January 2025 - Linux-stable-mirror

[PATCH AUTOSEL 5.10 1/3] printk: Fix signed integer overflow when defining LOG_BUF_LEN_MAX

by Sasha Levin

From: Kuan-Wei Chiu <visitorckw(a)gmail.com> [ Upstream commit 3d6f83df8ff2d5de84b50377e4f0d45e25311c7a ] Shifting 1 << 31 on a 32-bit int causes signed integer overflow, which leads to undefined behavior. To prevent this, cast 1 to u32 before performing the shift, ensuring well-defined behavior. This change explicitly avoids any potential overflow by ensuring that the shift occurs on an unsigned 32-bit integer. Signed-off-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> Acked-by: Petr Mladek <pmladek(a)suse.com> Link: https://lore.kernel.org/r/20240928113608.1438087-1-visitorckw@gmail.com Signed-off-by: Petr Mladek <pmladek(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/printk/printk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a8af93cbc2936..3a7fd61c0e7be 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -420,7 +420,7 @@ static u64 clear_seq; /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) -#define LOG_BUF_LEN_MAX (u32)(1 << 31) +#define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; -- 2.39.5

4 months, 1 week

1
2
0 0

[PATCH AUTOSEL 5.15 1/3] printk: Fix signed integer overflow when defining LOG_BUF_LEN_MAX

by Sasha Levin

From: Kuan-Wei Chiu <visitorckw(a)gmail.com> [ Upstream commit 3d6f83df8ff2d5de84b50377e4f0d45e25311c7a ] Shifting 1 << 31 on a 32-bit int causes signed integer overflow, which leads to undefined behavior. To prevent this, cast 1 to u32 before performing the shift, ensuring well-defined behavior. This change explicitly avoids any potential overflow by ensuring that the shift occurs on an unsigned 32-bit integer. Signed-off-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> Acked-by: Petr Mladek <pmladek(a)suse.com> Link: https://lore.kernel.org/r/20240928113608.1438087-1-visitorckw@gmail.com Signed-off-by: Petr Mladek <pmladek(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/printk/printk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 5e81d2a79d5cc..113990f38436e 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -403,7 +403,7 @@ static struct latched_seq clear_seq = { /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) -#define LOG_BUF_LEN_MAX (u32)(1 << 31) +#define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; -- 2.39.5

