diff options
Diffstat (limited to 'drivers/gpu/drm/gud')
| -rw-r--r-- | drivers/gpu/drm/gud/gud_drv.c | 61 | ||||
| -rw-r--r-- | drivers/gpu/drm/gud/gud_internal.h | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/gud/gud_pipe.c | 86 |
3 files changed, 110 insertions, 39 deletions
diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index e8b672dc9832..eb4e08846da4 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -364,7 +364,6 @@ static void gud_debugfs_init(struct drm_minor *minor) static const struct drm_simple_display_pipe_funcs gud_pipe_funcs = { .check = gud_pipe_check, .update = gud_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct drm_mode_config_funcs gud_mode_config_funcs = { @@ -394,14 +393,42 @@ static const struct drm_driver gud_drm_driver = { .minor = 0, }; -static void gud_free_buffers_and_mutex(struct drm_device *drm, void *unused) +static int gud_alloc_bulk_buffer(struct gud_device *gdrm) { - struct gud_device *gdrm = to_gud_device(drm); + unsigned int i, num_pages; + struct page **pages; + void *ptr; + int ret; + + gdrm->bulk_buf = vmalloc_32(gdrm->bulk_len); + if (!gdrm->bulk_buf) + return -ENOMEM; + + num_pages = DIV_ROUND_UP(gdrm->bulk_len, PAGE_SIZE); + pages = kmalloc_array(num_pages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + for (i = 0, ptr = gdrm->bulk_buf; i < num_pages; i++, ptr += PAGE_SIZE) + pages[i] = vmalloc_to_page(ptr); + + ret = sg_alloc_table_from_pages(&gdrm->bulk_sgt, pages, num_pages, + 0, gdrm->bulk_len, GFP_KERNEL); + kfree(pages); + + return ret; +} + +static void gud_free_buffers_and_mutex(void *data) +{ + struct gud_device *gdrm = data; vfree(gdrm->compress_buf); - kfree(gdrm->bulk_buf); + gdrm->compress_buf = NULL; + sg_free_table(&gdrm->bulk_sgt); + vfree(gdrm->bulk_buf); + gdrm->bulk_buf = NULL; mutex_destroy(&gdrm->ctrl_lock); - mutex_destroy(&gdrm->damage_lock); } static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) @@ -455,7 +482,7 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) INIT_WORK(&gdrm->work, gud_flush_work); gud_clear_damage(gdrm); - ret = drmm_add_action_or_reset(drm, gud_free_buffers_and_mutex, NULL); + ret = devm_add_action(dev, gud_free_buffers_and_mutex, gdrm); if (ret) return ret; @@ -536,24 +563,17 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) if (desc.max_buffer_size) max_buffer_size = le32_to_cpu(desc.max_buffer_size); -retry: - /* - * Use plain kmalloc here since devm_kmalloc() places struct devres at the beginning - * of the buffer it allocates. This wastes a lot of memory when allocating big buffers. - * Asking for 2M would actually allocate 4M. This would also prevent getting the biggest - * possible buffer potentially leading to split transfers. - */ - gdrm->bulk_buf = kmalloc(max_buffer_size, GFP_KERNEL | __GFP_NOWARN); - if (!gdrm->bulk_buf) { - max_buffer_size = roundup_pow_of_two(max_buffer_size) / 2; - if (max_buffer_size < SZ_512K) - return -ENOMEM; - goto retry; - } + /* Prevent a misbehaving device from allocating loads of RAM. 4096x4096@XRGB8888 = 64 MB */ + if (max_buffer_size > SZ_64M) + max_buffer_size = SZ_64M; gdrm->bulk_pipe = usb_sndbulkpipe(interface_to_usbdev(intf), usb_endpoint_num(bulk_out)); gdrm->bulk_len = max_buffer_size; + ret = gud_alloc_bulk_buffer(gdrm); + if (ret) + return ret; + if (gdrm->compression & GUD_COMPRESSION_LZ4) { gdrm->lz4_comp_mem = devm_kmalloc(dev, LZ4_MEM_COMPRESS, GFP_KERNEL); if (!gdrm->lz4_comp_mem) @@ -640,6 +660,7 @@ static int gud_resume(struct usb_interface *intf) static const struct usb_device_id gud_id_table[] = { { USB_DEVICE_INTERFACE_CLASS(0x1d50, 0x614d, USB_CLASS_VENDOR_SPEC) }, + { USB_DEVICE_INTERFACE_CLASS(0x16d0, 0x10a9, USB_CLASS_VENDOR_SPEC) }, { } }; diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index b65105585578..2a388e27d5d7 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -5,6 +5,7 @@ #include <linux/list.h> #include <linux/mutex.h> +#include <linux/scatterlist.h> #include <linux/usb.h> #include <linux/workqueue.h> #include <uapi/drm/drm_fourcc.h> @@ -26,6 +27,7 @@ struct gud_device { unsigned int bulk_pipe; void *bulk_buf; size_t bulk_len; + struct sg_table bulk_sgt; u8 compression; void *lz4_comp_mem; diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 2f83ab6b8e61..b9b0e435ea0f 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -3,7 +3,6 @@ * Copyright 2020 Noralf Trønnes */ -#include <linux/dma-buf.h> #include <linux/lz4.h> #include <linux/usb.h> #include <linux/workqueue.h> @@ -15,7 +14,8 @@ #include <drm/drm_format_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> -#include <drm/drm_gem_shmem_helper.h> +#include <drm/drm_gem.h> +#include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_print.h> #include <drm/drm_rect.h> #include <drm/drm_simple_kms_helper.h> @@ -24,6 +24,19 @@ #include "gud_internal.h" /* + * Some userspace rendering loops runs all displays in the same loop. + * This means that a fast display will have to wait for a slow one. + * For this reason gud does flushing asynchronous by default. + * The down side is that in e.g. a single display setup userspace thinks + * the display is insanely fast since the driver reports back immediately + * that the flush/pageflip is done. This wastes CPU and power. + * Such users might want to set this module parameter to false. + */ +static bool gud_async_flush = true; +module_param_named(async_flush, gud_async_flush, bool, 0644); +MODULE_PARM_DESC(async_flush, "Enable asynchronous flushing [default=true]"); + +/* * FIXME: The driver is probably broken on Big Endian machines. * See discussion: * https://lore.kernel.org/dri-devel/CAKb7UvihLX0hgBOP3VBG7O+atwZcUVCPVuBdfmDMpg0NjXe-cQ@mail.gmail.com/ @@ -139,7 +152,8 @@ static int gud_prep_flush(struct gud_device *gdrm, struct drm_framebuffer *fb, { struct dma_buf_attachment *import_attach = fb->obj[0]->import_attach; u8 compression = gdrm->compression; - struct dma_buf_map map; + struct dma_buf_map map[DRM_FORMAT_MAX_PLANES]; + struct dma_buf_map map_data[DRM_FORMAT_MAX_PLANES]; void *vaddr, *buf; size_t pitch, len; int ret = 0; @@ -149,17 +163,15 @@ static int gud_prep_flush(struct gud_device *gdrm, struct drm_framebuffer *fb, if (len > gdrm->bulk_len) return -E2BIG; - ret = drm_gem_shmem_vmap(fb->obj[0], &map); + ret = drm_gem_fb_vmap(fb, map, map_data); if (ret) return ret; - vaddr = map.vaddr + fb->offsets[0]; + vaddr = map_data[0].vaddr; - if (import_attach) { - ret = dma_buf_begin_cpu_access(import_attach->dmabuf, DMA_FROM_DEVICE); - if (ret) - goto vunmap; - } + ret = drm_gem_fb_begin_cpu_access(fb, DMA_FROM_DEVICE); + if (ret) + goto vunmap; retry: if (compression) buf = gdrm->compress_buf; @@ -212,10 +224,48 @@ retry: } end_cpu_access: - if (import_attach) - dma_buf_end_cpu_access(import_attach->dmabuf, DMA_FROM_DEVICE); + drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE); vunmap: - drm_gem_shmem_vunmap(fb->obj[0], &map); + drm_gem_fb_vunmap(fb, map); + + return ret; +} + +struct gud_usb_bulk_context { + struct timer_list timer; + struct usb_sg_request sgr; +}; + +static void gud_usb_bulk_timeout(struct timer_list *t) +{ + struct gud_usb_bulk_context *ctx = from_timer(ctx, t, timer); + + usb_sg_cancel(&ctx->sgr); +} + +static int gud_usb_bulk(struct gud_device *gdrm, size_t len) +{ + struct gud_usb_bulk_context ctx; + int ret; + + ret = usb_sg_init(&ctx.sgr, gud_to_usb_device(gdrm), gdrm->bulk_pipe, 0, + gdrm->bulk_sgt.sgl, gdrm->bulk_sgt.nents, len, GFP_KERNEL); + if (ret) + return ret; + + timer_setup_on_stack(&ctx.timer, gud_usb_bulk_timeout, 0); + mod_timer(&ctx.timer, jiffies + msecs_to_jiffies(3000)); + + usb_sg_wait(&ctx.sgr); + + if (!del_timer_sync(&ctx.timer)) + ret = -ETIMEDOUT; + else if (ctx.sgr.status < 0) + ret = ctx.sgr.status; + else if (ctx.sgr.bytes != len) + ret = -EIO; + + destroy_timer_on_stack(&ctx.timer); return ret; } @@ -223,10 +273,9 @@ vunmap: static int gud_flush_rect(struct gud_device *gdrm, struct drm_framebuffer *fb, const struct drm_format_info *format, struct drm_rect *rect) { - struct usb_device *usb = gud_to_usb_device(gdrm); struct gud_set_buffer_req req; - int ret, actual_length; size_t len, trlen; + int ret; drm_dbg(&gdrm->drm, "Flushing [FB:%d] " DRM_RECT_FMT "\n", fb->base.id, DRM_RECT_ARG(rect)); @@ -255,10 +304,7 @@ static int gud_flush_rect(struct gud_device *gdrm, struct drm_framebuffer *fb, return ret; } - ret = usb_bulk_msg(usb, gdrm->bulk_pipe, gdrm->bulk_buf, trlen, - &actual_length, msecs_to_jiffies(3000)); - if (!ret && trlen != actual_length) - ret = -EIO; + ret = gud_usb_bulk(gdrm, trlen); if (ret) gdrm->stats_num_errors++; @@ -543,6 +589,8 @@ void gud_pipe_update(struct drm_simple_display_pipe *pipe, if (gdrm->flags & GUD_DISPLAY_FLAG_FULL_UPDATE) drm_rect_init(&damage, 0, 0, fb->width, fb->height); gud_fb_queue_damage(gdrm, fb, &damage); + if (!gud_async_flush) + flush_work(&gdrm->work); } if (!crtc->state->enable) |