Linaro-mm-sig

linaro-mm-sig@lists.linaro.org

13 participants
2894 discussions

Re: [PATCH v10 6/9] tee: add tee_shm_alloc_dma_mem()

by Jens Wiklander

On Tue, Jun 17, 2025 at 1:32 PM Sumit Garg <sumit.garg(a)kernel.org> wrote: > > On Tue, Jun 10, 2025 at 03:13:50PM +0200, Jens Wiklander wrote: > > Add tee_shm_alloc_dma_mem() to allocate DMA memory. The memory is > > represented by a tee_shm object using the new flag TEE_SHM_DMA_MEM to > > identify it as DMA memory. The allocated memory will later be lent to > > the TEE to be used as protected memory. > > > > Signed-off-by: Jens Wiklander <jens.wiklander(a)linaro.org> > > --- > > drivers/tee/tee_shm.c | 85 +++++++++++++++++++++++++++++++++++++++- > > include/linux/tee_core.h | 5 +++ > > 2 files changed, 88 insertions(+), 2 deletions(-) > > > > diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c > > index e63095e84644..60b0f3932cee 100644 > > --- a/drivers/tee/tee_shm.c > > +++ b/drivers/tee/tee_shm.c > > @@ -5,6 +5,8 @@ > > #include <linux/anon_inodes.h> > > #include <linux/device.h> > > #include <linux/dma-buf.h> > > +#include <linux/dma-mapping.h> > > +#include <linux/highmem.h> > > #include <linux/idr.h> > > #include <linux/io.h> > > #include <linux/mm.h> > > @@ -13,9 +15,14 @@ > > #include <linux/tee_core.h> > > #include <linux/uaccess.h> > > #include <linux/uio.h> > > -#include <linux/highmem.h> > > #include "tee_private.h" > > > > +struct tee_shm_dma_mem { > > + struct tee_shm shm; > > + dma_addr_t dma_addr; > > + struct page *page; > > +}; > > + > > static void shm_put_kernel_pages(struct page **pages, size_t page_count) > > { > > size_t n; > > @@ -48,7 +55,16 @@ static void tee_shm_release(struct tee_device *teedev, struct tee_shm *shm) > > { > > void *p = shm; > > > > - if (shm->flags & TEE_SHM_DMA_BUF) { > > + if (shm->flags & TEE_SHM_DMA_MEM) { > > +#if IS_ENABLED(CONFIG_TEE_DMABUF_HEAPS) > > nit: this config check can be merged into the above if check. No, because dma_free_pages() is only defined if CONFIG_TEE_DMABUF_HEAPS is enabled. > > > + struct tee_shm_dma_mem *dma_mem; > > + > > + dma_mem = container_of(shm, struct tee_shm_dma_mem, shm); > > + p = dma_mem; > > + dma_free_pages(&teedev->dev, shm->size, dma_mem->page, > > + dma_mem->dma_addr, DMA_BIDIRECTIONAL); > > +#endif > > + } else if (shm->flags & TEE_SHM_DMA_BUF) { > > Do we need a similar config check for this flag too? No, because DMA_SHARED_BUFFER is selected, so the dma_buf functions are defined. Cheers, Jens > > With these addressed, feel free to add: > > Reviewed-by: Sumit Garg <sumit.garg(a)oss.qualcomm.com> > > -Sumit > > > struct tee_shm_dmabuf_ref *ref; > > > > ref = container_of(shm, struct tee_shm_dmabuf_ref, shm); > > @@ -303,6 +319,71 @@ struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size) > > } > > EXPORT_SYMBOL_GPL(tee_shm_alloc_priv_buf); > > > > +#if IS_ENABLED(CONFIG_TEE_DMABUF_HEAPS) > > +/** > > + * tee_shm_alloc_dma_mem() - Allocate DMA memory as shared memory object > > + * @ctx: Context that allocates the shared memory > > + * @page_count: Number of pages > > + * > > + * The allocated memory is expected to be lent (made inaccessible to the > > + * kernel) to the TEE while it's used and returned (accessible to the > > + * kernel again) before it's freed. > > + * > > + * This function should normally only be used internally in the TEE > > + * drivers. > > + * > > + * @returns a pointer to 'struct tee_shm' > > + */ > > +struct tee_shm *tee_shm_alloc_dma_mem(struct tee_context *ctx, > > + size_t page_count) > > +{ > > + struct tee_device *teedev = ctx->teedev; > > + struct tee_shm_dma_mem *dma_mem; > > + dma_addr_t dma_addr; > > + struct page *page; > > + > > + if (!tee_device_get(teedev)) > > + return ERR_PTR(-EINVAL); > > + > > + page = dma_alloc_pages(&teedev->dev, page_count * PAGE_SIZE, > > + &dma_addr, DMA_BIDIRECTIONAL, GFP_KERNEL); > > + if (!page) > > + goto err_put_teedev; > > + > > + dma_mem = kzalloc(sizeof(*dma_mem), GFP_KERNEL); > > + if (!dma_mem) > > + goto err_free_pages; > > + > > + refcount_set(&dma_mem->shm.refcount, 1); > > + dma_mem->shm.ctx = ctx; > > + dma_mem->shm.paddr = page_to_phys(page); > > + dma_mem->dma_addr = dma_addr; > > + dma_mem->page = page; > > + dma_mem->shm.size = page_count * PAGE_SIZE; > > + dma_mem->shm.flags = TEE_SHM_DMA_MEM; > > + > > + teedev_ctx_get(ctx); > > + > > + return &dma_mem->shm; > > + > > +err_free_pages: > > + dma_free_pages(&teedev->dev, page_count * PAGE_SIZE, page, dma_addr, > > + DMA_BIDIRECTIONAL); > > +err_put_teedev: > > + tee_device_put(teedev); > > + > > + return ERR_PTR(-ENOMEM); > > +} > > +EXPORT_SYMBOL_GPL(tee_shm_alloc_dma_mem); > > +#else > > +struct tee_shm *tee_shm_alloc_dma_mem(struct tee_context *ctx, > > + size_t page_count) > > +{ > > + return ERR_PTR(-EINVAL); > > +} > > +EXPORT_SYMBOL_GPL(tee_shm_alloc_dma_mem); > > +#endif > > + > > int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, > > int (*shm_register)(struct tee_context *ctx, > > struct tee_shm *shm, > > diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h > > index f17710196c4c..e46a53e753af 100644 > > --- a/include/linux/tee_core.h > > +++ b/include/linux/tee_core.h > > @@ -29,6 +29,8 @@ > > #define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ > > #define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ > > #define TEE_SHM_DMA_BUF BIT(4) /* Memory with dma-buf handle */ > > +#define TEE_SHM_DMA_MEM BIT(5) /* Memory allocated with */ > > + /* dma_alloc_pages() */ > > > > #define TEE_DEVICE_FLAG_REGISTERED 0x1 > > #define TEE_MAX_DEV_NAME_LEN 32 > > @@ -310,6 +312,9 @@ void *tee_get_drvdata(struct tee_device *teedev); > > */ > > struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); > > > > +struct tee_shm *tee_shm_alloc_dma_mem(struct tee_context *ctx, > > + size_t page_count); > > + > > int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, > > int (*shm_register)(struct tee_context *ctx, > > struct tee_shm *shm, > > -- > > 2.43.0 > >