4 months, 1 week

1
2
0 0

[PATCH AUTOSEL 6.1 1/9] drm/virtio: New fence for every plane update

by Sasha Levin

From: Dongwon Kim <dongwon.kim(a)intel.com> [ Upstream commit d3c55b8ab6fe5fa2e7ab02efd36d09c39ee5022f ] Having a fence linked to a virtio_gpu_framebuffer in the plane update sequence would cause conflict when several planes referencing the same framebuffer (e.g. Xorg screen covering multi-displays configured for an extended mode) and those planes are updated concurrently. So it is needed to allocate a fence for every plane state instead of the framebuffer. Signed-off-by: Dongwon Kim <dongwon.kim(a)intel.com> [dmitry.osipenko(a)collabora.com: rebase, fix up, edit commit message] Signed-off-by: Dmitry Osipenko <dmitry.osipenko(a)collabora.com> Acked-by: Vivek Kasireddy <vivek.kasireddy(a)intel.com> Reviewed-by: Rob Clark <robdclark(a)gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20241020230803.247419-2-dmitr… Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 7 ++++ drivers/gpu/drm/virtio/virtgpu_plane.c | 58 +++++++++++++++++--------- 2 files changed, 46 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 9b98470593b06..20a418f64533b 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -190,6 +190,13 @@ struct virtio_gpu_framebuffer { #define to_virtio_gpu_framebuffer(x) \ container_of(x, struct virtio_gpu_framebuffer, base) +struct virtio_gpu_plane_state { + struct drm_plane_state base; + struct virtio_gpu_fence *fence; +}; +#define to_virtio_gpu_plane_state(x) \ + container_of(x, struct virtio_gpu_plane_state, base) + struct virtio_gpu_queue { struct virtqueue *vq; spinlock_t qlock; diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index 4c09e313bebcd..0c073ba4974fb 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -66,11 +66,28 @@ uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc) return format; } +static struct +drm_plane_state *virtio_gpu_plane_duplicate_state(struct drm_plane *plane) +{ + struct virtio_gpu_plane_state *new; + + if (WARN_ON(!plane->state)) + return NULL; + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NULL; + + __drm_atomic_helper_plane_duplicate_state(plane, &new->base); + + return &new->base; +} + static const struct drm_plane_funcs virtio_gpu_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .reset = drm_atomic_helper_plane_reset, - .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, + .atomic_duplicate_state = virtio_gpu_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, }; @@ -128,11 +145,13 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo; vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgplane_st = to_virtio_gpu_plane_state(plane->state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); - if (vgfb->fence) { + if (vgplane_st->fence) { struct virtio_gpu_object_array *objs; objs = virtio_gpu_array_alloc(1); @@ -141,13 +160,11 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]); virtio_gpu_array_lock_resv(objs); virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, - width, height, objs, vgfb->fence); + width, height, objs, + vgplane_st->fence); virtio_gpu_notify(vgdev); - - dma_fence_wait_timeout(&vgfb->fence->f, true, + dma_fence_wait_timeout(&vgplane_st->fence->f, true, msecs_to_jiffies(50)); - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; } else { virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, width, height, NULL, NULL); @@ -237,20 +254,23 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo; if (!new_state->fb) return 0; vgfb = to_virtio_gpu_framebuffer(new_state->fb); + vgplane_st = to_virtio_gpu_plane_state(new_state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); if (!bo || (plane->type == DRM_PLANE_TYPE_PRIMARY && !bo->guest_blob)) return 0; - if (bo->dumb && (plane->state->fb != new_state->fb)) { - vgfb->fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context, + if (bo->dumb) { + vgplane_st->fence = virtio_gpu_fence_alloc(vgdev, + vgdev->fence_drv.context, 0); - if (!vgfb->fence) + if (!vgplane_st->fence) return -ENOMEM; } @@ -260,15 +280,15 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *state) { - struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; if (!state->fb) return; - vgfb = to_virtio_gpu_framebuffer(state->fb); - if (vgfb->fence) { - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; + vgplane_st = to_virtio_gpu_plane_state(state); + if (vgplane_st->fence) { + dma_fence_put(&vgplane_st->fence->f); + vgplane_st->fence = NULL; } } @@ -281,6 +301,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_output *output = NULL; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo = NULL; uint32_t handle; @@ -293,6 +314,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, if (plane->state->fb) { vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgplane_st = to_virtio_gpu_plane_state(plane->state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); handle = bo->hw_res_handle; } else { @@ -312,11 +334,9 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, (vgdev, 0, plane->state->crtc_w, plane->state->crtc_h, - 0, 0, objs, vgfb->fence); + 0, 0, objs, vgplane_st->fence); virtio_gpu_notify(vgdev); - dma_fence_wait(&vgfb->fence->f, true); - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; + dma_fence_wait(&vgplane_st->fence->f, true); } if (plane->state->fb != old_state->fb) { -- 2.39.5

