Commit 60d98e1a authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge tag 'drm-misc-fixes-2025-08-28' of... 

Merge tag 'drm-misc-fixes-2025-08-28' of https://gitlab.freedesktop.org/drm/misc/kernel

 into drm-fixes

Several nouveau fixes to remove unused code, fix an error path and be
less restrictive with the formats it accepts. A fix for amdgpu to pin
vmapped dma-buf, and a revert for tegra for a regression in the dma-buf
/ GEM code.

Signed-off-by: default avatarDave Airlie <airlied@redhat.com>

From: Maxime Ripard <mripard@redhat.com>
Link: https://lore.kernel.org/r/20250828-hypersonic-colorful-squirrel-64f04b@houat
parents 59b00024 16fdb3cc

drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c

+32 −2
Original line number Diff line number Diff line
@@ -285,6 +285,36 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf, 
	return ret;

}



static int amdgpu_dma_buf_vmap(struct dma_buf *dma_buf, struct iosys_map *map)

{

	struct drm_gem_object *obj = dma_buf->priv;

	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);

	int ret;



	/*

	 * Pin to keep buffer in place while it's vmap'ed. The actual

	 * domain is not that important as long as it's mapable. Using

	 * GTT and VRAM should be compatible with most use cases.

	 */

	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT | AMDGPU_GEM_DOMAIN_VRAM);

	if (ret)

		return ret;

	ret = drm_gem_dmabuf_vmap(dma_buf, map);

	if (ret)

		amdgpu_bo_unpin(bo);



	return ret;

}



static void amdgpu_dma_buf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map)

{

	struct drm_gem_object *obj = dma_buf->priv;

	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);



	drm_gem_dmabuf_vunmap(dma_buf, map);

	amdgpu_bo_unpin(bo);

}



const struct dma_buf_ops amdgpu_dmabuf_ops = {

	.attach = amdgpu_dma_buf_attach,

	.pin = amdgpu_dma_buf_pin,
@@ -294,8 +324,8 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = { 
	.release = drm_gem_dmabuf_release,

	.begin_cpu_access = amdgpu_dma_buf_begin_cpu_access,

	.mmap = drm_gem_dmabuf_mmap,

	.vmap = drm_gem_dmabuf_vmap,

	.vunmap = drm_gem_dmabuf_vunmap,

	.vmap = amdgpu_dma_buf_vmap,

	.vunmap = amdgpu_dma_buf_vunmap,

};



/**

drivers/gpu/drm/drm_gpuvm.c

+39 −39
Original line number Diff line number Diff line
@@ -40,7 +40,7 @@ 
 * mapping's backing &drm_gem_object buffers.

 *

 * &drm_gem_object buffers maintain a list of &drm_gpuva objects representing

 * all existent GPU VA mappings using this &drm_gem_object as backing buffer.

 * all existing GPU VA mappings using this &drm_gem_object as backing buffer.

 *

 * GPU VAs can be flagged as sparse, such that drivers may use GPU VAs to also

 * keep track of sparse PTEs in order to support Vulkan 'Sparse Resources'.
@@ -72,7 +72,7 @@ 
 * but it can also be a 'dummy' object, which can be allocated with

 * drm_gpuvm_resv_object_alloc().

 *

 * In order to connect a struct drm_gpuva its backing &drm_gem_object each

 * In order to connect a struct drm_gpuva to its backing &drm_gem_object each

 * &drm_gem_object maintains a list of &drm_gpuvm_bo structures, and each

 * &drm_gpuvm_bo contains a list of &drm_gpuva structures.

 *
@@ -81,7 +81,7 @@ 
 * This is ensured by the API through drm_gpuvm_bo_obtain() and

 * drm_gpuvm_bo_obtain_prealloc() which first look into the corresponding

 * &drm_gem_object list of &drm_gpuvm_bos for an existing instance of this

 * particular combination. If not existent a new instance is created and linked

 * particular combination. If not present, a new instance is created and linked

 * to the &drm_gem_object.

