_err(&gdev->drm, "Failed to request IRQ %d\n",
+				gdev->irq);
+			return ret;
+		}
+
+		writel(INT_DONE, gdev->mmio_base + REG_IER);
+		drm_info(&gdev->drm, "IRQ %d requested and enabled\n", gdev->irq);
+	} else {
+		drm_warn(&gdev->drm, "No IRQ found, falling back to polling\n");
+	}
+
+	ret = drm_dev_register(&gdev->drm, 0);
+	if (ret)
+		return ret;
+
+	drm_info(&gdev->drm, "GlandaGPU DRM Initialized (/dev/dri/cardX created)\n");
+	return 0;
+}
+
+/* Shared teardown, mirrors glanda_drm_init() */
+static void glanda_drm_fini(struct glanda_device *gdev)
+{
+	drm_dev_unplug(&gdev->drm);
+	drm_atomic_helper_shutdown(&gdev->drm);
+
+	/* Disable interrupts */
+	writel(0, gdev->mmio_base + REG_IER);
+
+	drm_info(&gdev->drm, "GlandaGPU DRM Driver removed\n");
+}
+
+static int glandagpu_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct glanda_device *gdev;
+	int irq;
+
+	dev_info(&pdev->dev, "GlandaGPU Probe started\n");
+
+	gdev = devm_drm_dev_alloc(&pdev->dev, &glanda_drm_driver, struct glanda_device, drm);
+	if (IS_ERR(gdev))
+		return PTR_ERR(gdev);
+
+	platform_set_drvdata(pdev, gdev);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+
+	gdev->vram_phys = res->start;
+	gdev->vram_base = devm_ioremap(&pdev->dev, res->start, GLANDA_VRAM_SIZE);
+	gdev->mmio_base = devm_ioremap(&pdev->dev, res->start + GLANDA_MMIO_OFFSET,
+				       GLANDA_MMIO_SIZE);
+	if (!gdev->vram_base || !gdev->mmio_base) {
+		drm_err(&gdev->drm, "failed to ioremap\n");
+		return -ENOMEM;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq == -ENXIO)
+		irq = -1;	/* no IRQ resource, fall back to polling */
+	else if (irq < 0)
+		return irq;
+
+	return glanda_drm_init(gdev, irq);
+}
+
+static void glandagpu_remove(struct platform_device *pdev)
+{
+	glanda_drm_fini(platform_get_drvdata(pdev));
+}
+
+/* Device Tree match table. */
+static const struct of_device_id glanda_of_match[] = {
+	{ .compatible = "glanda,gpu-1.0" },
+	{ /* end of table */  }
+};
+
+MODULE_DEVICE_TABLE(of, glanda_of_match);
+
+static struct platform_driver glandagpu_driver = {
+	.driver = {
+		.name = "glandagpu",
+	   .of_match_table = glanda_of_match,
+	},
+	.probe = glandagpu_probe,
+	.remove = glandagpu_remove,
+};
+
+/* PCI probe path for the QEMU test device, real hardware uses platform_driver */
+static int glandagpu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct glanda_device *gdev;
+	int ret;
+
+	dev_info(&pdev->dev, "GlandaGPU PCI Probe started\n");
+
+	ret = pcim_enable_device(pdev);
+	if (ret)
+		return ret;
+	pci_set_master(pdev);
+
+	ret = pcim_iomap_regions(pdev, BIT(0) | BIT(1), "glandagpu");
+	if (ret)
+		return ret;
+
+	gdev = devm_drm_dev_alloc(&pdev->dev, &glanda_drm_driver, struct glanda_device, drm);
+	if (IS_ERR(gdev))
+		return PTR_ERR(gdev);
+
+	pci_set_drvdata(pdev, gdev);
+
+	gdev->mmio_base = pcim_iomap_table(pdev)[0];
+	gdev->vram_base = pcim_iomap_table(pdev)[1];
+	gdev->vram_phys = pci_resource_start(pdev, 1);
+
+	return glanda_drm_init(gdev, pdev->irq);
+}
+
+static void glandagpu_pci_remove(struct pci_dev *pdev)
+{
+	glanda_drm_fini(pci_get_drvdata(pdev));
+}
+
+static const struct pci_device_id glanda_pci_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_REDHAT_QUMRANET, PCI_DEVICE_ID_GLANDA_GPU) },
+	{ /* end of table */ }
+};
+
+MODULE_DEVICE_TABLE(pci, glanda_pci_ids);
+
+static struct pci_driver glandagpu_pci_driver = {
+	.name = "glandagpu-pci",
+	.id_table = glanda_pci_ids,
+	.probe = glandagpu_pci_probe,
+	.remove = glandagpu_pci_remove,
+};
+
+static int __init glandagpu_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&glandagpu_driver);
+	if (ret) {
+		pr_err("GlandaGPU: Failed to register platform driver\n");
+		return ret;
+	}
+
+	ret = pci_register_driver(&glandagpu_pci_driver);
+	if (ret) {
+		pr_err("GlandaGPU: Failed to register PCI driver\n");
+		platform_driver_unregister(&glandagpu_driver);
+		return ret;
+	}
+
+	pr_info("GlandaGPU: Module loaded successfully\n");
+	return 0;
+}
+
+static void __exit glandagpu_exit(void)
+{
+	pci_unregister_driver(&glandagpu_pci_driver);
+	platform_driver_unregister(&glandagpu_driver);
+	pr_info("GlandaGPU: Module unloaded\n");
+}
+
+module_init(glandagpu_init);
+module_exit(glandagpu_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Leander Kieweg <kieweg.leander@gmail.com>");
+MODULE_DESCRIPTION("DRM driver for GlandaGPU, an FPGA-based 2D GPU with VGA output");
-- 
2.43.0


