* [PATCH v4 0/6] drm/hibmc: Fix plane helpers and convert to gem-shmem
@ 2026-06-18 12:28 Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 1/6] drm/hibmc: Use drm_atomic_helper_check_plane_state() Thomas Zimmermann
` (5 more replies)
0 siblings, 6 replies; 10+ messages in thread
From: Thomas Zimmermann @ 2026-06-18 12:28 UTC (permalink / raw)
To: shiyongbang, tiantao6, kong.kongxinwei, maarten.lankhorst,
mripard, airlied, simona
Cc: dri-devel, sashiko-reviews, Thomas Zimmermann
Convert hibmc's memory management from gem-vram ot gem-shmem. Fix a
number of bugs in preparation.
Patches 1 to 5 fix various bugs and minor issues in the plane code.
Patch 6 replaces gem-vram with gem-shmem. The rational is that gem-vram
has corner cases on low-end devices and is limited in functionality. The
commit messages state a list of possible issues.
Switching to gem-shmem avoids these problems. It also enables buffer
sharing via dma_buf, which improves the hibmc driver's integration with
the overall graphics ecosystem.
We've done these changes on drivers for similar hardware, such as ast and
mgag200. Hibmc is the last of these drivers to run on gem-shmem. Gem-vram
instead is deprecated and can hopefully be removed in a later release.
Tested on an RH1288 v3 system.
v4:
- verify framebuffer pitch aligns to 128
- store fb in local variable in atomic_update (Yongbang)
v3:
- fix coding style
- rebase on display-detection fixes
v2:
- extend commit message of patch 2 (Yongbang)
- so not select TTM any longer
Thomas Zimmermann (6):
drm/hibmc: Use drm_atomic_helper_check_plane_state()
drm/hibmc: Fix list of formats on the primary plane
drm/hibmc: Store fb in variable in atomic_update
drm/hibmc: Do not use cpp from struct drm_format_info
drm/hibmc: Verify the framebuffer pitch to be a multiple of 128
drm/hibmc: Use gem-shmem with shadow-plane helpers for memory
management
drivers/gpu/drm/drm_gem_shmem_helper.c | 22 +++-
drivers/gpu/drm/hisilicon/hibmc/Kconfig | 4 +-
.../gpu/drm/hisilicon/hibmc/hibmc_drm_de.c | 110 +++++++++---------
.../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 78 ++++++++++---
.../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 5 +
include/drm/drm_gem_shmem_helper.h | 4 +
6 files changed, 145 insertions(+), 78 deletions(-)
--
2.54.0
^ permalink raw reply [flat|nested] 10+ messages in thread
* [PATCH v4 1/6] drm/hibmc: Use drm_atomic_helper_check_plane_state()
2026-06-18 12:28 [PATCH v4 0/6] drm/hibmc: Fix plane helpers and convert to gem-shmem Thomas Zimmermann
@ 2026-06-18 12:28 ` Thomas Zimmermann
2026-06-18 12:48 ` sashiko-bot
2026-06-18 12:28 ` [PATCH v4 2/6] drm/hibmc: Fix list of formats on the primary plane Thomas Zimmermann
` (4 subsequent siblings)
5 siblings, 1 reply; 10+ messages in thread
From: Thomas Zimmermann @ 2026-06-18 12:28 UTC (permalink / raw)
To: shiyongbang, tiantao6, kong.kongxinwei, maarten.lankhorst,
mripard, airlied, simona
Cc: dri-devel, sashiko-reviews, Thomas Zimmermann, Rongrong Zou,
Sean Paul, Xinliang Liu, Dmitry Baryshkov, Baihan Li, stable
Call drm_atomic_helper_check_plane_state() from the primary plane's
atomic-check helper and replace the custom implementation.
All plane's implementations of atomic_check should call the shared
_check_plane_state() helper first. It adjusts the plane state for
correct positioning, rotation and scaling of the plane. Do this
even if the plane's CRTC has been disabled by setting the parameter
can_update_disabled. The original code returned early in this case,
but it's safe to so and cleaner to have all plane state initialized.
As we don't set can_position, drm_atomic_helper_check_plane_state()'s
visibility check tests if the plane covers all of the CRTC. This is
a small change from the original code, which tested if the plane is
exactly the size of the CRTC. With the new test, the plane still has
to cover all of the CRTC, but can be larger than the CRTC's size. A
later patch can fully implement this feature in hibmc.
If the plane is disabled, the helper clears the visibility flag in the
plane state. On errors or if the plane is not visible, the atomic-check
helper can return early. Implement all this in hibmc and drop the custom
code that does some of it.