4 months, 1 week

1
8
0 0

[PATCH AUTOSEL 6.6 01/17] drm/virtio: New fence for every plane update

by Sasha Levin

From: Dongwon Kim <dongwon.kim(a)intel.com> [ Upstream commit d3c55b8ab6fe5fa2e7ab02efd36d09c39ee5022f ] Having a fence linked to a virtio_gpu_framebuffer in the plane update sequence would cause conflict when several planes referencing the same framebuffer (e.g. Xorg screen covering multi-displays configured for an extended mode) and those planes are updated concurrently. So it is needed to allocate a fence for every plane state instead of the framebuffer. Signed-off-by: Dongwon Kim <dongwon.kim(a)intel.com> [dmitry.osipenko(a)collabora.com: rebase, fix up, edit commit message] Signed-off-by: Dmitry Osipenko <dmitry.osipenko(a)collabora.com> Acked-by: Vivek Kasireddy <vivek.kasireddy(a)intel.com> Reviewed-by: Rob Clark <robdclark(a)gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20241020230803.247419-2-dmitr… Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 7 ++++ drivers/gpu/drm/virtio/virtgpu_plane.c | 58 +++++++++++++++++--------- 2 files changed, 46 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 4126c384286bf..61fd37f95fbd9 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -191,6 +191,13 @@ struct virtio_gpu_framebuffer { #define to_virtio_gpu_framebuffer(x) \ container_of(x, struct virtio_gpu_framebuffer, base) +struct virtio_gpu_plane_state { + struct drm_plane_state base; + struct virtio_gpu_fence *fence; +}; +#define to_virtio_gpu_plane_state(x) \ + container_of(x, struct virtio_gpu_plane_state, base) + struct virtio_gpu_queue { struct virtqueue *vq; spinlock_t qlock; diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index a1ef657eba077..36de73e03bbfa 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -66,11 +66,28 @@ uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc) return format; } +static struct +drm_plane_state *virtio_gpu_plane_duplicate_state(struct drm_plane *plane) +{ + struct virtio_gpu_plane_state *new; + + if (WARN_ON(!plane->state)) + return NULL; + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NULL; + + __drm_atomic_helper_plane_duplicate_state(plane, &new->base); + + return &new->base; +} + static const struct drm_plane_funcs virtio_gpu_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .reset = drm_atomic_helper_plane_reset, - .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, + .atomic_duplicate_state = virtio_gpu_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, }; @@ -138,11 +155,13 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo; vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgplane_st = to_virtio_gpu_plane_state(plane->state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); - if (vgfb->fence) { + if (vgplane_st->fence) { struct virtio_gpu_object_array *objs; objs = virtio_gpu_array_alloc(1); @@ -151,13 +170,11 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]); virtio_gpu_array_lock_resv(objs); virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, - width, height, objs, vgfb->fence); + width, height, objs, + vgplane_st->fence); virtio_gpu_notify(vgdev); - - dma_fence_wait_timeout(&vgfb->fence->f, true, + dma_fence_wait_timeout(&vgplane_st->fence->f, true, msecs_to_jiffies(50)); - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; } else { virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, width, height, NULL, NULL); @@ -247,20 +264,23 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo; if (!new_state->fb) return 0; vgfb = to_virtio_gpu_framebuffer(new_state->fb); + vgplane_st = to_virtio_gpu_plane_state(new_state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); if (!bo || (plane->type == DRM_PLANE_TYPE_PRIMARY && !bo->guest_blob)) return 0; - if (bo->dumb && (plane->state->fb != new_state->fb)) { - vgfb->fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context, + if (bo->dumb) { + vgplane_st->fence = virtio_gpu_fence_alloc(vgdev, + vgdev->fence_drv.context, 0); - if (!vgfb->fence) + if (!vgplane_st->fence) return -ENOMEM; } @@ -270,15 +290,15 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *state) { - struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; if (!state->fb) return; - vgfb = to_virtio_gpu_framebuffer(state->fb); - if (vgfb->fence) { - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; + vgplane_st = to_virtio_gpu_plane_state(state); + if (vgplane_st->fence) { + dma_fence_put(&vgplane_st->fence->f); + vgplane_st->fence = NULL; } } @@ -291,6 +311,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_output *output = NULL; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo = NULL; uint32_t handle; @@ -303,6 +324,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, if (plane->state->fb) { vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgplane_st = to_virtio_gpu_plane_state(plane->state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); handle = bo->hw_res_handle; } else { @@ -322,11 +344,9 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, (vgdev, 0, plane->state->crtc_w, plane->state->crtc_h, - 0, 0, objs, vgfb->fence); + 0, 0, objs, vgplane_st->fence); virtio_gpu_notify(vgdev); - dma_fence_wait(&vgfb->fence->f, true); - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; + dma_fence_wait(&vgplane_st->fence->f, true); } if (plane->state->fb != old_state->fb) { -- 2.39.5