1 hour, 52 minutes

Re: [PATCH v10 5/9] tee: new ioctl to a register tee_shm from a dmabuf file descriptor

by Jens Wiklander

On Tue, Jun 17, 2025 at 12:48 PM Sumit Garg <sumit.garg(a)kernel.org> wrote: > > On Tue, Jun 10, 2025 at 03:13:49PM +0200, Jens Wiklander wrote: > > From: Etienne Carriere <etienne.carriere(a)foss.st.com> > > > > Add a userspace API to create a tee_shm object that refers to a dmabuf > > reference. > > > > Userspace registers the dmabuf file descriptor as in a tee_shm object. > > The registration is completed with a tee_shm returned file descriptor. > > > > Userspace is free to close the dmabuf file descriptor after it has been > > registered since all the resources are now held via the new tee_shm > > object. > > > > Closing the tee_shm file descriptor will eventually release all > > resources used by the tee_shm object when all references are released. > > > > The new IOCTL, TEE_IOC_SHM_REGISTER_FD, supports dmabuf references to > > physically contiguous memory buffers. Dmabuf references acquired from > > the TEE DMA-heap can be used as protected memory for Secure Video Path > > and such use cases. It depends on the TEE and the TEE driver if dmabuf > > references acquired by other means can be used. > > > > A new tee_shm flag is added to identify tee_shm objects built from a > > registered dmabuf, TEE_SHM_DMA_BUF. > > > > Signed-off-by: Etienne Carriere <etienne.carriere(a)foss.st.com> > > Signed-off-by: Olivier Masse <olivier.masse(a)nxp.com> > > Signed-off-by: Jens Wiklander <jens.wiklander(a)linaro.org> > > --- > > drivers/tee/tee_core.c | 63 +++++++++++++++++++++- > > drivers/tee/tee_private.h | 10 ++++ > > drivers/tee/tee_shm.c | 106 ++++++++++++++++++++++++++++++++++++-- > > include/linux/tee_core.h | 1 + > > include/linux/tee_drv.h | 10 ++++ > > include/uapi/linux/tee.h | 31 +++++++++++ > > 6 files changed, 217 insertions(+), 4 deletions(-) > > > > diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c > > index 5259b8223c27..0e9d9e5872a4 100644 > > --- a/drivers/tee/tee_core.c > > +++ b/drivers/tee/tee_core.c > > @@ -353,11 +353,49 @@ tee_ioctl_shm_register(struct tee_context *ctx, > > return ret; > > } > > > > +static int > > +tee_ioctl_shm_register_fd(struct tee_context *ctx, > > + struct tee_ioctl_shm_register_fd_data __user *udata) > > +{ > > + struct tee_ioctl_shm_register_fd_data data; > > + struct tee_shm *shm; > > + long ret; > > + > > + if (copy_from_user(&data, udata, sizeof(data))) > > + return -EFAULT; > > + > > + /* Currently no input flags are supported */ > > + if (data.flags) > > + return -EINVAL; > > + > > + shm = tee_shm_register_fd(ctx, data.fd); > > + if (IS_ERR(shm)) > > + return -EINVAL; > > + > > + data.id = shm->id; > > + data.flags = shm->flags; > > + data.size = shm->size; > > + > > + if (copy_to_user(udata, &data, sizeof(data))) > > + ret = -EFAULT; > > + else > > + ret = tee_shm_get_fd(shm); > > + > > + /* > > + * When user space closes the file descriptor the shared memory > > + * should be freed or if tee_shm_get_fd() failed then it will > > + * be freed immediately. > > + */ > > + tee_shm_put(shm); > > + return ret; > > +} > > + > > static int param_from_user_memref(struct tee_context *ctx, > > struct tee_param_memref *memref, > > struct tee_ioctl_param *ip) > > { > > struct tee_shm *shm; > > + size_t offs = 