 *

 * &drm_gpuvm_bo structures, since unique for a given &drm_gpuvm, are also used
@@ -108,7 +108,7 @@ 
 * sequence of operations to satisfy a given map or unmap request.

 *

 * Therefore the DRM GPU VA manager provides an algorithm implementing splitting

 * and merging of existent GPU VA mappings with the ones that are requested to

 * and merging of existing GPU VA mappings with the ones that are requested to

 * be mapped or unmapped. This feature is required by the Vulkan API to

 * implement Vulkan 'Sparse Memory Bindings' - drivers UAPIs often refer to this

 * as VM BIND.
@@ -119,7 +119,7 @@ 
 * execute in order to integrate the new mapping cleanly into the current state

 * of the GPU VA space.

 *

 * Depending on how the new GPU VA mapping intersects with the existent mappings

 * Depending on how the new GPU VA mapping intersects with the existing mappings

 * of the GPU VA space the &drm_gpuvm_ops callbacks contain an arbitrary amount

 * of unmap operations, a maximum of two remap operations and a single map

 * operation. The caller might receive no callback at all if no operation is
@@ -139,16 +139,16 @@ 
 * one unmap operation and one or two map operations, such that drivers can

 * derive the page table update delta accordingly.

 *

 * Note that there can't be more than two existent mappings to split up, one at

 * Note that there can't be more than two existing mappings to split up, one at

 * the beginning and one at the end of the new mapping, hence there is a

 * maximum of two remap operations.

 *

 * Analogous to drm_gpuvm_sm_map() drm_gpuvm_sm_unmap() uses &drm_gpuvm_ops to

 * call back into the driver in order to unmap a range of GPU VA space. The

 * logic behind this function is way simpler though: For all existent mappings

 * logic behind this function is way simpler though: For all existing mappings

 * enclosed by the given range unmap operations are created. For mappings which

 * are only partically located within the given range, remap operations are

 * created such that those mappings are split up and re-mapped partically.

 * are only partially located within the given range, remap operations are

 * created such that those mappings are split up and re-mapped partially.

 *

 * As an alternative to drm_gpuvm_sm_map() and drm_gpuvm_sm_unmap(),

 * drm_gpuvm_sm_map_ops_create() and drm_gpuvm_sm_unmap_ops_create() can be used
@@ -168,7 +168,7 @@ 
 * provided helper functions drm_gpuva_map(), drm_gpuva_remap() and

 * drm_gpuva_unmap() instead.

 *

 * The following diagram depicts the basic relationships of existent GPU VA

 * The following diagram depicts the basic relationships of existing GPU VA

 * mappings, a newly requested mapping and the resulting mappings as implemented

 * by drm_gpuvm_sm_map() - it doesn't cover any arbitrary combinations of these.

 *
@@ -218,7 +218,7 @@ 
 *

 *

 * 4) Existent mapping is a left aligned subset of the requested one, hence

 *    replace the existent one.

 *    replace the existing one.

 *

 *    ::

 *
@@ -236,9 +236,9 @@ 
 *       and/or non-contiguous BO offset.

 *

 *

 * 5) Requested mapping's range is a left aligned subset of the existent one,

 * 5) Requested mapping's range is a left aligned subset of the existing one,

 *    but backed by a different BO. Hence, map the requested mapping and split

 *    the existent one adjusting its BO offset.

 *    the existing one adjusting its BO offset.

 *

 *    ::

 *
@@ -271,9 +271,9 @@ 
 *	new: |-----|-----| (a.bo_offset=n, a'.bo_offset=n+1)

 *

 *

 * 7) Requested mapping's range is a right aligned subset of the existent one,

 * 7) Requested mapping's range is a right aligned subset of the existing one,

 *    but backed by a different BO. Hence, map the requested mapping and split

 *    the existent one, without adjusting the BO offset.

 *    the existing one, without adjusting the BO offset.

 *

 *    ::

 *
@@ -304,7 +304,7 @@ 
 *

 * 9) Existent mapping is overlapped at the end by the requested mapping backed

 *    by a different BO. Hence, map the requested mapping and split up the

 *    existent one, without adjusting the BO offset.