v2:
- extend the commit description (Yongbang)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: da52605eea8f ("drm/hisilicon/hibmc: Add support for display engine")
Reviewed-by: Yongbang Shi <shiyongbang@huawei.com>
Cc: Rongrong Zou <zourongrong@gmail.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Xinliang Liu <xinliang.liu@linaro.org>
Cc: Dmitry Baryshkov <lumag@kernel.org>
Cc: Baihan Li <libaihan@huawei.com>
Cc: Yongbang Shi <shiyongbang@huawei.com>
Cc: <stable@vger.kernel.org> # v4.10+
---
.../gpu/drm/hisilicon/hibmc/hibmc_drm_de.c | 46 ++++++-------------
1 file changed, 14 insertions(+), 32 deletions(-)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index 3066dc9ebc64..7c0b88c774b5 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -72,46 +72,28 @@ static int hibmc_get_best_clock_idx(const struct drm_display_mode *mode)
static int hibmc_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_framebuffer *fb = new_plane_state->fb;
- struct drm_crtc *crtc = new_plane_state->crtc;
- struct drm_crtc_state *crtc_state;
- u32 src_w = new_plane_state->src_w >> 16;
- u32 src_h = new_plane_state->src_h >> 16;
-
- if (!crtc || !fb)
- return 0;
+ struct drm_plane_state *new_plane_state =
+ drm_atomic_get_new_plane_state(state, plane);
+ struct drm_crtc_state *new_crtc_state = NULL;
+ int ret;
- crtc_state = drm_atomic_get_crtc_state(state, crtc);
- if (IS_ERR(crtc_state))
- return PTR_ERR(crtc_state);
+ if (new_plane_state->crtc)
+ new_crtc_state = drm_atomic_get_new_crtc_state(state, new_plane_state->crtc);
- if (src_w != new_plane_state->crtc_w || src_h != new_plane_state->crtc_h) {
- drm_dbg_atomic(plane->dev, "scale not support\n");
- return -EINVAL;
- }
-
- if (new_plane_state->crtc_x < 0 || new_plane_state->crtc_y < 0) {
- drm_dbg_atomic(plane->dev, "crtc_x/y of drm_plane state is invalid\n");
- return -EINVAL;
- }
-
- if (!crtc_state->enable)
+ ret = drm_atomic_helper_check_plane_state(new_plane_state, new_crtc_state,
+ DRM_PLANE_NO_SCALING,
+ DRM_PLANE_NO_SCALING,
+ false, true);
+ if (ret)
+ return ret;
+ else if (!new_plane_state->visible)
return 0;
- if (new_plane_state->crtc_x + new_plane_state->crtc_w >
- crtc_state->adjusted_mode.hdisplay ||
- new_plane_state->crtc_y + new_plane_state->crtc_h >
- crtc_state->adjusted_mode.vdisplay) {
- drm_dbg_atomic(plane->dev, "visible portion of plane is invalid\n");
- return -EINVAL;
- }
-
if (new_plane_state->fb->pitches[0] % 128 != 0) {
drm_dbg_atomic(plane->dev, "wrong stride with 128-byte aligned\n");
return -EINVAL;
}
+
return 0;
}
--
2.54.0
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH v4 2/6] drm/hibmc: Fix list of formats on the primary plane
2026-06-18 12:28 [PATCH v4 0/6] drm/hibmc: Fix plane helpers and convert to gem-shmem Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 1/6] drm/hibmc: Use drm_atomic_helper_check_plane_state() Thomas Zimmermann
@ 2026-06-18 12:28 ` Thomas Zimmermann
2026-06-18 12:43 ` sashiko-bot
2026-06-18 12:28 ` [PATCH v4 3/6] drm/hibmc: Store fb in variable in atomic_update Thomas Zimmermann
` (3 subsequent siblings)
5 siblings, 1 reply; 10+ messages in thread
From: Thomas Zimmermann @ 2026-06-18 12:28 UTC (permalink / raw)
To: shiyongbang, tiantao6, kong.kongxinwei, maarten.lankhorst,
mripard, airlied, simona
Cc: dri-devel, sashiko-reviews, Thomas Zimmermann, Rongrong Zou,
Sean Paul, Xinliang Liu, Dmitry Baryshkov, Baihan Li, stable
Remove all formats from the primary plane that are unsupported for
various reasons.
* Formats with alpha channel: planes should not announce alpha channels
unless they support transparency. There's no transparency support in
the primary plane's implementation.
* Formats with BGR order. The common format is in RGB channel order.
There's no BGR support in the primary plane's implementation.
* RGB888: atomic_update programs the format from cpp[0] * 8 / 16. For
RGB888's cpp value of 3 this returns 1.5; rounded to 1. Programming
the value of 1 to HIBMC_CRT_DISP_CTL_FORMAT sets up RGB565. Hence, the
output is distorted. This can be tested by booting with video=1024x768-24.
Removing all unsupported formats leaves XRGB8888 and RGB565. Both of
which are supported and work correctly.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: da52605eea8f ("drm/hisilicon/hibmc: Add support for display engine")
Reviewed-by: Yongbang Shi <shiyongbang@huawei.com>
Cc: Rongrong Zou <zourongrong@gmail.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Xinliang Liu <xinliang.liu@linaro.org>
Cc: Dmitry Baryshkov <lumag@kernel.org>
Cc: Yongbang Shi <shiyongbang@huawei.com>
Cc: Baihan Li <libaihan@huawei.com>
Cc: <stable@vger.kernel.org> # v4.10+
---
drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index 7c0b88c774b5..2e6e189bec1a 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -135,10 +135,8 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
}
static const u32 channel_formats1[] = {
- DRM_FORMAT_RGB565, DRM_FORMAT_BGR565, DRM_FORMAT_RGB888,
- DRM_FORMAT_BGR888, DRM_FORMAT_XRGB8888, DRM_FORMAT_XBGR8888,
- DRM_FORMAT_RGBA8888, DRM_FORMAT_BGRA8888, DRM_FORMAT_ARGB8888,
- DRM_FORMAT_ABGR8888
+ DRM_FORMAT_XRGB8888,
+ DRM_FORMAT_RGB565,
};
static const struct drm_plane_funcs hibmc_plane_funcs = {
--
2.54.0
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH v4 3/6] drm/hibmc: Store fb in variable in atomic_update
2026-06-18 12:28 [PATCH v4 0/6] drm/hibmc: Fix plane helpers and convert to gem-shmem Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 1/6] drm/hibmc: Use drm_atomic_helper_check_plane_state() Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 2/6] drm/hibmc: Fix list of formats on the primary plane Thomas Zimmermann
@ 2026-06-18 12:28 ` Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 4/6] drm/hibmc: Do not use cpp from struct drm_format_info Thomas Zimmermann
` (2 subsequent siblings)
5 siblings, 0 replies; 10+ messages in thread
From: Thomas Zimmermann @ 2026-06-18 12:28 UTC (permalink / raw)
To: shiyongbang, tiantao6, kong.kongxinwei, maarten.lankhorst,
mripard, airlied, simona
Cc: dri-devel, sashiko-reviews, Thomas Zimmermann
The atomic-update helper frequently refers to the framebuffer in
new_state->fb. Store it in a local variable to make the code more
readable. No functional changes.
