diff options
Diffstat (limited to 'drivers/staging/media/tegra-vde')
| -rw-r--r-- | drivers/staging/media/tegra-vde/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/staging/media/tegra-vde/Makefile | 1 | ||||
| -rw-r--r-- | drivers/staging/media/tegra-vde/dmabuf-cache.c | 226 | ||||
| -rw-r--r-- | drivers/staging/media/tegra-vde/iommu.c | 157 | ||||
| -rw-r--r-- | drivers/staging/media/tegra-vde/trace.h | 2 | ||||
| -rw-r--r-- | drivers/staging/media/tegra-vde/uapi.h | 48 | ||||
| -rw-r--r-- | drivers/staging/media/tegra-vde/vde.c (renamed from drivers/staging/media/tegra-vde/tegra-vde.c) | 212 | ||||
| -rw-r--r-- | drivers/staging/media/tegra-vde/vde.h | 107 |
8 files changed, 591 insertions, 163 deletions
diff --git a/drivers/staging/media/tegra-vde/Kconfig b/drivers/staging/media/tegra-vde/Kconfig index ff8e846cd15d..2e7f644ae591 100644 --- a/drivers/staging/media/tegra-vde/Kconfig +++ b/drivers/staging/media/tegra-vde/Kconfig @@ -3,6 +3,7 @@ config TEGRA_VDE tristate "NVIDIA Tegra Video Decoder Engine driver" depends on ARCH_TEGRA || COMPILE_TEST select DMA_SHARED_BUFFER + select IOMMU_IOVA if IOMMU_SUPPORT select SRAM help Say Y here to enable support for the NVIDIA Tegra video decoder diff --git a/drivers/staging/media/tegra-vde/Makefile b/drivers/staging/media/tegra-vde/Makefile index 7f9020e634f3..2827f7601de8 100644 --- a/drivers/staging/media/tegra-vde/Makefile +++ b/drivers/staging/media/tegra-vde/Makefile @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 +tegra-vde-y := vde.o iommu.o dmabuf-cache.o obj-$(CONFIG_TEGRA_VDE) += tegra-vde.o diff --git a/drivers/staging/media/tegra-vde/dmabuf-cache.c b/drivers/staging/media/tegra-vde/dmabuf-cache.c new file mode 100644 index 000000000000..a93b317885bf --- /dev/null +++ b/drivers/staging/media/tegra-vde/dmabuf-cache.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * NVIDIA Tegra Video decoder driver + * + * Copyright (C) 2016-2019 GRATE-DRIVER project + */ + +#include <linux/dma-buf.h> +#include <linux/iova.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/workqueue.h> + +#include "vde.h" + +struct tegra_vde_cache_entry { + enum dma_data_direction dma_dir; + struct dma_buf_attachment *a; + struct delayed_work dwork; + struct tegra_vde *vde; + struct list_head list; + struct sg_table *sgt; + struct iova *iova; + unsigned int refcnt; +}; + +static void tegra_vde_release_entry(struct tegra_vde_cache_entry *entry) +{ + struct dma_buf *dmabuf = entry->a->dmabuf; + + WARN_ON_ONCE(entry->refcnt); + + if (entry->vde->domain) + tegra_vde_iommu_unmap(entry->vde, entry->iova); + + dma_buf_unmap_attachment(entry->a, entry->sgt, entry->dma_dir); + dma_buf_detach(dmabuf, entry->a); + dma_buf_put(dmabuf); + + list_del(&entry->list); + kfree(entry); +} + +static void tegra_vde_delayed_unmap(struct work_struct *work) +{ + struct tegra_vde_cache_entry *entry; + struct tegra_vde *vde; + + entry = container_of(work, struct tegra_vde_cache_entry, + dwork.work); + vde = entry->vde; + + mutex_lock(&vde->map_lock); + tegra_vde_release_entry(entry); + mutex_unlock(&vde->map_lock); +} + +int tegra_vde_dmabuf_cache_map(struct tegra_vde *vde, + struct dma_buf *dmabuf, + enum dma_data_direction dma_dir, + struct dma_buf_attachment **ap, + dma_addr_t *addrp) +{ + struct device *dev = vde->miscdev.parent; + struct