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* Re: [PATCH v2 2/2] drm/glanda: Add initial DRM driver for GlandaGPU
  2026-07-30 17:36 ` [PATCH v2 2/2] drm/glanda: Add initial DRM driver for GlandaGPU Leander Kieweg
@ 2026-07-30 17:52   ` sashiko-bot
  0 siblings, 0 replies; 4+ messages in thread
From: sashiko-bot @ 2026-07-30 17:52 UTC (permalink / raw)
  To: Leander Kieweg; +Cc: devicetree, robh, conor+dt, dri-devel

Thank you for your contribution! Sashiko AI review found 8 potential issue(s) to consider:
- [High] Ignored return value of drm_mode_config_init().
- [High] Hardware interrupts are left enabled if drm_dev_register() fails, leading to an unhandled interrupt storm.
- [High] Missing resource size validation before I/O memory mapping allows out-of-bounds mapping and writes.
- [High] Userspace atomic commits hang when the driver falls back to polling mode because vblank events are armed but never signaled.
- [Medium] Unused INT_DONE interrupt is unconditionally enabled, risking an interrupt storm.
- [Medium] Native u32 read of little-endian pixel data breaks color conversions on big-endian CPUs.
- [Low] Missing dependencies in Kconfig for DRM_GLANDA.
- [Low] Using platform_get_irq() for an optional IRQ causes log spam.
--

--- Patch [2]: [PATCH v2 2/2] drm/glanda: Add initial DRM driver for GlandaGPU ---
commit 47c9d06e7235a576cf0a48e9d5a1011c1d5c7ced
Author: Leander Kieweg <kieweg.leander@gmail.com>
Subject: drm/glanda: Add initial DRM driver for GlandaGPU

Introduce the core DRM/KMS driver for GlandaGPU. This driver supports basic
modesetting, atomic updates via shadow plane helpers, and optional QEMU PCI
probing alongside the platform driver.

> diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
> index f0e72d4b6a470..f5aaf499e34eb 100644
> --- a/drivers/gpu/drm/tiny/Kconfig
> +++ b/drivers/gpu/drm/tiny/Kconfig
[ ... ]
> @@ -56,6 +56,17 @@ config DRM_CIRRUS_QEMU
>  	   - qxl (DRM_QXL, qemu -vga qxl, works best with spice)
>  	   - virtio (DRM_VIRTIO_GPU), qemu -vga virtio)
>  
> +config DRM_GLANDA
> +	tristate "GlandaGPU DRM driver"
> +	depends on DRM
> +	select DRM_KMS_HELPER
> +	select DRM_GEM_SHMEM_HELPER

[Severity: Low]
Does this config need to depend on MMU and PCI || COMPILE_TEST? The driver
selects DRM_GEM_SHMEM_HELPER which depends on MMU, and it calls PCI devres
functions that lack non-PCI stubs when CONFIG_PCI is disabled.

> diff --git a/drivers/gpu/drm/tiny/glandagpu.c b/drivers/gpu/drm/tiny/glandagpu.c
> new file mode 100644
> index 0000000000000..e4dfddaba4e3b
> --- /dev/null
> +++ b/drivers/gpu/drm/tiny/glandagpu.c
[ ... ]
> +static void glanda_plane_atomic_update(struct drm_plane *plane,
> +				       struct drm_atomic_commit *state)
> +{
[ ... ]
> +	for (y = 0; y < height; y++) {
> +		size_t offset = y * GLANDA_WIDTH * sizeof(u32);
> +		u32 __iomem *dst = (u32 __iomem *)(gdev->vram_base + offset);
> +
> +		for (x = 0; x < width; x++) {
> +			u32 pixel = iosys_map_rd(&shadow_state->data[0],
> +						 y * src_pitch + x * sizeof(u32), u32);
> +			u32 packed = ((pixel >> 12) & 0x0F00) |
> +				((pixel >> 8) & 0x00F0) |
> +				((pixel >> 4) & 0x000F);
> +
> +			writel_relaxed(packed, &dst[x]);
> +		}
> +	}

[Severity: Medium]
Will this bitwise extraction read the correct color channels on big-endian
architectures? By using iosys_map_rd to read a native u32, the little-endian
DRM_FORMAT_XRGB8888 byte stream will have its bytes inverted on big-endian
CPUs.

[ ... ]
> +static void glanda_crtc_atomic_flush(struct drm_crtc *crtc,
> +				     struct drm_atomic_commit *state)
> +{
> +	struct drm_crtc_state *new_state = drm_atomic_get_new_crtc_state(state, crtc);
> +	struct drm_pending_vblank_event *event;
> +
> +	if (new_state->event) {
> +		event = new_state->event;
> +
> +		new_state->event = NULL;
> +
> +		spin_lock_irq(&crtc->dev->event_lock);
> +
> +		if (drm_crtc_vblank_get(crtc) == 0)
> +			drm_crtc_arm_vblank_event(crtc, event);
> +		else
> +			drm_crtc_send_vblank_event(crtc, event);

[Severity: High]
What happens to armed vblank events when the driver falls back to polling
mode? If there is no hardware interrupt to call drm_crtc_handle_vblank(),
these events might never be signaled, which can cause userspace page flips
to hang. Should the driver set crtc->state->no_vblank = true or bypass
drm_crtc_arm_vblank_event in polling mode?

[ ... ]
> +static int glanda_drm_init(struct glanda_device *gdev, int irq)
> +{
[ ... ]
> +	writel(0, gdev->mmio_base + REG_IER);
> +	writel(0xFFFFFFFF, gdev->mmio_base + REG_ISR);	/* clear flags */
> +
> +	/* DRM mode config */
> +	drm_mode_config_init(&gdev->drm);

[Severity: High]
Is it safe to ignore the integer return value of drm_mode_config_init? If
this fails due to memory allocation issues, the DRM mode configuration state
will be partially initialized, potentially leading to NULL pointer
dereferences later when the DRM core accesses it.