Suggested-by: Yongbang Shi <shiyongbang@huawei.com>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c | 15 +++++++--------
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index 2e6e189bec1a..19cb16a7daf9 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -100,18 +100,18 @@ static int hibmc_plane_atomic_check(struct drm_plane *plane,
static void hibmc_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_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane);
+ struct drm_framebuffer *fb = new_state->fb;
u32 reg;
s64 gpu_addr = 0;
u32 line_l;
struct hibmc_drm_private *priv = to_hibmc_drm_private(plane->dev);
struct drm_gem_vram_object *gbo;
- if (!new_state->fb)
+ if (!fb)
return;
- gbo = drm_gem_vram_of_gem(new_state->fb->obj[0]);
+ gbo = drm_gem_vram_of_gem(fb->obj[0]);
gpu_addr = drm_gem_vram_offset(gbo);
if (WARN_ON_ONCE(gpu_addr < 0))
@@ -119,9 +119,9 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
writel(gpu_addr, priv->mmio + HIBMC_CRT_FB_ADDRESS);
- reg = new_state->fb->width * (new_state->fb->format->cpp[0]);
+ reg = fb->width * fb->format->cpp[0];
- line_l = new_state->fb->pitches[0];
+ line_l = fb->pitches[0];
writel(HIBMC_FIELD(HIBMC_CRT_FB_WIDTH_WIDTH, reg) |
HIBMC_FIELD(HIBMC_CRT_FB_WIDTH_OFFS, line_l),
priv->mmio + HIBMC_CRT_FB_WIDTH);
@@ -129,8 +129,7 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
/* SET PIXEL FORMAT */
reg = readl(priv->mmio + HIBMC_CRT_DISP_CTL);
reg &= ~HIBMC_CRT_DISP_CTL_FORMAT_MASK;
- reg |= HIBMC_FIELD(HIBMC_CRT_DISP_CTL_FORMAT,
- new_state->fb->format->cpp[0] * 8 / 16);
+ reg |= HIBMC_FIELD(HIBMC_CRT_DISP_CTL_FORMAT, fb->format->cpp[0] * 8 / 16);
writel(reg, priv->mmio + HIBMC_CRT_DISP_CTL);
}
--
2.54.0
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH v4 4/6] drm/hibmc: Do not use cpp from struct drm_format_info
2026-06-18 12:28 [PATCH v4 0/6] drm/hibmc: Fix plane helpers and convert to gem-shmem Thomas Zimmermann
` (2 preceding siblings ...)
2026-06-18 12:28 ` [PATCH v4 3/6] drm/hibmc: Store fb in variable in atomic_update Thomas Zimmermann
@ 2026-06-18 12:28 ` Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 5/6] drm/hibmc: Verify the framebuffer pitch to be a multiple of 128 Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 6/6] drm/hibmc: Use gem-shmem with shadow-plane helpers for memory management Thomas Zimmermann
5 siblings, 0 replies; 10+ messages in thread
From: Thomas Zimmermann @ 2026-06-18 12:28 UTC (permalink / raw)
To: shiyongbang, tiantao6, kong.kongxinwei, maarten.lankhorst,
mripard, airlied, simona
Cc: dri-devel, sashiko-reviews, Thomas Zimmermann
Replace uses of struct drm_format_info's cpp with appropriate interfaces.
The cpp field contains the characters per pixel. It is deprecated and
should be avoided.
Calculate the line width in bytes with drm_format_info_min_pitch(). This
is the preferred way of getting pixel and line sizes.
Program HIB_CRT_DISP_CTL_FORMAT from the format's 4CC code instead of
calculating the field's value from the cpp.
v4:
- introduce fb variable in separate patch (Yongbang)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index 19cb16a7daf9..fe73b365e547 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -119,7 +119,7 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
writel(gpu_addr, priv->mmio + HIBMC_CRT_FB_ADDRESS);
- reg = fb->width * fb->format->cpp[0];
+ reg = drm_format_info_min_pitch(fb->format, 0, fb->width);
line_l = fb->pitches[0];
writel(HIBMC_FIELD(HIBMC_CRT_FB_WIDTH_WIDTH, reg) |
@@ -129,7 +129,14 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
/* SET PIXEL FORMAT */
reg = readl(priv->mmio + HIBMC_CRT_DISP_CTL);
reg &= ~HIBMC_CRT_DISP_CTL_FORMAT_MASK;
- reg |= HIBMC_FIELD(HIBMC_CRT_DISP_CTL_FORMAT, fb->format->cpp[0] * 8 / 16);
+ switch (fb->format->format) {
+ case DRM_FORMAT_XRGB8888:
+ reg |= HIBMC_FIELD(HIBMC_CRT_DISP_CTL_FORMAT, 2);
+ break;
+ case DRM_FORMAT_RGB565:
+ reg |= HIBMC_FIELD(HIBMC_CRT_DISP_CTL_FORMAT, 1);
+ break;
+ }
writel(reg, priv->mmio + HIBMC_CRT_DISP_CTL);
}
--
2.54.0
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH v4 5/6] drm/hibmc: Verify the framebuffer pitch to be a multiple of 128
2026-06-18 12:28 [PATCH v4 0/6] drm/hibmc: Fix plane helpers and convert to gem-shmem Thomas Zimmermann
` (3 preceding siblings ...)