0; > > > > /* > > * If a NULL pointer is passed to a TA in the TEE, > > @@ -388,6 +426,26 @@ static int param_from_user_memref(struct tee_context *ctx, > > tee_shm_put(shm); > > return -EINVAL; > > } > > + > > + if (shm->flags & TEE_SHM_DMA_BUF) { > > + struct tee_shm_dmabuf_ref *ref; > > + > > + ref = container_of(shm, struct tee_shm_dmabuf_ref, shm); > > + if (ref->parent_shm) { > > + /* > > + * The shm already has one reference to > > + * ref->parent_shm so we are clear of 0. > > + * We're getting another reference since > > + * this shm will be used in the parameter > > + * list instead of the shm we got with > > + * tee_shm_get_from_id() above. > > + */ > > + refcount_inc(&ref->parent_shm->refcount); > > + tee_shm_put(shm); > > + shm = ref->parent_shm; > > + offs = ref->offset; > > + } > > + } > > } else if (ctx->cap_memref_null) { > > /* Pass NULL pointer to OP-TEE */ > > shm = NULL; > > @@ -395,7 +453,7 @@ static int param_from_user_memref(struct tee_context *ctx, > > return -EINVAL; > > } > > > > - memref->shm_offs = ip->a; > > + memref->shm_offs = ip->a + offs; > > memref->size = ip->b; > > memref->shm = shm; > > > > @@ -841,6 +899,8 @@ static long tee_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) > > return tee_ioctl_shm_alloc(ctx, uarg); > > case TEE_IOC_SHM_REGISTER: > > return tee_ioctl_shm_register(ctx, uarg); > > + case TEE_IOC_SHM_REGISTER_FD: > > + return tee_ioctl_shm_register_fd(ctx, uarg); > > case TEE_IOC_OPEN_SESSION: > > return tee_ioctl_open_session(ctx, uarg); > > case TEE_IOC_INVOKE: > > @@ -1300,3 +1360,4 @@ MODULE_AUTHOR("Linaro"); > > MODULE_DESCRIPTION("TEE Driver"); > > MODULE_VERSION("1.0"); > > MODULE_LICENSE("GPL v2"); > > +MODULE_IMPORT_NS("DMA_BUF"); > > diff --git a/drivers/tee/tee_private.h b/drivers/tee/tee_private.h > > index 6c6ff5d5eed2..308467705da6 100644 > > --- a/drivers/tee/tee_private.h > > +++ b/drivers/tee/tee_private.h > > @@ -13,6 +13,16 @@ > > #include <linux/mutex.h> > > #include <linux/types.h> > > > > +/* extra references appended to shm object for registered shared memory */ > > +struct tee_shm_dmabuf_ref { > > + struct tee_shm shm; > > + size_t offset; > > + struct dma_buf *dmabuf; > > + struct dma_buf_attachment *attach; > > + struct sg_table *sgt; > > + struct tee_shm *parent_shm; > > +}; > > + > > int tee_shm_get_fd(struct tee_shm *shm); > > > > bool tee_device_get(struct tee_device *teedev); > > diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c > > index daf6e5cfd59a..e63095e84644 100644 > > --- a/drivers/tee/tee_shm.c > > +++ b/drivers/tee/tee_shm.c > > @@ -4,6 +4,7 @@ > > */ > > #include <linux/anon_inodes.h> > > #include <linux/device.h> > > +#include <linux/dma-buf.h> > > #include <linux/idr.h> > > #include <linux/io.h> > > #include <linux/mm.h> > > @@ -45,7 +46,21 @@ static void release_registered_pages(struct tee_shm *shm) > > > > static void tee_shm_release(struct tee_device *teedev, struct tee_shm *shm) > > { > > - if (shm->flags & TEE_SHM_POOL) { > > + void *p = shm; > > + > > + if (shm->flags & TEE_SHM_DMA_BUF) { > > + struct tee_shm_dmabuf_ref *ref; > > + > > + ref = container_of(shm, struct tee_shm_dmabuf_ref, shm); > > + p = ref; > > + if (ref->attach) { > > + dma_buf_unmap_attachment(ref->attach, ref->sgt, > > + DMA_BIDIRECTIONAL); > > + > > + dma_buf_detach(ref->dmabuf, ref->attach); > > + } > > + dma_buf_put(ref->dmabuf); > > + } else