 *    existing one, without adjusting the BO offset.

 *

 *    ::

 *
@@ -334,9 +334,9 @@ 
 *	 new: |-----|-----------| (a'.bo_offset=n, a.bo_offset=n+1)

 *

 *

 * 11) Requested mapping's range is a centered subset of the existent one

 * 11) Requested mapping's range is a centered subset of the existing one

 *     having a different backing BO. Hence, map the requested mapping and split

 *     up the existent one in two mappings, adjusting the BO offset of the right

 *     up the existing one in two mappings, adjusting the BO offset of the right

 *     one accordingly.

 *

 *     ::
@@ -351,7 +351,7 @@ 
 *	 new: |-----|-----|-----| (a.bo_offset=n,b.bo_offset=m,a'.bo_offset=n+2)

 *

 *

 * 12) Requested mapping is a contiguous subset of the existent one. Split it

 * 12) Requested mapping is a contiguous subset of the existing one. Split it

 *     up, but indicate that the backing PTEs could be kept.

 *

 *     ::
@@ -367,7 +367,7 @@ 
 *

 *

 * 13) Existent mapping is a right aligned subset of the requested one, hence

 *     replace the existent one.

 *     replace the existing one.

 *

 *     ::

 *
@@ -386,7 +386,7 @@ 
 *

 *

 * 14) Existent mapping is a centered subset of the requested one, hence

 *     replace the existent one.

 *     replace the existing one.

 *

 *     ::

 *
@@ -406,7 +406,7 @@ 
 *

 * 15) Existent mappings is overlapped at the beginning by the requested mapping

 *     backed by a different BO. Hence, map the requested mapping and split up

 *     the existent one, adjusting its BO offset accordingly.

 *     the existing one, adjusting its BO offset accordingly.

 *

 *     ::

 *
@@ -469,8 +469,8 @@ 
 * make use of them.

 *

 * The below code is strictly limited to illustrate the generic usage pattern.

 * To maintain simplicitly, it doesn't make use of any abstractions for common

 * code, different (asyncronous) stages with fence signalling critical paths,

 * To maintain simplicity, it doesn't make use of any abstractions for common

 * code, different (asynchronous) stages with fence signalling critical paths,

 * any other helpers or error handling in terms of freeing memory and dropping

 * previously taken locks.

 *
@@ -479,7 +479,7 @@ 
 *	// Allocates a new &drm_gpuva.

 *	struct drm_gpuva * driver_gpuva_alloc(void);

 *

 *	// Typically drivers would embedd the &drm_gpuvm and &drm_gpuva

 *	// Typically drivers would embed the &drm_gpuvm and &drm_gpuva

 *	// structure in individual driver structures and lock the dma-resv with

 *	// drm_exec or similar helpers.

 *	int driver_mapping_create(struct drm_gpuvm *gpuvm,
@@ -582,7 +582,7 @@ 
 *		.sm_step_unmap = driver_gpuva_unmap,

 *	};

 *

 *	// Typically drivers would embedd the &drm_gpuvm and &drm_gpuva

 *	// Typically drivers would embed the &drm_gpuvm and &drm_gpuva

 *	// structure in individual driver structures and lock the dma-resv with

 *	// drm_exec or similar helpers.

 *	int driver_mapping_create(struct drm_gpuvm *gpuvm,
@@ -680,7 +680,7 @@ 
 *

 * This helper is here to provide lockless list iteration. Lockless as in, the

 * iterator releases the lock immediately after picking the first element from

 * the list, so list insertion deletion can happen concurrently.

 * the list, so list insertion and deletion can happen concurrently.