2026-06-18 12:28 ` [PATCH v4 4/6] drm/hibmc: Do not use cpp from struct drm_format_info Thomas Zimmermann
@ 2026-06-18 12:28 ` Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 6/6] drm/hibmc: Use gem-shmem with shadow-plane helpers for memory management Thomas Zimmermann
5 siblings, 0 replies; 10+ messages in thread
From: Thomas Zimmermann @ 2026-06-18 12:28 UTC (permalink / raw)
To: shiyongbang, tiantao6, kong.kongxinwei, maarten.lankhorst,
mripard, airlied, simona
Cc: dri-devel, sashiko-reviews, Thomas Zimmermann
The hibmc hardware requires the framebuffer pitch to be aligned to
a multiple of 128. Dumb-buffer creation already guarantees this for
the created GEM buffer object. Also verify this contraint during
framebuffer creation.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
.../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index 99b36de1fe13..55d175028c46 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -14,6 +14,7 @@
#include <linux/aperture.h>
#include <linux/module.h>
#include <linux/pci.h>
+#include <linux/sizes.h>
#include <drm/clients/drm_client_setup.h>
#include <drm/drm_atomic_helper.h>
@@ -106,11 +107,26 @@ static const struct dev_pm_ops hibmc_pm_ops = {
hibmc_pm_resume)
};
+static struct drm_framebuffer *hibmc_mode_config_fb_create(struct drm_device *dev,
+ struct drm_file *file_priv,
+ const struct drm_format_info *info,
+ const struct drm_mode_fb_cmd2 *mode_cmd)
+{
+ int i;
+
+ for (i = 0; i < info->num_planes; ++i) {
+ if (mode_cmd->pitches[i] % SZ_128)
+ return ERR_PTR(-EINVAL);
+ }
+
+ return drm_gem_fb_create(dev, file_priv, info, mode_cmd);
+}
+
static const struct drm_mode_config_funcs hibmc_mode_funcs = {
.mode_valid = drm_vram_helper_mode_valid,
.atomic_check = drm_atomic_helper_check,
.atomic_commit = drm_atomic_helper_commit,
- .fb_create = drm_gem_fb_create,
+ .fb_create = hibmc_mode_config_fb_create,
};
static int hibmc_kms_init(struct hibmc_drm_private *priv)
--
2.54.0
^ permalink raw reply related [flat|nested] 10+ messages in thread
* [PATCH v4 6/6] drm/hibmc: Use gem-shmem with shadow-plane helpers for memory management
2026-06-18 12:28 [PATCH v4 0/6] drm/hibmc: Fix plane helpers and convert to gem-shmem Thomas Zimmermann
` (4 preceding siblings ...)
2026-06-18 12:28 ` [PATCH v4 5/6] drm/hibmc: Verify the framebuffer pitch to be a multiple of 128 Thomas Zimmermann
@ 2026-06-18 12:28 ` Thomas Zimmermann
2026-06-18 12:43 ` sashiko-bot
5 siblings, 1 reply; 10+ messages in thread
From: Thomas Zimmermann @ 2026-06-18 12:28 UTC (permalink / raw)
To: shiyongbang, tiantao6, kong.kongxinwei, maarten.lankhorst,
mripard, airlied, simona
Cc: dri-devel, sashiko-reviews, Thomas Zimmermann
Replace the gem-vram memory manager with gem-shmem. Makes the driver more
robust and enables dma-buf sharing with other hardware.
Gem-vram was created from various drivers that used TTM for their memory
management. All these drivers have meanwhile been converted to gem-shmem.
Using gem-vram is deprecated because it has several problems.
* TTM requires significant overcommitment of video memory for reliable
page flips. There needs to be 3 times the size of the largest possible
framebuffer available or page flips can fail. This leaves the display
dark without further warning. Hibmc hardware with 32 MiB and a maximum
framebuffer size of 1920x2000 is at the limit.
* No dma-buf sharing without GTT support. Neither gem-vram nor hibmc
hardware support a GTT address space. This is required to share buffers
with other devices via dma-buf interfaces.
* TTM requires hardware-accelerated rendering into video memory for
optimal results. As hibmc hardware cannot do this, hibmc renders in
system memory and copies the result to video memory. This can be more
effectively implemented with gem-shmem and DRM's shadow-plane helpers.
Converting hibmc to gem-shmem and shadow-plane helpers.
* Replace gem-vram entry points in struct drm_driver with gem-shmem
equivalents. This makes the driver allocate struct drm_gem_shmem_object
for its buffers.
* Use DRM_GEM_SHADOW_*_PLANE for its plane funcs and plane-helper
funcs. The shadow-plane helpers map a plane's gem buffer objects into
kernel address space during a page flip, so that atomic_update can
copy them to video memory.
* Handle framebuffer damage in hibmc_plane_atomic_update(). This updates
video memory from the plane's framebuffer. It automatically synchronizes
shared buffers with other devices. Create the framebuffer with
drm_gem_fb_create_with_dirty() to trigger the update on each page flip.
* Initialize the plane with drm_plane_enable_fb_damage_clips() to limit
the damage updates to the framebuffer areas that changed. We don't want
to do a full-buffer memcpy if only a small area has changed.
* Test display modes against the available video memory in
hibmc_mode_config_mode_valid(). We only want to announce display modes
that fit into display memory.
* Map the display memory itself into kernel address space.
* Do not set drm_mode_config.prefer_shadow. This would advise user space
to install a shadow buffer. But with gem-shmem, the gem buffer object
already acts as a shadow buffer for video memory.