dma_buf_attachment *attachment; + struct tegra_vde_cache_entry *entry; + struct sg_table *sgt; + struct iova *iova; + int err; + + mutex_lock(&vde->map_lock); + + list_for_each_entry(entry, &vde->map_list, list) { + if (entry->a->dmabuf != dmabuf) + continue; + + if (!cancel_delayed_work(&entry->dwork)) + continue; + + if (entry->dma_dir != dma_dir) + entry->dma_dir = DMA_BIDIRECTIONAL; + + dma_buf_put(dmabuf); + + if (vde->domain) + *addrp = iova_dma_addr(&vde->iova, entry->iova); + else + *addrp = sg_dma_address(entry->sgt->sgl); + + goto ref; + } + + attachment = dma_buf_attach(dmabuf, dev); + if (IS_ERR(attachment)) { + dev_err(dev, "Failed to attach dmabuf\n"); + err = PTR_ERR(attachment); + goto err_unlock; + } + + sgt = dma_buf_map_attachment(attachment, dma_dir); + if (IS_ERR(sgt)) { + dev_err(dev, "Failed to get dmabufs sg_table\n"); + err = PTR_ERR(sgt); + goto err_detach; + } + + if (!vde->domain && sgt->nents > 1) { + dev_err(dev, "Sparse DMA region is unsupported, please enable IOMMU\n"); + err = -EINVAL; + goto err_unmap; + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + err = -ENOMEM; + goto err_unmap; + } + + if (vde->domain) { + err = tegra_vde_iommu_map(vde, sgt, &iova, dmabuf->size); + if (err) + goto err_free; + + *addrp = iova_dma_addr(&vde->iova, iova); + } else { + *addrp = sg_dma_address(sgt->sgl); + iova = NULL; + } + + INIT_DELAYED_WORK(&entry->dwork, tegra_vde_delayed_unmap); + list_add(&entry->list, &vde->map_list); + + entry->dma_dir = dma_dir; + entry->iova = iova; + entry->vde = vde; + entry->sgt = sgt; + entry->a = attachment; +ref: + entry->refcnt++; + + *ap = entry->a; + + mutex_unlock(&vde->map_lock); + + return 0; + +err_free: + kfree(entry); +err_unmap: + dma_buf_unmap_attachment(attachment, sgt, dma_dir); +err_detach: + dma_buf_detach(dmabuf, attachment); +err_unlock: + mutex_unlock(&vde->map_lock); + + return err; +} + +void tegra_vde_dmabuf_cache_unmap(struct tegra_vde *vde, + struct dma_buf_attachment *a, + bool release) +{ + struct tegra_vde_cache_entry *entry; + + mutex_lock(&vde->map_lock); + + list_for_each_entry(entry, &vde->map_list, list) { + if (entry->a != a) + continue; + + WARN_ON_ONCE(!entry->refcnt); + + if (--entry->refcnt == 0) { + if (release) + tegra_vde_release_entry(entry); + else + schedule_delayed_work(&entry->dwork, 5 * HZ); + } + break; + } + + mutex_unlock(&vde->map_lock); +} + +void tegra_vde_dmabuf_cache_unmap_sync(struct tegra_vde *vde) +{ + struct tegra_vde_cache_entry *entry, *tmp; + + mutex_lock(&vde->map_lock); + + list_for_each_entry_safe(entry, tmp, &vde->map_list, list) { + if (entry->refcnt) + continue; + + if (!cancel_delayed_work(&entry->dwork)) + continue; + + tegra_vde_release_entry(entry); + } + + mutex_unlock(&vde->map_lock); +} + +void tegra_vde_dmabuf_cache_unmap_all(struct tegra_vde *vde) +{ + struct tegra_vde_cache_entry *entry, *tmp; + + mutex_lock(&vde->map_lock); + + while (!list_empty(&vde->map_list)) { + list_for_each_entry_safe(entry, tmp, &vde->map_list, list) { + if (!cancel_delayed_work(&entry->dwork)) + continue; + + tegra_vde_release_entry(entry); + } + + mutex_unlock(&vde->map_lock); + schedule(); + mutex_lock(&vde->map_lock); + } + + mutex_unlock(&vde->map_lock); +} diff --git a/drivers/staging/media/tegra-vde/iommu.c b/drivers/staging/media/tegra-vde/iommu.c new file mode 100644 index 000000000000..6af863d92123 --- /dev/null +++ b/drivers/staging/media/tegra-vde/iommu.