4 months, 1 week

1
16
0 0

[PATCH AUTOSEL 6.13 01/34] drm/virtio: New fence for every plane update

by Sasha Levin

From: Dongwon Kim <dongwon.kim(a)intel.com> [ Upstream commit d3c55b8ab6fe5fa2e7ab02efd36d09c39ee5022f ] Having a fence linked to a virtio_gpu_framebuffer in the plane update sequence would cause conflict when several planes referencing the same framebuffer (e.g. Xorg screen covering multi-displays configured for an extended mode) and those planes are updated concurrently. So it is needed to allocate a fence for every plane state instead of the framebuffer. Signed-off-by: Dongwon Kim <dongwon.kim(a)intel.com> [dmitry.osipenko(a)collabora.com: rebase, fix up, edit commit message] Signed-off-by: Dmitry Osipenko <dmitry.osipenko(a)collabora.com> Acked-by: Vivek Kasireddy <vivek.kasireddy(a)intel.com> Reviewed-by: Rob Clark <robdclark(a)gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20241020230803.247419-2-dmitr… Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 7 ++++ drivers/gpu/drm/virtio/virtgpu_plane.c | 58 +++++++++++++++++--------- 2 files changed, 46 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 64c236169db88..5dc8eeaf7123c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -194,6 +194,13 @@ struct virtio_gpu_framebuffer { #define to_virtio_gpu_framebuffer(x) \ container_of(x, struct virtio_gpu_framebuffer, base) +struct virtio_gpu_plane_state { + struct drm_plane_state base; + struct virtio_gpu_fence *fence; +}; +#define to_virtio_gpu_plane_state(x) \ + container_of(x, struct virtio_gpu_plane_state, base) + struct virtio_gpu_queue { struct virtqueue *vq; spinlock_t qlock; diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index a72a2dbda031c..7acd38b962c62 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -66,11 +66,28 @@ uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc) return format; } +static struct +drm_plane_state *virtio_gpu_plane_duplicate_state(struct drm_plane *plane) +{ + struct virtio_gpu_plane_state *new; + + if (WARN_ON(!plane->state)) + return NULL; + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NULL; + + __drm_atomic_helper_plane_duplicate_state(plane, &new->base); + + return &new->base; +} + static const struct drm_plane_funcs virtio_gpu_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .reset = drm_atomic_helper_plane_reset, - .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, + .atomic_duplicate_state = virtio_gpu_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, }; @@ -138,11 +155,13 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo; vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgplane_st = to_virtio_gpu_plane_state(plane->state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); - if (vgfb->fence) { + if (vgplane_st->fence) { struct virtio_gpu_object_array *objs; objs = virtio_gpu_array_alloc(1); @@ -151,13 +170,11 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]); virtio_gpu_array_lock_resv(objs); virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, - width, height, objs, vgfb->fence); + width, height, objs, + vgplane_st->fence); virtio_gpu_notify(vgdev); - - dma_fence_wait_timeout(&vgfb->fence->f, true, + dma_fence_wait_timeout(&vgplane_st->fence->f, true, msecs_to_jiffies(50)); - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; } else { virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, width, height, NULL, NULL); @@ -247,20 +264,23 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo; if (!new_state->fb) return 0; vgfb = to_virtio_gpu_framebuffer(new_state->fb); + vgplane_st = to_virtio_gpu_plane_state(new_state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); if (!bo || (plane->type == DRM_PLANE_TYPE_PRIMARY && !bo->guest_blob)) return 0; - if (bo->dumb && (plane->state->fb != new_state->fb)) { - vgfb->fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context, + if (bo->dumb) { + vgplane_st->fence = virtio_gpu_fence_alloc(vgdev, + vgdev->fence_drv.context, 0); - if (!vgfb->fence) + if (!vgplane_st->fence) return -ENOMEM; } @@ -270,15 +290,15 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *state) { - struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; if (!state->fb) return; - vgfb = to_virtio_gpu_framebuffer(state->fb); - if (vgfb->fence) { - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; + vgplane_st = to_virtio_gpu_plane_state(state); + if (vgplane_st->fence) { + dma_fence_put(&vgplane_st->fence->f); + vgplane_st->fence = NULL; } } @@ -291,6 +311,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_output *output = NULL; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo = NULL; uint32_t handle; @@ -303,6 +324,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, if (plane->state->fb) { vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgplane_st = to_virtio_gpu_plane_state(plane->state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); handle = bo->hw_res_handle; } else { @@ -322,11 +344,9 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, (vgdev, 0, plane->state->crtc_w, plane->state->crtc_h, - 0, 0, objs, vgfb->fence); + 0, 0, objs, vgplane_st->fence); virtio_gpu_notify(vgdev); - dma_fence_wait(&vgfb->fence->f, true); - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; + dma_fence_wait(&vgplane_st->fence->f, true); } if (plane->state->fb != old_state->fb) { -- 2.39.5