We use these patterns in many other drivers with similar limitation as
hibmc and its hardware. With these changes in place, hibmc is more robust
and better integrated into the overall DRM framework.
v3:
- fix coding style
v2:
- do not select TTM symbols
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
drivers/gpu/drm/drm_gem_shmem_helper.c | 22 +++++--
drivers/gpu/drm/hisilicon/hibmc/Kconfig | 4 +-
.../gpu/drm/hisilicon/hibmc/hibmc_drm_de.c | 38 ++++++++----
.../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 62 ++++++++++++++-----
.../gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h | 5 ++
include/drm/drm_gem_shmem_helper.h | 4 ++
6 files changed, 100 insertions(+), 35 deletions(-)
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index c989459eb215..22ec52e2ffb8 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -473,10 +473,23 @@ void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem,
}
EXPORT_SYMBOL_GPL(drm_gem_shmem_vunmap_locked);
-static int
-drm_gem_shmem_create_with_handle(struct drm_file *file_priv,
- struct drm_device *dev, size_t size,
- uint32_t *handle)
+/**
+ * drm_gem_shmem_create_with_handle - Allocate an object with the given size and
+ * returns a GEM handle
+ * @file_priv: DRM file structure to create the dumb buffer for
+ * @dev: DRM device
+ * @size: Size of the object to allocate
+ * @handle: Returns the GEM handle on success
+ *
+ * Allocates an shmem GEM buffer using drm_gem_shmem_create() and returns
+ * a GEM handle to it.
+ *
+ * Returns:
+ * Zero on success, or an error code otherwise.
+ */
+int drm_gem_shmem_create_with_handle(struct drm_file *file_priv,
+ struct drm_device *dev, size_t size,
+ uint32_t *handle)
{
struct drm_gem_shmem_object *shmem;
int ret;
@@ -495,6 +508,7 @@ drm_gem_shmem_create_with_handle(struct drm_file *file_priv,
return ret;
}
+EXPORT_SYMBOL_GPL(drm_gem_shmem_create_with_handle);
/* Update madvise status, returns true if not purged, else
* false or -errno.
diff --git a/drivers/gpu/drm/hisilicon/hibmc/Kconfig b/drivers/gpu/drm/hisilicon/hibmc/Kconfig
index d1f3f5793f34..adf4516bf8f6 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/Kconfig
+++ b/drivers/gpu/drm/hisilicon/hibmc/Kconfig
@@ -5,10 +5,8 @@ config DRM_HISI_HIBMC
select DRM_CLIENT_SELECTION
select DRM_DISPLAY_HELPER
select DRM_DISPLAY_DP_HELPER
+ select DRM_GEM_SHMEM_HELPER
select DRM_KMS_HELPER
- select DRM_VRAM_HELPER
- select DRM_TTM
- select DRM_TTM_HELPER
select I2C
select I2C_ALGOBIT
help
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index fe73b365e547..b4ab53db1c08 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -15,8 +15,10 @@
#include <drm/drm_atomic.h>
#include <drm/drm_atomic_helper.h>
+#include <drm/drm_damage_helper.h>
#include <drm/drm_fourcc.h>
-#include <drm/drm_gem_vram_helper.h>
+#include <drm/drm_gem_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
#include <drm/drm_vblank.h>
#include "hibmc_drm_drv.h"
@@ -100,22 +102,35 @@ static int hibmc_plane_atomic_check(struct drm_plane *plane,
static void hibmc_plane_atomic_update(struct drm_plane *plane,
struct drm_atomic_commit *state)
{
+ struct hibmc_drm_private *priv = to_hibmc_drm_private(plane->dev);
struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane);
+ struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(new_state);
struct drm_framebuffer *fb = new_state->fb;
+ struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state, plane);
+ u32 gpu_addr = 0;
u32 reg;
- s64 gpu_addr = 0;
u32 line_l;
- struct hibmc_drm_private *priv = to_hibmc_drm_private(plane->dev);
- struct drm_gem_vram_object *gbo;
if (!fb)
return;
- gbo = drm_gem_vram_of_gem(fb->obj[0]);
+ if (drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE) == 0) {
+ struct drm_rect damage;
+ struct drm_atomic_helper_damage_iter iter;
+
+ drm_atomic_helper_damage_iter_init(&iter, old_state, new_state);
+ drm_atomic_for_each_plane_damage(&iter, &damage) {
+ struct iosys_map dst[DRM_FORMAT_MAX_PLANES] = {
+ IOSYS_MAP_INIT_VADDR_IOMEM(priv->vram + gpu_addr),
+ };
- gpu_addr = drm_gem_vram_offset(gbo);
- if (WARN_ON_ONCE(gpu_addr < 0))
- return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */
+ iosys_map_incr(&dst[0],
+ drm_fb_clip_offset(fb->pitches[0], fb->format, &damage));
+ drm_fb_memcpy(dst, fb->pitches, shadow_plane_state->data, fb, &damage);
+ }
+
+ drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
+ }
writel(gpu_addr, priv->mmio + HIBMC_CRT_FB_ADDRESS);
@@ -149,13 +164,11 @@ static const struct drm_plane_funcs hibmc_plane_funcs = {
.update_plane = drm_atomic_helper_update_plane,
.disable_plane = drm_atomic_helper_disable_plane,
.destroy = drm_plane_cleanup,
- .reset = drm_atomic_helper_plane_reset,
- .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
- .atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+ DRM_GEM_SHADOW_PLANE_FUNCS,
};
static const struct drm_plane_helper_funcs hibmc_plane_helper_funcs = {
- DRM_GEM_VRAM_PLANE_HELPER_FUNCS,
+ DRM_GEM_SHADOW_PLANE_HELPER_FUNCS,
.atomic_check = hibmc_plane_atomic_check,
.atomic_update = hibmc_plane_atomic_update,
};
@@ -515,6 +528,7 @@ int hibmc_de_init(struct hibmc_drm_private *priv)
}
drm_plane_helper_add(plane, &hibmc_plane_helper_funcs);
+ drm_plane_enable_fb_damage_clips(plane);
ret = drm_crtc_init_with_planes(dev, crtc, plane,
NULL, &hibmc_crtc_funcs, NULL);
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index 55d175028c46..4d85c89f3f88 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -19,9 +19,10 @@