if (shm->flags & TEE_SHM_POOL) { > > teedev->pool->ops->free(teedev->pool, shm); > > } else if (shm->flags & TEE_SHM_DYNAMIC) { > > int rc = teedev->desc->ops->shm_unregister(shm->ctx, shm); > > @@ -59,7 +74,7 @@ static void tee_shm_release(struct tee_device *teedev, struct tee_shm *shm) > > > > teedev_ctx_put(shm->ctx); > > > > - kfree(shm); > > + kfree(p); > > > > tee_device_put(teedev); > > } > > @@ -169,7 +184,7 @@ struct tee_shm *tee_shm_alloc_user_buf(struct tee_context *ctx, size_t size) > > * tee_client_invoke_func(). The memory allocated is later freed with a > > * call to tee_shm_free(). > > * > > - * @returns a pointer to 'struct tee_shm' > > + * @returns a pointer to 'struct tee_shm' on success, and ERR_PTR on failure > > */ > > struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size) > > { > > @@ -179,6 +194,91 @@ struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size) > > } > > EXPORT_SYMBOL_GPL(tee_shm_alloc_kernel_buf); > > > > +struct tee_shm *tee_shm_register_fd(struct tee_context *ctx, int fd) > > +{ > > + struct tee_shm_dmabuf_ref *ref; > > + int rc; > > + > > + if (!tee_device_get(ctx->teedev)) > > + return ERR_PTR(-EINVAL); > > + > > + teedev_ctx_get(ctx); > > + > > + ref = kzalloc(sizeof(*ref), GFP_KERNEL); > > + if (!ref) { > > + rc = -ENOMEM; > > + goto err_put_tee; > > + } > > + > > + refcount_set(&ref->shm.refcount, 1); > > + ref->shm.ctx = ctx; > > + ref->shm.id = -1; > > + ref->shm.flags = TEE_SHM_DMA_BUF; > > + > > + ref->dmabuf = dma_buf_get(fd); > > + if (IS_ERR(ref->dmabuf)) { > > + rc = PTR_ERR(ref->dmabuf); > > + goto err_kfree_ref; > > + } > > + > > + rc = tee_heap_update_from_dma_buf(ctx->teedev, ref->dmabuf, > > + &ref->offset, &ref->shm, > > + &ref->parent_shm); > > + if (!rc) > > + goto out; > > One odd thing I find here, why do we bail out on success case here? > Don't we need the DMA buffer attach and map APIs to be invoked on > success case here? No, because if tee_heap_update_from_dma_buf() succeeds, we know everything we need about the buffer. Note that we're returning a valid pointer below to indicate success. Cheers, Jens > > -Sumit > > > + if (rc != -EINVAL) > > + goto err_put_dmabuf; > > + > > + ref->attach = dma_buf_attach(ref->dmabuf, &ctx->teedev->dev); > > + if (IS_ERR(ref->attach)) { > > + rc = PTR_ERR(ref->attach); > > + goto err_put_dmabuf; > > + } > > + > > + ref->sgt = dma_buf_map_attachment(ref->attach, DMA_BIDIRECTIONAL); > > + if (IS_ERR(ref->sgt)) { > > + rc = PTR_ERR(ref->sgt); > > + goto err_detach; > > + } > > + > > + if (sg_nents(ref->sgt->sgl) != 1) { > > + rc = -EINVAL; > > + goto err_unmap_attachement; > > + } > > + > > + ref->shm.paddr = page_to_phys(sg_page(ref->sgt->sgl)); > > + ref->shm.size = ref->sgt->sgl->length; > > + > > +out: > > + mutex_lock(&ref->shm.ctx->teedev->mutex); > > + ref->shm.id = idr_alloc(&ref->shm.ctx->teedev->idr, &ref->shm, > > + 1, 0, GFP_KERNEL); > > + mutex_unlock(&ref->shm.ctx->teedev->mutex); > > + if (ref->shm.id < 0) { > > + rc = ref->shm.id; > > + if (ref->attach) > > + goto err_unmap_attachement; > > + goto err_put_dmabuf; > > + } > > + > > + return &ref->shm; > > + > > +err_unmap_attachement: > > + dma_buf_unmap_attachment(ref->attach, ref->sgt, DMA_BIDIRECTIONAL); > > +err_detach: > > + dma_buf_detach(ref->dmabuf, ref->attach); > > +err_put_dmabuf: > > + dma_buf_put(ref->dmabuf); > > +err_kfree_ref: > > + kfree(ref); > > +err_put_tee: > > + teedev_ctx_put(ctx); > > + tee_device_put(ctx->teedev); > > + > > + return ERR_PTR(rc); > > +} > > +EXPORT_SYMBOL_GPL(tee_shm_register_fd); > > + > > /** > > * tee_shm_alloc_priv_buf() - Allocate shared memory for a privately shared > > * kernel buffer > > diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h > > index 22e03d897dc3..f17710196c4c 100644 > > --- a/include/linux/tee_core.h > > +++ b/include/linux/tee_core.h > > @@ -28,6 +28,7 @@ > > #define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ > > #define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ > > #define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ > > +#define TEE_SHM_DMA_BUF BIT(4) /* Memory with dma-buf handle */ > > > > #define TEE_DEVICE_FLAG_REGISTERED 0x1 > > #define TEE_MAX_DEV_NAME_LEN 32 > > diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h > > index a54c203000ed..824f1251de60 100644 > > --- a/include/linux/tee_drv.h > > +++ b/include/linux/tee_drv.h > > @@ -116,6 +116,16 @@ struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); > > struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, > > void *addr, size_t length); > > > > +/** > > + * tee_shm_register_fd() - Register shared memory from file descriptor > > + * > > + * @ctx: Context that allocates the shared memory > > + * @fd: Shared memory file descriptor reference > > + * > > + * @returns a pointer to 'struct tee_shm' on success, and ERR_PTR on failure > > + */ > > +struct tee_shm *tee_shm_register_fd(struct tee_context *ctx, int fd); > > + > > /** > > * tee_shm_free() - Free shared memory > > * @shm: Handle to shared memory to free > > diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h > > index d0430bee8292..d843cf980d98 100644 > > --- a/include/uapi/linux/tee.h > > +++ b/include/uapi/linux/tee.h > > @@ -378,6 +378,37 @@ struct tee_ioctl_shm_register_data { > > __s32 id; > > }; > > > > +/** > > + * struct tee_ioctl_shm_register_fd_data - Shared memory registering argument > > + * @fd: [in] File descriptor identifying dmabuf reference > > + * @size: [out] Size of referenced memory > > + * @flags: [in] Flags to/from allocation. > > + * @id: [out] Identifier of the shared memory > > + * > > + * The flags field should currently be zero as input. Updated by the call > > + * with actual flags as defined by TEE_IOCTL_SHM_* above. > > + * This structure is used as argument for TEE_IOC_SHM_REGISTER_FD below. > > + */ > > +struct tee_ioctl_shm_register_fd_data { > > + __s64 fd; > > + __u64 size; > > + __u32 flags; > > + __s32 id; > > +}; > > + > > +/** > > + * TEE_IOC_SHM_REGISTER_FD - register a shared memory from a file descriptor > > + * > > + * Returns a file descriptor on success or < 0 on failure > > + * > > + * The returned file descriptor refers to the shared memory object in the > > + * kernel. The supplied file deccriptor can be closed if it's not needed > > + * for other purposes. The shared memory is freed when the descriptor is > > + * closed. > > + */ > > +#define TEE_IOC_SHM_REGISTER_FD _IOWR(TEE_IOC_MAGIC, TEE_IOC_BASE + 8, \ > > + struct tee_ioctl_shm_register_fd_data) > > + > > /** > > * TEE_IOC_SHM_REGISTER - Register shared memory argument > > * > > -- > > 2.43.0 > >