 *

 * Elements popped from the original list are kept in a local list, so removal

 * and is_empty checks can still happen while we're iterating the list.
@@ -1160,7 +1160,7 @@ drm_gpuvm_prepare_objects_locked(struct drm_gpuvm *gpuvm, 
}



/**

 * drm_gpuvm_prepare_objects() - prepare all assoiciated BOs

 * drm_gpuvm_prepare_objects() - prepare all associated BOs

 * @gpuvm: the &drm_gpuvm

 * @exec: the &drm_exec locking context

 * @num_fences: the amount of &dma_fences to reserve
@@ -1230,13 +1230,13 @@ drm_gpuvm_prepare_range(struct drm_gpuvm *gpuvm, struct drm_exec *exec, 
EXPORT_SYMBOL_GPL(drm_gpuvm_prepare_range);



/**

 * drm_gpuvm_exec_lock() - lock all dma-resv of all assoiciated BOs

 * drm_gpuvm_exec_lock() - lock all dma-resv of all associated BOs

 * @vm_exec: the &drm_gpuvm_exec wrapper

 *

 * Acquires all dma-resv locks of all &drm_gem_objects the given

 * &drm_gpuvm contains mappings of.

 *

 * Addionally, when calling this function with struct drm_gpuvm_exec::extra

 * Additionally, when calling this function with struct drm_gpuvm_exec::extra

 * being set the driver receives the given @fn callback to lock additional

 * dma-resv in the context of the &drm_gpuvm_exec instance. Typically, drivers

 * would call drm_exec_prepare_obj() from within this callback.
@@ -1293,7 +1293,7 @@ fn_lock_array(struct drm_gpuvm_exec *vm_exec) 
}



/**

 * drm_gpuvm_exec_lock_array() - lock all dma-resv of all assoiciated BOs

 * drm_gpuvm_exec_lock_array() - lock all dma-resv of all associated BOs

 * @vm_exec: the &drm_gpuvm_exec wrapper

 * @objs: additional &drm_gem_objects to lock

 * @num_objs: the number of additional &drm_gem_objects to lock
@@ -1588,7 +1588,7 @@ drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm, 
EXPORT_SYMBOL_GPL(drm_gpuvm_bo_find);



/**

 * drm_gpuvm_bo_obtain() - obtains and instance of the &drm_gpuvm_bo for the

 * drm_gpuvm_bo_obtain() - obtains an instance of the &drm_gpuvm_bo for the

 * given &drm_gpuvm and &drm_gem_object

 * @gpuvm: The &drm_gpuvm the @obj is mapped in.

 * @obj: The &drm_gem_object being mapped in the @gpuvm.
@@ -1624,7 +1624,7 @@ drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm, 
EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain);



/**

 * drm_gpuvm_bo_obtain_prealloc() - obtains and instance of the &drm_gpuvm_bo

 * drm_gpuvm_bo_obtain_prealloc() - obtains an instance of the &drm_gpuvm_bo

 * for the given &drm_gpuvm and &drm_gem_object

 * @__vm_bo: A pre-allocated struct drm_gpuvm_bo.

 *
@@ -1688,7 +1688,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_extobj_add); 
 * @vm_bo: the &drm_gpuvm_bo to add or remove

 * @evict: indicates whether the object is evicted

 *

 * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvms evicted list.

 * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvm's evicted list.

 */

void

drm_gpuvm_bo_evict(struct drm_gpuvm_bo *vm_bo, bool evict)
@@ -1790,7 +1790,7 @@ __drm_gpuva_remove(struct drm_gpuva *va) 
 * drm_gpuva_remove() - remove a &drm_gpuva

 * @va: the &drm_gpuva to remove

 *

 * This removes the given &va from the underlaying tree.

 * This removes the given &va from the underlying tree.

 *

 * It is safe to use this function using the safe versions of iterating the GPU

 * VA space, such as drm_gpuvm_for_each_va_safe() and
@@ -2358,7 +2358,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_sm_map); 
 *

 * This function iterates the given range of the GPU VA space. It utilizes the

 * &drm_gpuvm_ops to call back into the driver providing the operations to

 * unmap and, if required, split existent mappings.

 * unmap and, if required, split existing mappings.

 *

 * Drivers may use these callbacks to update the GPU VA space right away within

 * the callback. In case the driver decides to copy and store the operations for
@@ -2475,7 +2475,7 @@ static const struct drm_gpuvm_ops lock_ops = { 
 *    required without the earlier DRIVER_OP_MAP.  This is safe because we've

 *    already locked the GEM object in the earlier DRIVER_OP_MAP step.