#include <drm/clients/drm_client_setup.h>
#include <drm/drm_atomic_helper.h>
#include <drm/drm_drv.h>
-#include <drm/drm_fbdev_ttm.h>
+#include <drm/drm_dumb_buffers.h>
+#include <drm/drm_fbdev_shmem.h>
#include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_gem_vram_helper.h>
+#include <drm/drm_gem_shmem_helper.h>
#include <drm/drm_managed.h>
#include <drm/drm_module.h>
#include <drm/drm_vblank.h>
@@ -72,7 +73,13 @@ static irqreturn_t hibmc_dp_interrupt(int irq, void *arg)
static int hibmc_dumb_create(struct drm_file *file, struct drm_device *dev,
struct drm_mode_create_dumb *args)
{
- return drm_gem_vram_fill_create_dumb(file, dev, 0, 128, args);
+ int ret;
+
+ ret = drm_mode_size_dumb(dev, args, SZ_128, 0);
+ if (ret)
+ return ret;
+
+ return drm_gem_shmem_create_with_handle(file, dev, args->size, &args->handle);
}
static const struct drm_driver hibmc_driver = {
@@ -82,10 +89,9 @@ static const struct drm_driver hibmc_driver = {
.desc = "hibmc drm driver",
.major = 1,
.minor = 0,
- .debugfs_init = drm_vram_mm_debugfs_init,
- .dumb_create = hibmc_dumb_create,
- .dumb_map_offset = drm_gem_ttm_dumb_map_offset,
- DRM_FBDEV_TTM_DRIVER_OPS,
+ .gem_prime_import = drm_gem_shmem_prime_import_no_map,
+ .dumb_create = hibmc_dumb_create,
+ DRM_FBDEV_SHMEM_DRIVER_OPS,
};
static int __maybe_unused hibmc_pm_suspend(struct device *dev)
@@ -107,6 +113,27 @@ static const struct dev_pm_ops hibmc_pm_ops = {
hibmc_pm_resume)
};
+static enum drm_mode_status hibmc_mode_config_mode_valid(struct drm_device *dev,
+ const struct drm_display_mode *mode)
+{
+ const struct drm_format_info *info =
+ drm_get_format_info(dev, DRM_FORMAT_XRGB8888, DRM_FORMAT_MOD_LINEAR);
+ struct hibmc_drm_private *priv = to_hibmc_drm_private(dev);
+ unsigned long max_fb_size = priv->vram_size;
+ u64 pitch;
+
+ if (drm_WARN_ON_ONCE(dev, !info))
+ return MODE_ERROR; /* driver bug */
+
+ pitch = drm_format_info_min_pitch(info, 0, mode->hdisplay);
+ if (!pitch)
+ return MODE_BAD_WIDTH;
+ else if (pitch > max_fb_size / mode->vdisplay)
+ return MODE_MEM;
+
+ return MODE_OK;
+}
+
static struct drm_framebuffer *hibmc_mode_config_fb_create(struct drm_device *dev,
struct drm_file *file_priv,
const struct drm_format_info *info,
@@ -119,11 +146,11 @@ static struct drm_framebuffer *hibmc_mode_config_fb_create(struct drm_device *de
return ERR_PTR(-EINVAL);
}
- return drm_gem_fb_create(dev, file_priv, info, mode_cmd);
+ return drm_gem_fb_create_with_dirty(dev, file_priv, info, mode_cmd);
}
static const struct drm_mode_config_funcs hibmc_mode_funcs = {
- .mode_valid = drm_vram_helper_mode_valid,
+ .mode_valid = hibmc_mode_config_mode_valid,
.atomic_check = drm_atomic_helper_check,
.atomic_commit = drm_atomic_helper_commit,
.fb_create = hibmc_mode_config_fb_create,
@@ -146,7 +173,6 @@ static int hibmc_kms_init(struct hibmc_drm_private *priv)
dev->mode_config.max_height = 1200;
dev->mode_config.preferred_depth = 24;
- dev->mode_config.prefer_shadow = 1;
dev->mode_config.funcs = (void *)&hibmc_mode_funcs;
@@ -351,18 +377,22 @@ static int hibmc_load(struct drm_device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
struct hibmc_drm_private *priv = to_hibmc_drm_private(dev);
+ resource_size_t vram_base, vram_size;
int ret;
ret = hibmc_hw_init(priv);
if (ret)
return ret;
- ret = drmm_vram_helper_init(dev, pci_resource_start(pdev, 0),
- pci_resource_len(pdev, 0));
- if (ret) {
- drm_err(dev, "Error initializing VRAM MM; %d\n", ret);
- return ret;
- }
+ vram_base = pci_resource_start(pdev, 0);
+ vram_size = pci_resource_len(pdev, 0);
+
+ priv->vram = devm_ioremap_wc(dev->dev, vram_base, vram_size);
+ if (!priv->vram)
+ return -ENOMEM;
+
+ priv->vram_base = vram_base;
+ priv->vram_size = vram_size;
ret = hibmc_kms_init(priv);
if (ret)
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
index cd3a3fca1fe6..dce8572bf63e 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
@@ -38,6 +38,11 @@ struct hibmc_drm_private {
/* hw */
void __iomem *mmio;
+ /* vram */
+ void __iomem *vram;
+ resource_size_t vram_base;
+ resource_size_t vram_size;
+
/* drm */
struct drm_device dev;
struct drm_plane primary_plane;
diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h
index b2c23af628e1..bcbb92f3fe9b 100644
--- a/include/drm/drm_gem_shmem_helper.h
+++ b/include/drm/drm_gem_shmem_helper.h
@@ -142,6 +142,10 @@ struct sg_table *drm_gem_shmem_get_pages_sgt(struct drm_gem_shmem_object *shmem)
void drm_gem_shmem_print_info(const struct drm_gem_shmem_object *shmem,
struct drm_printer *p, unsigned int indent);
+int drm_gem_shmem_create_with_handle(struct drm_file *file_priv,
+ struct drm_device *dev, size_t size,
+ uint32_t *handle);
+
extern const struct vm_operations_struct drm_gem_shmem_vm_ops;
/*
--
2.54.0
^ permalink raw reply related [flat|nested] 10+ messages in thread
* Re: [PATCH v4 2/6] drm/hibmc: Fix list of formats on the primary plane
2026-06-18 12:28 ` [PATCH v4 2/6] drm/hibmc: Fix list of formats on the primary plane Thomas Zimmermann
@ 2026-06-18 12:43 ` sashiko-bot
0 siblings, 0 replies; 10+ messages in thread
From: sashiko-bot @ 2026-06-18 12:43 UTC (permalink / raw)
To: Thomas Zimmermann; +Cc: dri-devel
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
Pre-existing issues:
- [High] The display plane atomic update ignores the plane state's source coordinates and dimensions, causing corrupted output for cropped or panned framebuffers.