4 months, 1 week

1
33
0 0

[PATCH AUTOSEL 5.4 1/2] sched: Don't try to catch up excess steal time.

by Sasha Levin

From: Suleiman Souhlal <suleiman(a)google.com> [ Upstream commit 108ad0999085df2366dd9ef437573955cb3f5586 ] When steal time exceeds the measured delta when updating clock_task, we currently try to catch up the excess in future updates. However, this results in inaccurate run times for the future things using clock_task, in some situations, as they end up getting additional steal time that did not actually happen. This is because there is a window between reading the elapsed time in update_rq_clock() and sampling the steal time in update_rq_clock_task(). If the VCPU gets preempted between those two points, any additional steal time is accounted to the outgoing task even though the calculated delta did not actually contain any of that "stolen" time. When this race happens, we can end up with steal time that exceeds the calculated delta, and the previous code would try to catch up that excess steal time in future clock updates, which is given to the next, incoming task, even though it did not actually have any time stolen. This behavior is particularly bad when steal time can be very long, which we've seen when trying to extend steal time to contain the duration that the host was suspended [0]. When this happens, clock_task stays frozen, during which the running task stays running for the whole duration, since its run time doesn't increase. However the race can happen even under normal operation. Ideally we would read the elapsed cpu time and the steal time atomically, to prevent this race from happening in the first place, but doing so is non-trivial. Since the time between those two points isn't otherwise accounted anywhere, neither to the outgoing task nor the incoming task (because the "end of outgoing task" and "start of incoming task" timestamps are the same), I would argue that the right thing to do is to simply drop any excess steal time, in order to prevent these issues. [0] https://lore.kernel.org/kvm/20240820043543.837914-1-suleiman@google.com/ Signed-off-by: Suleiman Souhlal <suleiman(a)google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lore.kernel.org/r/20241118043745.1857272-1-suleiman@google.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/sched/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 51ac62637e4ed..39ce8a3d8c573 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -176,13 +176,15 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((&paravirt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); + u64 prev_steal; + + steal = prev_steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - rq->prev_steal_time_rq += steal; + rq->prev_steal_time_rq = prev_steal; delta -= steal; } #endif -- 2.39.5

4 months, 1 week

1
1
0 0

[PATCH AUTOSEL 5.10 1/3] sched: Don't try to catch up excess steal time.