 *

 * Returns: 0 on success or a negative error codec

 * Returns: 0 on success or a negative error code

 */

int

drm_gpuvm_sm_map_exec_lock(struct drm_gpuvm *gpuvm,
@@ -2619,12 +2619,12 @@ static const struct drm_gpuvm_ops gpuvm_list_ops = { 
 * @req_offset: the offset within the &drm_gem_object

 *

 * This function creates a list of operations to perform splitting and merging

 * of existent mapping(s) with the newly requested one.

 * of existing mapping(s) with the newly requested one.

 *

 * The list can be iterated with &drm_gpuva_for_each_op and must be processed

 * in the given order. It can contain map, unmap and remap operations, but it

 * also can be empty if no operation is required, e.g. if the requested mapping

 * already exists is the exact same way.

 * already exists in the exact same way.

 *

 * There can be an arbitrary amount of unmap operations, a maximum of two remap

 * operations and a single map operation. The latter one represents the original

drivers/gpu/drm/nouveau/dispnv50/wndw.c

+4 −0
Original line number Diff line number Diff line
@@ -795,6 +795,10 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane, 
	struct nouveau_drm *drm = nouveau_drm(plane->dev);

	uint8_t i;



	/* All chipsets can display all formats in linear layout */

	if (modifier == DRM_FORMAT_MOD_LINEAR)

		return true;



	if (drm->client.device.info.chipset < 0xc0) {

		const struct drm_format_info *info = drm_format_info(format);

		const uint8_t kind = (modifier >> 12) & 0xff;

drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c

+4 −11
Original line number Diff line number Diff line
@@ -103,7 +103,7 @@ gm200_flcn_pio_imem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 i 
static void

gm200_flcn_pio_imem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int len, u16 tag)

{

	nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag++);

	nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag);

	while (len >= 4) {

		nvkm_falcon_wr32(falcon, 0x184 + (port * 0x10), *(u32 *)img);

		img += 4;
@@ -249,9 +249,11 @@ int 
gm200_flcn_fw_load(struct nvkm_falcon_fw *fw)

{

	struct nvkm_falcon *falcon = fw->falcon;

	int target, ret;

	int ret;



	if (fw->inst) {

		int target;



		nvkm_falcon_mask(falcon, 0x048, 0x00000001, 0x00000001);



		switch (nvkm_memory_target(fw->inst)) {
@@ -285,15 +287,6 @@ gm200_flcn_fw_load(struct nvkm_falcon_fw *fw) 
	}



	if (fw->boot) {

		switch (nvkm_memory_target(&fw->fw.mem.memory)) {

		case NVKM_MEM_TARGET_VRAM: target = 4; break;

		case NVKM_MEM_TARGET_HOST: target = 5; break;

		case NVKM_MEM_TARGET_NCOH: target = 6; break;

		default:

			WARN_ON(1);

			return -EINVAL;

		}



		ret = nvkm_falcon_pio_wr(falcon, fw->boot, 0, 0,

					 IMEM, falcon->code.limit - fw->boot_size, fw->boot_size,

					 fw->boot_addr >> 8, false);

drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c

+3 −2
Original line number Diff line number Diff line
@@ -209,11 +209,12 @@ nvkm_gsp_fwsec_v2(struct nvkm_gsp *gsp, const char *name, 
	fw->boot_addr = bld->start_tag << 8;

	fw->boot_size = bld->code_size;

	fw->boot = kmemdup(bl->data + hdr->data_offset + bld->code_off, fw->boot_size, GFP_KERNEL);

	if (!fw->boot)

		ret = -ENOMEM;



	nvkm_firmware_put(bl);



	if (!fw->boot)

		return -ENOMEM;



	/* Patch in interface data. */

	return nvkm_gsp_fwsec_patch(gsp, fw, desc->InterfaceOffset, init_cmd);

}