- [High] The CRTC atomic flush immediately sends the vblank event instead of arming it, breaking page-flip synchronization.
--
commit c951a1d1c3d9caa9dc42e8ab8693ac3a8121b925
Author: Thomas Zimmermann <tzimmermann@suse.de>
Subject: drm/hibmc: Fix list of formats on the primary plane
This commit removes unsupported formats from the primary plane, leaving
only XRGB8888 and RGB565. It addresses issues where planes with alpha
channels or BGR order were not properly supported, and fixes distorted
output for RGB888.
> diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> index 7c0b88c774b5e..2e6e189bec1a0 100644
> --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> @@ -135,10 +135,8 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
> }
[Severity: High]
This isn't a bug introduced by this patch, but does
hibmc_plane_atomic_update() ignore the plane state's source coordinates?
It programs the hardware's visible scanout width using the full fb->width
instead of the active source width (new_state->src_w >> 16):
writel(gpu_addr, priv->mmio + HIBMC_CRT_FB_ADDRESS);
reg = drm_format_info_min_pitch(fb->format, 0, fb->width);
line_l = fb->pitches[0];
writel(HIBMC_FIELD(HIBMC_CRT_FB_WIDTH_WIDTH, reg) |
HIBMC_FIELD(HIBMC_CRT_FB_WIDTH_OFFS, line_l),
priv->mmio + HIBMC_CRT_FB_WIDTH);
Since the shadow plane damage copy maintains the original framebuffer's
layout in VRAM, scanning out from offset 0 with fb->width means the
hardware will always display the top-left of the framebuffer. If userspace
provides a framebuffer larger than the CRTC (e.g., for panning) or requests
cropping, will the hardware fetch the wrong number of pixels per scanline
and display the wrong region?
>
> static const u32 channel_formats1[] = {
> - DRM_FORMAT_RGB565, DRM_FORMAT_BGR565, DRM_FORMAT_RGB888,
> - DRM_FORMAT_BGR888, DRM_FORMAT_XRGB8888, DRM_FORMAT_XBGR8888,
> - DRM_FORMAT_RGBA8888, DRM_FORMAT_BGRA8888, DRM_FORMAT_ARGB8888,
> - DRM_FORMAT_ABGR8888
> + DRM_FORMAT_XRGB8888,
> + DRM_FORMAT_RGB565,
> };
[Severity: High]
This is a pre-existing issue, but does hibmc_crtc_atomic_flush()
immediately send the vblank event instead of arming it?
if (crtc->state->event)
drm_crtc_send_vblank_event(crtc, crtc->state->event);
crtc->state->event = NULL;
Because the driver has working vblank interrupts (as shown by
hibmc_crtc_enable_vblank()), shouldn't it defer the event until the actual
vertical blanking interval with drm_crtc_arm_vblank_event()? Immediately
completing the event violates the atomic KMS API contract, causing
userspace compositors to render the next frame prematurely, which results
in screen tearing and breaks presentation timing guarantees.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260618123142.92298-1-tzimmermann@suse.de?part=2
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v4 6/6] drm/hibmc: Use gem-shmem with shadow-plane helpers for memory management
2026-06-18 12:28 ` [PATCH v4 6/6] drm/hibmc: Use gem-shmem with shadow-plane helpers for memory management Thomas Zimmermann
@ 2026-06-18 12:43 ` sashiko-bot
0 siblings, 0 replies; 10+ messages in thread
From: sashiko-bot @ 2026-06-18 12:43 UTC (permalink / raw)
To: Thomas Zimmermann; +Cc: dri-devel
Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Critical] Missing bounds check on framebuffer size and pitch allows an out-of-bounds write into the memory mapped VRAM.
- [High] Sleep in atomic context due to manual call of `drm_gem_fb_begin_cpu_access()` inside plane atomic update.
--
commit dadf851669fd23173dce5357fbb44cac3db06b77
Author: Thomas Zimmermann <tzimmermann@suse.de>
drm/hibmc: Use gem-shmem with shadow-plane helpers for memory management
Replace the gem-vram memory manager with gem-shmem. Makes the driver more
robust and enables dma-buf sharing with other hardware.
[ ... ]
> diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> index fe73b365e5474..b4ab53db1c087 100644
> --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> @@ -100,22 +102,35 @@ static int hibmc_plane_atomic_check(struct drm_plane *plane,
> static void hibmc_plane_atomic_update(struct drm_plane *plane,
> struct drm_atomic_commit *state)
> {
> + struct hibmc_drm_private *priv = to_hibmc_drm_private(plane->dev);
> struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane);
> + struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(new_state);
> struct drm_framebuffer *fb = new_state->fb;
> + struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state, plane);
> + u32 gpu_addr = 0;
> u32 reg;
> - s64 gpu_addr = 0;
> u32 line_l;
> - struct hibmc_drm_private *priv = to_hibmc_drm_private(plane->dev);
> - struct drm_gem_vram_object *gbo;
>
> if (!fb)
> return;
>
> - gbo = drm_gem_vram_of_gem(fb->obj[0]);
> + if (drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE) == 0) {
[Severity: High]
Is it safe to call drm_gem_fb_begin_cpu_access() here?