[ ... ]
> +	if (irq > 0) {
> +		gdev->irq = irq;
> +		ret = devm_request_irq(gdev->drm.dev, gdev->irq, glanda_irq_handler,
> +				       IRQF_SHARED, "glandagpu", gdev);
> +		if (ret) {
> +			drm_err(&gdev->drm, "Failed to request IRQ %d\n",
> +				gdev->irq);
> +			return ret;
> +		}
> +
> +		writel(INT_DONE, gdev->mmio_base + REG_IER);

[Severity: Medium]
Could enabling INT_DONE cause an interrupt storm? If the hardware asserts
INT_DONE when the 2D engine is idle, and the driver never submits commands
to it, the IRQ handler might get caught in a loop continuously clearing it.

> +		drm_info(&gdev->drm, "IRQ %d requested and enabled\n", gdev->irq);
> +	} else {
> +		drm_warn(&gdev->drm, "No IRQ found, falling back to polling\n");
> +	}
> +
> +	ret = drm_dev_register(&gdev->drm, 0);
> +	if (ret)
> +		return ret;

[Severity: High]
Does this error path leave hardware interrupts enabled? If
drm_dev_register fails, the function returns without clearing REG_IER.
Since devres frees the IRQ handler, this might leave the hardware asserting
an interrupt with no kernel handler available to acknowledge it.

[ ... ]
> +static int glandagpu_probe(struct platform_device *pdev)
> +{
[ ... ]
> +	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
> +	if (!res)
> +		return -ENODEV;
> +
> +	gdev->vram_phys = res->start;
> +	gdev->vram_base = devm_ioremap(&pdev->dev, res->start, GLANDA_VRAM_SIZE);
> +	gdev->mmio_base = devm_ioremap(&pdev->dev, res->start + GLANDA_MMIO_OFFSET,
> +				       GLANDA_MMIO_SIZE);

[Severity: High]
Should there be a check on the underlying resource length before mapping?
Blindly mapping GLANDA_VRAM_SIZE without verifying resource_size(res) could
cause out-of-bounds mappings if the hardware resource is undersized. Later,
the shadow plane write loop in glanda_plane_atomic_update() could overrun
the boundaries and corrupt physical memory.

> +	if (!gdev->vram_base || !gdev->mmio_base) {
> +		drm_err(&gdev->drm, "failed to ioremap\n");
> +		return -ENOMEM;
> +	}
> +
> +	irq = platform_get_irq(pdev, 0);
> +	if (irq == -ENXIO)
> +		irq = -1;	/* no IRQ resource, fall back to polling */

[Severity: Low]
Since the driver gracefully supports polling mode, could this use
platform_get_irq_optional instead? Using platform_get_irq logs a
false-positive error when the IRQ is not found.

[ ... ]
> +static int glandagpu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
> +{
[ ... ]
> +	gdev->mmio_base = pcim_iomap_table(pdev)[0];
> +	gdev->vram_base = pcim_iomap_table(pdev)[1];
> +	gdev->vram_phys = pci_resource_start(pdev, 1);

[Severity: High]
Does this PCI probe path also need to validate the size of the mapped BARs
against the expected GLANDA_VRAM_SIZE and GLANDA_MMIO_SIZE to prevent
similar out-of-bounds writes?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260730173643.256052-1-kieweg.leander@gmail.com?part=2

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2026-07-30 17:52 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-30 17:36 [PATCH v2 0/2] drm: Add DRM driver for GlandaGPU (VHDL soft-IP GPU) Leander Kieweg
2026-07-30 17:36 ` [PATCH v2 1/2] dt-bindings: display: Add GlandaGPU binding Leander Kieweg
2026-07-30 17:36 ` [PATCH v2 2/2] drm/glanda: Add initial DRM driver for GlandaGPU Leander Kieweg
2026-07-30 17:52   ` sashiko-bot

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).