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * NVIDIA Tegra Video decoder driver + * + * Copyright (C) 2016-2019 GRATE-DRIVER project + */ + +#include <linux/iommu.h> +#include <linux/iova.h> +#include <linux/kernel.h> +#include <linux/platform_device.h> + +#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU) +#include <asm/dma-iommu.h> +#endif + +#include "vde.h" + +int tegra_vde_iommu_map(struct tegra_vde *vde, + struct sg_table *sgt, + struct iova **iovap, + size_t size) +{ + struct iova *iova; + unsigned long shift; + unsigned long end; + dma_addr_t addr; + + end = vde->domain->geometry.aperture_end; + size = iova_align(&vde->iova, size); + shift = iova_shift(&vde->iova); + + iova = alloc_iova(&vde->iova, size >> shift, end >> shift, true); + if (!iova) + return -ENOMEM; + + addr = iova_dma_addr(&vde->iova, iova); + + size = iommu_map_sg(vde->domain, addr, sgt->sgl, sgt->nents, + IOMMU_READ | IOMMU_WRITE); + if (!size) { + __free_iova(&vde->iova, iova); + return -ENXIO; + } + + *iovap = iova; + + return 0; +} + +void tegra_vde_iommu_unmap(struct tegra_vde *vde, struct iova *iova) +{ + unsigned long shift = iova_shift(&vde->iova); + unsigned long size = iova_size(iova) << shift; + dma_addr_t addr = iova_dma_addr(&vde->iova, iova); + + iommu_unmap(vde->domain, addr, size); + __free_iova(&vde->iova, iova); +} + +int tegra_vde_iommu_init(struct tegra_vde *vde) +{ + struct device *dev = vde->miscdev.parent; + struct iova *iova; + unsigned long order; + unsigned long shift; + int err; + + vde->group = iommu_group_get(dev); + if (!vde->group) + return 0; + +#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU) + if (dev->archdata.mapping) { + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); + + arm_iommu_detach_device(dev); + arm_iommu_release_mapping(mapping); + } +#endif + vde->domain = iommu_domain_alloc(&platform_bus_type); + if (!vde->domain) { + err = -ENOMEM; + goto put_group; + } + + err = iova_cache_get(); + if (err) + goto free_domain; + + order = __ffs(vde->domain->pgsize_bitmap); + init_iova_domain(&vde->iova, 1UL << order, 0); + + err = iommu_attach_group(vde->domain, vde->group); + if (err) + goto put_iova; + + /* + * We're using some static addresses that are not accessible by VDE + * to trap invalid memory accesses. + */ + shift = iova_shift(&vde->iova); + iova = reserve_iova(&vde->iova, 0x60000000 >> shift, + 0x70000000 >> shift); + if (!iova) { + err = -ENOMEM; + goto detach_group; + } + + vde->iova_resv_static_addresses = iova; + + /* + * BSEV's end-address wraps around due to integer overflow during + * of hardware context preparation if IOVA is allocated at the end + * of address space and VDE can't handle that. Hence simply reserve + * the last page to avoid the problem. + */ + iova = reserve_iova(&vde->iova, 0xffffffff >> shift, + (0xffffffff >> shift) + 1); + if (!iova) { + err = -ENOMEM; + goto unreserve_iova; + } + + vde->iova_resv_last_page = iova; + + return 0; + +unreserve_iova: + __free_iova(&vde->iova, vde->iova_resv_static_addresses); +detach_group: + iommu_detach_group(vde->domain, vde->group); +put_iova: + put_iova_domain(&vde->iova); + iova_cache_put(); +free_domain: + iommu_domain_free(vde->domain); +put_group: + iommu_group_put(vde->group); + + return err; +} + +void tegra_vde_iommu_deinit(struct tegra_vde *vde) +{ + if (vde->domain) { + __free_iova(&vde->iova, vde->iova_resv_last_page); + __free_iova(&vde->iova, vde->iova_resv_static_addresses); + iommu_detach_group(vde->domain, vde->group); + put_iova_domain(&vde->iova); + iova_cache_put(); + iommu_domain_free(vde->domain); + iommu_group_put(vde->group); + + vde->domain = NULL; + } +} diff --git a/drivers/staging/media/tegra-vde/trace.h b/drivers/staging/media/tegra-vde/trace.h index 85e2f7e2d4d0..e5714107db58 100644 --- a/drivers/staging/media/tegra-vde/trace.h +++ b/drivers/staging/media/tegra-vde/trace.h @@ -8,6 +8,8 @@ #include <linux/tracepoint.h> +#include "vde.h" + DECLARE_EVENT_CLASS(register_access, TP_PROTO(struct tegra_vde *vde, void __iomem *base, u32 offset, u32 value), diff --git a/drivers/staging/media/tegra-vde/uapi.h b/drivers/staging/media/tegra-vde/uapi.h index a0dad1ed94ef..ffb4983e5bb6 100644 --- a/drivers/staging/media/tegra-vde/uapi.h +++ b/drivers/staging/media/tegra-vde/uapi.h @@ -6,8 +6,8 @@ #include <linux/types.h> #include <asm/ioctl.h> -#define FLAG_B_FRAME BIT(0) -#define FLAG_REFERENCE BIT(1) +#define FLAG_B_FRAME 0x1 +#define FLAG_REFERENCE 0x2 struct tegra_vde_h264_frame { __s32 y_fd; @@ -21,40 +21,42 @@ struct tegra_vde_h264_frame { __u32 frame_num; __u32 flags; - __u32 reserved; -} __attribute__((packed)); + // Must be zero'ed + __u32 reserved[6]; +}; struct tegra_vde_h264_decoder_ctx { __s32 bitstream_data_fd; __u32 bitstream_data_offset; __u64 dpb_frames_ptr; - __u8 dpb_frames_nb; - __u8 dpb_ref_frames_with_earlier_poc_nb; + __u32 dpb_frames_nb; + __u32 dpb_ref_frames_with_earlier_poc_nb; // SPS - __u8 baseline_profile; - __u8 level_idc; - __u8 log2_max_pic_order_cnt_lsb; - __u8 log2_max_frame_num; - __u8 pic_order_cnt_type; - __u8 direct_8x8_inference_flag; - __u8 pic_width_in_mbs; - __u8 pic_height_in_mbs; + __u32 baseline_profile; + __u32 level_idc; + __u32 log2_max_pic_order_cnt_lsb; + __u32 log2_max_frame_num; + __u32 pic_order_cnt_type; + __u32 direct_8x8_inference_flag; + __u32 pic_width_in_mbs; + __u32 pic_height_in_mbs; // PPS - __u8 pic_init_qp; - __u8 deblocking_filter_control_present_flag; - __u8 constrained_intra_pred_flag; - __u8 chroma_qp_index_offset; - __u8 pic_order_present_flag; + __u32 pic_init_qp; + __u32 deblocking_filter_control_present_flag; + __u32 constrained_intra_pred_flag; + __u32 chroma_qp_index_offset; + __u32 pic_order_present_flag; // Slice header - __u8 num_ref_idx_l0_active_minus1; - __u8 num_ref_idx_l1_active_minus1; + __u32 num_ref_idx_l0_active_minus1; + __u32 num_ref_idx_l1_active_minus1; - __u32 reserved; -} __attribute__((packed)); + // Must be zero'ed + __u32 reserved[11]; +}; #define VDE_IOCTL_BASE ('v' + 0x20) diff --git a/drivers/staging/media/tegra-vde/tegra-vde.c b/drivers/staging/media/tegra-vde/vde.c index a5020dbf6eef..3466daddf663 100644 --- a/drivers/staging/media/tegra-vde/tegra-vde.c +++ b/drivers/staging/media/tegra-vde/vde.c @@ -11,6 +11,7 @@ #include <linux/genalloc.h> #include <linux/interrupt.h> #include <linux/iopoll.h> +#include <linux/list.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/of_device.h> @@ -22,6 +23,10 @@ #include <soc/tegra/pmc.h> #include "uapi.h" +#include "vde.