This function can sleep (for example, by acquiring dma_resv_lock for
imported dma-bufs), but hibmc_plane_atomic_update() runs in atomic context
where sleeping is forbidden.
Also, since the driver uses DRM_GEM_SHADOW_PLANE_HELPER_FUNCS which
automatically registers .begin_fb_access = drm_gem_begin_shadow_fb_access,
doesn't the DRM core already handle buffer mapping and synchronization
outside the atomic section?
> + struct drm_rect damage;
> + struct drm_atomic_helper_damage_iter iter;
> +
> + drm_atomic_helper_damage_iter_init(&iter, old_state, new_state);
> + drm_atomic_for_each_plane_damage(&iter, &damage) {
> + struct iosys_map dst[DRM_FORMAT_MAX_PLANES] = {
> + IOSYS_MAP_INIT_VADDR_IOMEM(priv->vram + gpu_addr),
> + };
>
> - gpu_addr = drm_gem_vram_offset(gbo);
> - if (WARN_ON_ONCE(gpu_addr < 0))
> - return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */
> + iosys_map_incr(&dst[0],
> + drm_fb_clip_offset(fb->pitches[0], fb->format, &damage));
> + drm_fb_memcpy(dst, fb->pitches, shadow_plane_state->data, fb, &damage);
[Severity: Critical]
Could this overflow the priv->vram I/O memory mapping?
With the transition from gem-vram to gem-shmem, the driver no longer
implicitly restricts the GEM object size to the physical VRAM size. If
userspace provides a framebuffer with a pitch that exceeds what fits in
priv->vram_size, it appears this drm_fb_memcpy() operation will write past
the end of priv->vram.
Should there be a bounds check on the pitch during the atomic check phase
or during framebuffer creation to ensure the memory footprint fits within
priv->vram_size?
> + }
> +
> + drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE);
> + }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260618123142.92298-1-tzimmermann@suse.de?part=6
^ permalink raw reply [flat|nested] 10+ messages in thread
* Re: [PATCH v4 1/6] drm/hibmc: Use drm_atomic_helper_check_plane_state()
2026-06-18 12:28 ` [PATCH v4 1/6] drm/hibmc: Use drm_atomic_helper_check_plane_state() Thomas Zimmermann
@ 2026-06-18 12:48 ` sashiko-bot
0 siblings, 0 replies; 10+ messages in thread
From: sashiko-bot @ 2026-06-18 12:48 UTC (permalink / raw)
To: Thomas Zimmermann; +Cc: dri-devel
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Relaxing plane bounds checking allows configurations that the hardware programming function (`hibmc_plane_atomic_update`) does not support, causing the plane to be rendered incorrectly.
--
commit 4786b7e1e5ba6fbcc8a7b196d600f9e14eb06bb6
Author: Thomas Zimmermann <tzimmermann@suse.de>
drm/hibmc: Use drm_atomic_helper_check_plane_state()
This commit replaces custom plane boundary checks with the shared
drm_atomic_helper_check_plane_state() helper.
> diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> index 3066dc9ebc647..7c0b88c774b5e 100644
> --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
> @@ -72,46 +72,28 @@ static int hibmc_get_best_clock_idx(const struct drm_display_mode *mode)
> static int hibmc_plane_atomic_check(struct drm_plane *plane,
> struct drm_atomic_commit *state)
> {
[ ... ]
> + ret = drm_atomic_helper_check_plane_state(new_plane_state, new_crtc_state,
> + DRM_PLANE_NO_SCALING,
> + DRM_PLANE_NO_SCALING,
> + false, true);
> + if (ret)
> + return ret;
> + else if (!new_plane_state->visible)
> + return 0;
[Severity: High]
Does this introduce a mismatch with the hardware update logic?
The atomic helper permits planes larger than the CRTC by adjusting the source
offsets (src_x and src_y), and also permits completely off-screen planes by
setting visible to false.
However, looking at hibmc_plane_atomic_update(), it appears the hardware
programming function unconditionally scans out from the base address of the
framebuffer. It does not seem to check if the plane is visible to skip
programming, nor does it appear to account for src_x and src_y offsets.
If userspace submits an off-screen plane or a plane with a panning offset,
will the hardware incorrectly scan out the unshifted framebuffer, causing
display corruption?
> if (new_plane_state->fb->pitches[0] % 128 != 0) {
> drm_dbg_atomic(plane->dev, "wrong stride with 128-byte aligned\n");
> return -EINVAL;
> }
> +
> return 0;
> }
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260618123142.92298-1-tzimmermann@suse.de?part=1
^ permalink raw reply [flat|nested] 10+ messages in thread
end of thread, other threads:[~2026-06-18 12:48 UTC | newest]
Thread overview: 10+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-18 12:28 [PATCH v4 0/6] drm/hibmc: Fix plane helpers and convert to gem-shmem Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 1/6] drm/hibmc: Use drm_atomic_helper_check_plane_state() Thomas Zimmermann
2026-06-18 12:48 ` sashiko-bot
2026-06-18 12:28 ` [PATCH v4 2/6] drm/hibmc: Fix list of formats on the primary plane Thomas Zimmermann
2026-06-18 12:43 ` sashiko-bot
2026-06-18 12:28 ` [PATCH v4 3/6] drm/hibmc: Store fb in variable in atomic_update Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 4/6] drm/hibmc: Do not use cpp from struct drm_format_info Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 5/6] drm/hibmc: Verify the framebuffer pitch to be a multiple of 128 Thomas Zimmermann
2026-06-18 12:28 ` [PATCH v4 6/6] drm/hibmc: Use gem-shmem with shadow-plane helpers for memory management Thomas Zimmermann
2026-06-18 12:43 ` sashiko-bot
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.