2 hours, 7 minutes

[PATCH v5 0/2] dma-buf: heaps: Support carved-out heaps

by Maxime Ripard

Hi, This series is the follow-up of the discussion that John and I had some time ago here: https://lore.kernel.org/all/CANDhNCquJn6bH3KxKf65BWiTYLVqSd9892-xtFDHHqqyrr… The initial problem we were discussing was that I'm currently working on a platform which has a memory layout with ECC enabled. However, enabling the ECC has a number of drawbacks on that platform: lower performance, increased memory usage, etc. So for things like framebuffers, the trade-off isn't great and thus there's a memory region with ECC disabled to allocate from for such use cases. After a suggestion from John, I chose to first start using heap allocations flags to allow for userspace to ask for a particular ECC setup. This is then backed by a new heap type that runs from reserved memory chunks flagged as such, and the existing DT properties to specify the ECC properties. After further discussion, it was considered that flags were not the right solution, and relying on the names of the heaps would be enough to let userspace know the kind of buffer it deals with. Thus, even though the uAPI part of it has been dropped in this second version, we still need a driver to create heaps out of carved-out memory regions. In addition to the original usecase, a similar driver can be found in BSPs from most vendors, so I believe it would be a useful addition to the kernel. Let me know what you think, Maxime Signed-off-by: Maxime Ripard <mripard(a)kernel.org> --- Changes in v5: - Rebased on 6.16-rc2 - Switch from property to dedicated binding - Link to v4: https://lore.kernel.org/r/20250520-dma-buf-ecc-heap-v4-1-bd2e1f1bb42c@kerne… Changes in v4: - Rebased on 6.15-rc7 - Map buffers only when map is actually called, not at allocation time - Deal with restricted-dma-pool and shared-dma-pool - Reword Kconfig options - Properly report dma_map_sgtable failures - Link to v3: https://lore.kernel.org/r/20250407-dma-buf-ecc-heap-v3-0-97cdd36a5f29@kerne… Changes in v3: - Reworked global variable patch - Link to v2: https://lore.kernel.org/r/20250401-dma-buf-ecc-heap-v2-0-043fd006a1af@kerne… Changes in v2: - Add vmap/vunmap operations - Drop ECC flags uapi - Rebase on top of 6.14 - Link to v1: https://lore.kernel.org/r/20240515-dma-buf-ecc-heap-v1-0-54cbbd049511@kerne… --- Maxime Ripard (2): dt-bindings: reserved-memory: Introduce carved-out memory region binding dma-buf: heaps: Introduce a new heap for reserved memory .../bindings/reserved-memory/carved-out.yaml | 49 +++ drivers/dma-buf/heaps/Kconfig | 8 + drivers/dma-buf/heaps/Makefile | 1 + drivers/dma-buf/heaps/carveout_heap.c | 362 +++++++++++++++++++++ 4 files changed, 420 insertions(+) --- base-commit: d076bed8cb108ba2236d4d49c92303fda4036893 change-id: 20240515-dma-buf-ecc-heap-28a311d2c94e Best regards, -- Maxime Ripard <mripard(a)kernel.org>