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" #define ICMDQUE_WR 0x00 #define CMDQUE_CONTROL 0x08 @@ -37,10 +42,6 @@ struct video_frame { struct dma_buf_attachment *cb_dmabuf_attachment; struct dma_buf_attachment *cr_dmabuf_attachment; struct dma_buf_attachment *aux_dmabuf_attachment; - struct sg_table *y_sgt; - struct sg_table *cb_sgt; - struct sg_table *cr_sgt; - struct sg_table *aux_sgt; dma_addr_t y_addr; dma_addr_t cb_addr; dma_addr_t cr_addr; @@ -49,63 +50,6 @@ struct video_frame { u32 flags; }; -struct tegra_vde { - void __iomem *sxe; - void __iomem *bsev; - void __iomem *mbe; - void __iomem *ppe; - void __iomem *mce; - void __iomem *tfe; - void __iomem *ppb; - void __iomem *vdma; - void __iomem *frameid; - struct mutex lock; - struct miscdevice miscdev; - struct reset_control *rst; - struct reset_control *rst_mc; - struct gen_pool *iram_pool; - struct completion decode_completion; - struct clk *clk; - dma_addr_t iram_lists_addr; - u32 *iram; -}; - -static __maybe_unused char const * -tegra_vde_reg_base_name(struct tegra_vde *vde, void __iomem *base) -{ - if (vde->sxe == base) - return "SXE"; - - if (vde->bsev == base) - return "BSEV"; - - if (vde->mbe == base) - return "MBE"; - - if (vde->ppe == base) - return "PPE"; - - if (vde->mce == base) - return "MCE"; - - if (vde->tfe == base) - return "TFE"; - - if (vde->ppb == base) - return "PPB"; - - if (vde->vdma == base) - return "VDMA"; - - if (vde->frameid == base) - return "FRAMEID"; - - return "???"; -} - -#define CREATE_TRACE_POINTS -#include "trace.h" - static void tegra_vde_writel(struct tegra_vde *vde, u32 value, void __iomem *base, u32 offset) { @@ -543,31 +487,18 @@ static void tegra_vde_decode_frame(struct tegra_vde *vde, vde->sxe, 0x00); } -static void tegra_vde_detach_and_put_dmabuf(struct dma_buf_attachment *a, - struct sg_table *sgt, - enum dma_data_direction dma_dir) -{ - struct dma_buf *dmabuf = a->dmabuf; - - dma_buf_unmap_attachment(a, sgt, dma_dir); - dma_buf_detach(dmabuf, a); - dma_buf_put(dmabuf); -} - -static int tegra_vde_attach_dmabuf(struct device *dev, +static int tegra_vde_attach_dmabuf(struct tegra_vde *vde, int fd, unsigned long offset, size_t min_size, size_t align_size, struct dma_buf_attachment **a, - dma_addr_t *addr, - struct sg_table **s, + dma_addr_t *addrp, size_t *size, enum dma_data_direction dma_dir) { - struct dma_buf_attachment *attachment; + struct device *dev = vde->miscdev.parent; struct dma_buf *dmabuf; - struct sg_table *sgt; int err; dmabuf = dma_buf_get(fd); @@ -588,46 +519,24 @@ static int tegra_vde_attach_dmabuf(struct device *dev, return -EINVAL; } - attachment = dma_buf_attach(dmabuf, dev); - if (IS_ERR(attachment)) { - dev_err(dev, "Failed to attach dmabuf\n"); - err = PTR_ERR(attachment); + err = tegra_vde_dmabuf_cache_map(vde, dmabuf, dma_dir, a, addrp); + if (err) goto err_put; - } - sgt = dma_buf_map_attachment(attachment, dma_dir); - if (IS_ERR(sgt)) { - dev_err(dev, "Failed to get dmabufs sg_table\n"); - err = PTR_ERR(sgt); - goto err_detach; - } - - if (sgt->nents != 1) { - dev_err(dev, "Sparse DMA region is unsupported\n"); - err = -EINVAL; - goto err_unmap; - } - - *addr = sg_dma_address(sgt->sgl) + offset; - *a = attachment; - *s = sgt; + *addrp = *addrp + offset; if (size) *size = dmabuf->size - offset; return 0; -err_unmap: - dma_buf_unmap_attachment(attachment, sgt, dma_dir); -err_detach: - dma_buf_detach(dmabuf, attachment); err_put: dma_buf_put(dmabuf); return err; } -static int tegra_vde_attach_dmabufs_to_frame(struct device *dev, +static int tegra_vde_attach_dmabufs_to_frame(struct tegra_vde *vde, struct video_frame *frame, struct tegra_vde_h264_frame *src, enum dma_data_direction dma_dir, @@ -636,29 +545,26 @@ static int tegra_vde_attach_dmabufs_to_frame(struct device *dev, { int err; - err = tegra_vde_attach_dmabuf(dev, src->y_fd, + err = tegra_vde_attach_dmabuf(vde, src->y_fd, src->y_offset, lsize, SZ_256, &frame->y_dmabuf_attachment, &frame->y_addr, - &frame->y_sgt, NULL, dma_dir); if (err) return err; - err = tegra_vde_attach_dmabuf(dev, src->cb_fd, + err = tegra_vde_attach_dmabuf(vde, src->cb_fd, src->cb_offset, csize, SZ_256, &frame->cb_dmabuf_attachment, &frame->cb_addr, - &frame->cb_sgt, NULL, dma_dir); if (err) goto err_release_y; - err = tegra_vde_attach_dmabuf(dev, src->cr_fd, + err = tegra_vde_attach_dmabuf(vde, src->cr_fd, src->cr_offset, csize, SZ_256, &frame->cr_dmabuf_attachment, &frame->cr_addr, - &frame->cr_sgt, NULL, dma_dir); if (err) goto err_release_cb; @@ -668,11 +574,10 @@ static int tegra_vde_attach_dmabufs_to_frame(struct device *dev, return 0; } - err = tegra_vde_attach_dmabuf(dev, src->aux_fd, + err = tegra_vde_attach_dmabuf(vde, src->aux_fd, src->aux_offset, csize, SZ_256, &frame->aux_dmabuf_attachment, &frame->aux_addr, - &frame->aux_sgt, NULL, dma_dir); if (err) goto err_release_cr; @@ -680,34 +585,28 @@ static int tegra_vde_attach_dmabufs_to_frame(struct device *dev, return 0; err_release_cr: - tegra_vde_detach_and_put_dmabuf(frame->cr_dmabuf_attachment, - frame->cr_sgt, dma_dir); + tegra_vde_dmabuf_cache_unmap(vde, frame->cr_dmabuf_attachment, true); err_release_cb: - tegra_vde_detach_and_put_dmabuf(frame->cb_dmabuf_attachment, - frame->cb_sgt, dma_dir); + tegra_vde_dmabuf_cache_unmap(vde, frame->cb_dmabuf_attachment, true); err_release_y: - tegra_vde_detach_and_put_dmabuf(frame->y_dmabuf_attachment, - frame->y_sgt, dma_dir); + tegra_vde_dmabuf_cache_unmap(vde, frame->y_dmabuf_attachment, true); return err; } -static void tegra_vde_release_frame_dmabufs(struct video_frame *frame, +static void tegra_vde_release_frame_dmabufs(struct tegra_vde *vde, + struct video_frame *frame, enum dma_data_direction dma_dir, - bool baseline_profile) + bool baseline_profile, + bool release) { if (!baseline_profile) - tegra_vde_detach_and_put_dmabuf(frame->aux_dmabuf_attachment, - frame->aux_sgt, dma_dir); + tegra_vde_dmabuf_cache_unmap(vde, frame->aux_dmabuf_attachment, + release); - tegra_vde_detach_and_put_dmabuf(frame->cr_dmabuf_attachment, - frame->cr_sgt, dma_dir); - - tegra_vde_detach_and_put_dmabuf(frame->cb_dmabuf_attachment, - frame->cb_sgt, dma_dir); - - tegra_vde_detach_and_put_dmabuf(frame->y_dmabuf_attachment, - frame->y_sgt, dma_dir); + tegra_vde_dmabuf_cache_unmap(vde, frame->cr_dmabuf_attachment, release); + tegra_vde_dmabuf_cache_unmap(vde, frame->cb_dmabuf_attachment, release); + tegra_vde_dmabuf_cache_unmap(vde, frame->y_dmabuf_attachment, release); } static int tegra_vde_validate_frame(struct device *dev, @@ -795,11 +694,10 @@ static int tegra_vde_ioctl_decode_h264(struct