by Sasha Levin

From: Suleiman Souhlal <suleiman(a)google.com> [ Upstream commit 108ad0999085df2366dd9ef437573955cb3f5586 ] When steal time exceeds the measured delta when updating clock_task, we currently try to catch up the excess in future updates. However, this results in inaccurate run times for the future things using clock_task, in some situations, as they end up getting additional steal time that did not actually happen. This is because there is a window between reading the elapsed time in update_rq_clock() and sampling the steal time in update_rq_clock_task(). If the VCPU gets preempted between those two points, any additional steal time is accounted to the outgoing task even though the calculated delta did not actually contain any of that "stolen" time. When this race happens, we can end up with steal time that exceeds the calculated delta, and the previous code would try to catch up that excess steal time in future clock updates, which is given to the next, incoming task, even though it did not actually have any time stolen. This behavior is particularly bad when steal time can be very long, which we've seen when trying to extend steal time to contain the duration that the host was suspended [0]. When this happens, clock_task stays frozen, during which the running task stays running for the whole duration, since its run time doesn't increase. However the race can happen even under normal operation. Ideally we would read the elapsed cpu time and the steal time atomically, to prevent this race from happening in the first place, but doing so is non-trivial. Since the time between those two points isn't otherwise accounted anywhere, neither to the outgoing task nor the incoming task (because the "end of outgoing task" and "start of incoming task" timestamps are the same), I would argue that the right thing to do is to simply drop any excess steal time, in order to prevent these issues. [0] https://lore.kernel.org/kvm/20240820043543.837914-1-suleiman@google.com/ Signed-off-by: Suleiman Souhlal <suleiman(a)google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lore.kernel.org/r/20241118043745.1857272-1-suleiman@google.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/sched/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7cf45d506688c..42dad8c8d6f28 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -279,13 +279,15 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((&paravirt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); + u64 prev_steal; + + steal = prev_steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - rq->prev_steal_time_rq += steal; + rq->prev_steal_time_rq = prev_steal; delta -= steal; } #endif -- 2.39.5

4 months, 1 week

1
2
0 0

[PATCH AUTOSEL 5.15 1/3] sched: Don't try to catch up excess steal time.

by Sasha Levin

From: Suleiman Souhlal <suleiman(a)google.com> [ Upstream commit 108ad0999085df2366dd9ef437573955cb3f5586 ] When steal time exceeds the measured delta when updating clock_task, we currently try to catch up the excess in future updates. However, this results in inaccurate run times for the future things using clock_task, in some situations, as they end up getting additional steal time that did not actually happen. This is because there is a window between reading the elapsed time in update_rq_clock() and sampling the steal time in update_rq_clock_task(). If the VCPU gets preempted between those two points, any additional steal time is accounted to the outgoing task even though the calculated delta did not actually contain any of that "stolen" time. When this race happens, we can end up with steal time that exceeds the calculated delta, and the previous code would try to catch up that excess steal time in future clock updates, which is given to the next, incoming task, even though it did not actually have any time stolen. This behavior is particularly bad when steal time can be very long, which we've seen when trying to extend steal time to contain the duration that the host was suspended [0]. When this happens, clock_task stays frozen, during which the running task stays running for the whole duration, since its run time doesn't increase. However the race can happen even under normal operation. Ideally we would read the elapsed cpu time and the steal time atomically, to prevent this race from happening in the first place, but doing so is non-trivial. Since the time between those two points isn't otherwise accounted anywhere, neither to the outgoing task nor the incoming task (because the "end of outgoing task" and "start of incoming task" timestamps are the same), I would argue that the right thing to do is to simply drop any excess steal time, in order to prevent these issues. [0] https://lore.kernel.org/kvm/20240820043543.837914-1-suleiman@google.com/ Signed-off-by: Suleiman Souhlal <suleiman(a)google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lore.kernel.org/r/20241118043745.1857272-1-suleiman@google.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/sched/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ed92b75f7e024..691af58c156e1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -642,13 +642,15 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((&paravirt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); + u64 prev_steal; + + steal = prev_steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - rq->prev_steal_time_rq += steal; + rq->prev_steal_time_rq = prev_steal; delta -= steal; } #endif -- 2.39.5

4 months, 1 week

1
2
0 0

[PATCH AUTOSEL 6.1 1/3] sched: Don't try to catch up excess steal time.

by Sasha Levin

From: Suleiman Souhlal <suleiman(a)google.com> [ Upstream commit 108ad0999085df2366dd9ef437573955cb3f5586 ] When steal time exceeds the measured delta when updating clock_task, we currently try to catch up the excess in future updates. However, this results in inaccurate run times for the future things using clock_task, in some situations, as they end up getting additional steal time that did not actually happen. This is because there is a window between reading the elapsed time in update_rq_clock() and sampling the steal time in update_rq_clock_task(). If the VCPU gets preempted between those two points, any additional steal time is accounted to the outgoing task even though the calculated delta did not actually contain any of that "stolen" time. When this race happens, we can end up with steal time that exceeds the calculated delta, and the previous code would try to catch up that excess steal time in future clock updates, which is given to the next, incoming task, even though it did not actually have any time stolen. This behavior is particularly bad when steal time can be very long, which we've seen when trying to extend steal time to contain the duration that the host was suspended [0]. When this happens, clock_task stays frozen, during which the running task stays running for the whole duration, since its run time doesn't increase. However the race can happen even under normal operation. Ideally we would read the elapsed cpu time and the steal time atomically, to prevent this race from happening in the first place, but doing so is non-trivial. Since the time between those two points isn't otherwise accounted anywhere, neither to the outgoing task nor the incoming task (because the "end of outgoing task" and "start of incoming task" timestamps are the same), I would argue that the right thing to do is to simply drop any excess steal time, in order to prevent these issues. [0] https://lore.kernel.org/kvm/20240820043543.837914-1-suleiman@google.com/ Signed-off-by: Suleiman Souhlal <suleiman(a)google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lore.kernel.org/r/20241118043745.1857272-1-suleiman@google.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/sched/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 54af671e8d510..3927904984fd5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -704,13 +704,15 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((&paravirt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); + u64 prev_steal; + + steal = prev_steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - rq->prev_steal_time_rq += steal; + rq->prev_steal_time_rq = prev_steal; delta -= steal; } #endif -- 2.39.5

4 months, 1 week

1
2
0 0

[PATCH AUTOSEL 6.6 1/3] sched: Don't try to catch up excess steal time.

by Sasha Levin

From: Suleiman Souhlal <suleiman(a)google.com> [ Upstream commit 108ad0999085df2366dd9ef437573955cb3f5586 ] When steal time exceeds the measured delta when updating clock_task, we currently try to catch up the excess in future updates. However, this results in inaccurate run times for the future things using clock_task, in some situations, as they end up getting additional steal time that did not actually happen. This is because there is a window between reading the elapsed time in update_rq_clock() and sampling the steal time in update_rq_clock_task(). If the VCPU gets preempted between those two points, any additional steal time is accounted to the outgoing task even though the calculated delta did not actually contain any of that "stolen" time. When this race happens, we can end up with steal time that exceeds the calculated delta, and the previous code would try to catch up that excess steal time in future clock updates, which is given to the next, incoming task, even though it did not actually have any time stolen. This behavior is particularly bad when steal time can be very long, which we've seen when trying to extend steal time to contain the duration that the host was suspended [0]. When this happens, clock_task stays frozen, during which the running task stays running for the whole duration, since its run time doesn't increase. However the race can happen even under normal operation. Ideally we would read the elapsed cpu time and the steal time atomically, to prevent this race from happening in the first place, but doing so is non-trivial. Since the time between those two points isn't otherwise accounted anywhere, neither to the outgoing task nor the incoming task (because the "end of outgoing task" and "start of incoming task" timestamps are the same), I would argue that the right thing to do is to simply drop any excess steal time, in order to prevent these issues. [0] https://lore.kernel.org/kvm/20240820043543.837914-1-suleiman@google.com/ Signed-off-by: Suleiman Souhlal <suleiman(a)google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lore.kernel.org/r/20241118043745.1857272-1-suleiman@google.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- kernel/sched/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 86606fb9e6bc6..c686d826a91cf 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -726,13 +726,15 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((&paravirt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); + u64 prev_steal; + + steal = prev_steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - rq->prev_steal_time_rq += steal; + rq->prev_steal_time_rq = prev_steal; delta -= steal; } #endif -- 2.39.5

4 months, 1 week

1
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2025