tegra_vde *vde, { struct device *dev = vde->miscdev.parent; struct tegra_vde_h264_decoder_ctx ctx; - struct tegra_vde_h264_frame frames[17]; + struct tegra_vde_h264_frame *frames; struct tegra_vde_h264_frame __user *frames_user; struct video_frame *dpb_frames; struct dma_buf_attachment *bitstream_data_dmabuf_attachment; - struct sg_table *bitstream_sgt; enum dma_data_direction dma_dir; dma_addr_t bitstream_data_addr; dma_addr_t bsev_ptr; @@ -819,22 +717,27 @@ static int tegra_vde_ioctl_decode_h264(struct tegra_vde *vde, if (ret) return ret; - ret = tegra_vde_attach_dmabuf(dev, ctx.bitstream_data_fd, + ret = tegra_vde_attach_dmabuf(vde, ctx.bitstream_data_fd, ctx.bitstream_data_offset, SZ_16K, SZ_16K, &bitstream_data_dmabuf_attachment, &bitstream_data_addr, - &bitstream_sgt, &bitstream_data_size, DMA_TO_DEVICE); if (ret) return ret; + frames = kmalloc_array(ctx.dpb_frames_nb, sizeof(*frames), GFP_KERNEL); + if (!frames) { + ret = -ENOMEM; + goto release_bitstream_dmabuf; + } + dpb_frames = kcalloc(ctx.dpb_frames_nb, sizeof(*dpb_frames), GFP_KERNEL); if (!dpb_frames) { ret = -ENOMEM; - goto release_bitstream_dmabuf; + goto free_frames; } macroblocks_nb = ctx.pic_width_in_mbs * ctx.pic_height_in_mbs; @@ -860,7 +763,7 @@ static int tegra_vde_ioctl_decode_h264(struct tegra_vde *vde, dma_dir = (i == 0) ? DMA_FROM_DEVICE : DMA_TO_DEVICE; - ret = tegra_vde_attach_dmabufs_to_frame(dev, &dpb_frames[i], + ret = tegra_vde_attach_dmabufs_to_frame(vde, &dpb_frames[i], &frames[i], dma_dir, ctx.baseline_profile, lsize, csize); @@ -948,16 +851,19 @@ release_dpb_frames: while (i--) { dma_dir = (i == 0) ? DMA_FROM_DEVICE : DMA_TO_DEVICE; - tegra_vde_release_frame_dmabufs(&dpb_frames[i], dma_dir, - ctx.baseline_profile); + tegra_vde_release_frame_dmabufs(vde, &dpb_frames[i], dma_dir, + ctx.baseline_profile, ret != 0); } free_dpb_frames: kfree(dpb_frames); +free_frames: + kfree(frames); + release_bitstream_dmabuf: - tegra_vde_detach_and_put_dmabuf(bitstream_data_dmabuf_attachment, - bitstream_sgt, DMA_TO_DEVICE); + tegra_vde_dmabuf_cache_unmap(vde, bitstream_data_dmabuf_attachment, + ret != 0); return ret; } @@ -979,9 +885,21 @@ static long tegra_vde_unlocked_ioctl(struct file *filp, return -ENOTTY; } +static int tegra_vde_release_file(struct inode *inode, struct file *filp) +{ + struct miscdevice *miscdev = filp->private_data; + struct tegra_vde *vde = container_of(miscdev, struct tegra_vde, + miscdev); + + tegra_vde_dmabuf_cache_unmap_sync(vde); + + return 0; +} + static const struct file_operations tegra_vde_fops = { .owner = THIS_MODULE, .unlocked_ioctl = tegra_vde_unlocked_ioctl, + .release = tegra_vde_release_file, }; static irqreturn_t tegra_vde_isr(int irq, void *data) @@ -1159,6 +1077,8 @@ static int tegra_vde_probe(struct platform_device *pdev) return -ENOMEM; } + INIT_LIST_HEAD(&vde->map_list); + mutex_init(&vde->map_lock); mutex_init(&vde->lock); init_completion(&vde->decode_completion); @@ -1167,10 +1087,16 @@ static int tegra_vde_probe(struct platform_device *pdev) vde->miscdev.fops = &tegra_vde_fops; vde->miscdev.parent = dev; + err = tegra_vde_iommu_init(vde); + if (err) { + dev_err(dev, "Failed to initialize IOMMU: %d\n", err); + goto err_gen_free; + } + err = misc_register(&vde->miscdev); if (err) { dev_err(dev, "Failed to register misc device: %d\n", err); - goto err_gen_free; + goto err_deinit_iommu; } pm_runtime_enable(dev); @@ -1188,6 +1114,9 @@ static int tegra_vde_probe(struct platform_device *pdev) err_misc_unreg: misc_deregister(&vde->miscdev); +err_deinit_iommu: + tegra_vde_iommu_deinit(vde); + err_gen_free: gen_pool_free(vde->iram_pool, (unsigned long)vde->iram, gen_pool_size(vde->iram_pool)); @@ -1212,6 +1141,9 @@ static int tegra_vde_remove(struct platform_device *pdev) misc_deregister(&vde->miscdev); + tegra_vde_dmabuf_cache_unmap_all(vde); + tegra_vde_iommu_deinit(vde); + gen_pool_free(vde->iram_pool, (unsigned long)vde->iram, gen_pool_size(vde->iram_pool)); diff --git a/drivers/staging/media/tegra-vde/vde.h b/drivers/staging/media/tegra-vde/vde.h new file mode 100644 index 000000000000..d369f1466bc7 --- /dev/null +++ b/drivers/staging/media/tegra-vde/vde.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * NVIDIA Tegra Video decoder driver + * + * Copyright (C) 2016-2019 GRATE-DRIVER project + */ + +#ifndef TEGRA_VDE_H +#define TEGRA_VDE_H + +#include <linux/completion.h> +#include <linux/dma-direction.h> +#include <linux/list.h> +#include <linux/miscdevice.h> +#include <linux/mutex.h> +#include <linux/types.h> +#include <linux/iova.h> + +struct clk; +struct dma_buf; +struct gen_pool; +struct iommu_group; +struct iommu_domain; +struct reset_control; +struct dma_buf_attachment; + +struct tegra_vde { + void __iomem *sxe; + void __iomem *bsev; + void __iomem *mbe; + void __iomem *ppe; + void __iomem *mce; + void __iomem *tfe; + void __iomem *ppb; + void __iomem *vdma; + void __iomem *frameid; + struct mutex lock; + struct mutex map_lock; + struct list_head map_list; + struct miscdevice miscdev; + struct reset_control *rst; + struct reset_control *rst_mc; + struct gen_pool *iram_pool; + struct completion decode_completion; + struct clk *clk; + struct iommu_domain *domain; + struct iommu_group *group; + struct iova_domain iova; + struct iova *iova_resv_static_addresses; + struct iova *iova_resv_last_page; + dma_addr_t iram_lists_addr; + u32 *iram; +}; + +int tegra_vde_iommu_init(struct tegra_vde *vde); +void tegra_vde_iommu_deinit(struct tegra_vde *vde); +int tegra_vde_iommu_map(struct tegra_vde *vde, + struct sg_table *sgt, + struct iova **iovap, + size_t size); +void tegra_vde_iommu_unmap(struct tegra_vde *vde, struct iova *iova); + +int tegra_vde_dmabuf_cache_map(struct tegra_vde *vde, + struct dma_buf *dmabuf, + enum dma_data_direction dma_dir, + struct dma_buf_attachment **ap, + dma_addr_t *addrp); +void tegra_vde_dmabuf_cache_unmap(struct tegra_vde *vde, + struct dma_buf_attachment *a, + bool release); +void tegra_vde_dmabuf_cache_unmap_sync(struct tegra_vde *vde); +void tegra_vde_dmabuf_cache_unmap_all(struct tegra_vde *vde); + +static __maybe_unused char const * +tegra_vde_reg_base_name(struct tegra_vde *vde, void __iomem *base) +{ + if (vde->sxe == base) + return "SXE"; + + if (vde->bsev == base) + return "BSEV"; + + if (vde->mbe == base) + return "MBE"; + + if (vde->ppe == base) + return "PPE"; + + if (vde->mce == base) + return "MCE"; + + if (vde->tfe == base) + return "TFE"; + + if (vde->ppb == base) + return "PPB"; + + if (vde->vdma == base) + return "VDMA"; + + if (vde->frameid == base) + return "FRAMEID"; + + return "???"; +} + +#endif /* TEGRA_VDE_H */ |