20 hours, 29 minutes

[PATCH v2] Documentation: dma-buf: heaps: Add naming guidelines

by Maxime Ripard

We've discussed a number of times of how some heap names are bad, but not really what makes a good heap name. Let's document what we expect the heap names to look like. Reviewed-by: Bagas Sanjaya <bagasdotme(a)gmail.com> Signed-off-by: Maxime Ripard <mripard(a)kernel.org> --- Changes in v2: - Added justifications for each requirement / suggestions - Added a mention and example of buffer attributes - Link to v1: https://lore.kernel.org/r/20250520-dma-buf-heap-names-doc-v1-1-ab31f74809ee… --- Documentation/userspace-api/dma-buf-heaps.rst | 38 +++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/Documentation/userspace-api/dma-buf-heaps.rst b/Documentation/userspace-api/dma-buf-heaps.rst index 535f49047ce6450796bf4380c989e109355efc05..835ad1c3a65bc07b6f41d387d85c57162909e859 100644 --- a/Documentation/userspace-api/dma-buf-heaps.rst +++ b/Documentation/userspace-api/dma-buf-heaps.rst @@ -21,5 +21,43 @@ following heaps: usually created either through the kernel commandline through the `cma` parameter, a memory region Device-Tree node with the `linux,cma-default` property set, or through the `CMA_SIZE_MBYTES` or `CMA_SIZE_PERCENTAGE` Kconfig options. Depending on the platform, it might be called ``reserved``, ``linux,cma``, or ``default-pool``. + +Naming Convention +================= + +``dma-buf`` heaps name should meet a number of constraints: + +- That name must be stable, and must not change from one version to the + other. Userspace identifies heaps by their name, so if the names ever + changes, we would be likely to introduce regressions. + +- That name must describe the memory region the heap will allocate from, + and must uniquely identify it in a given platform. Since userspace + applications use the heap name as the discriminant, it must be able to + tell which heap it wants to use reliably if there's multiple heaps. + +- That name must not mention implementation details, such as the + allocator. The heap driver will change over time, and implementation + details when it was introduced might not be relevant in the future. + +- The name should describe properties of the buffers that would be + allocated. Doing so will make heap identification easier for + userspace. Such properties are: + + - ``cacheable`` / ``uncacheable`` for buffers with CPU caches enabled + or disabled; + + - ``contiguous`` for physically contiguous buffers; + + - ``protected`` for encrypted buffers not accessible the OS; + +- The name may describe intended usage. Doing so will make heap + identification easier for userspace applications and users. + +For example, assuming a platform with a reserved memory region located +at the RAM address 0x42000000, intended to allocate video framebuffers, +physically contiguous, and backed by the CMA kernel allocator. Good +names would be ``memory@42000000-cacheable-contiguous`` or +``video@42000000``, but ``cma-video`` wouldn't. --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250520-dma-buf-heap-names-doc-31261aa0cfe6 Best regards, -- Maxime Ripard <mripard(a)kernel.org>

1 day, 16 hours

[PATCH] Documentation: dma-buf: heaps: Add naming guidelines

by Maxime Ripard

We've discussed a number of times of how some heap names are bad, but not really what makes a good heap name. Let's document what we expect the heap names to look like. Signed-off-by: Maxime Ripard <mripard(a)kernel.org> --- Documentation/userspace-api/dma-buf-heaps.rst | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/Documentation/userspace-api/dma-buf-heaps.rst b/Documentation/userspace-api/dma-buf-heaps.rst index 535f49047ce6450796bf4380c989e109355efc05..b24618e360a9a9ba0bd85135d8c1760776f1a37f 100644 --- a/Documentation/userspace-api/dma-buf-heaps.rst +++ b/Documentation/userspace-api/dma-buf-heaps.rst @@ -21,5 +21,24 @@ following heaps: usually created either through the kernel commandline through the `cma` parameter, a memory region Device-Tree node with the `linux,cma-default` property set, or through the `CMA_SIZE_MBYTES` or `CMA_SIZE_PERCENTAGE` Kconfig options. Depending on the platform, it might be called ``reserved``, ``linux,cma``, or ``default-pool``. + +Naming Convention +================= + +A good heap name is a name that: + +- Is stable, and won't change from one version to the other; + +- Describes the memory region the heap will allocate from, and will + uniquely identify it in a given platform; + +- Doesn't use implementation details, such as the allocator; + +- Can describe intended usage. + +For example, assuming a platform with a reserved memory region located +at the RAM address 0x42000000, intended to allocate video framebuffers, +and backed by the CMA kernel allocator. Good names would be +`memory@42000000` or `video@42000000`, but `cma-video` wouldn't. --- base-commit: 92a09c47464d040866cf2b4cd052bc60555185fb change-id: 20250520-dma-buf-heap-names-doc-31261aa0cfe6 Best regards, -- Maxime Ripard <mripard(a)kernel.org>

1 day, 17 hours

Re: [PATCH v4 0/4] Implement dmabuf direct I/O via copy_file_range

by Christoph Hellwig

On Fri, Jun 13, 2025 at 09:33:55AM +0000, wangtao wrote: > > > > > On Mon, Jun 09, 2025 at 09:32:20AM +0000, wangtao wrote: > > > Are you suggesting adding an ITER_DMABUF type to iov_iter, > > > > Yes. > > May I clarify: Do all disk operations require data to pass through > memory (reading into memory or writing from memory)? In the block layer, > the bio structure uses bio_iov_iter_get_pages to convert iter_type > objects into memory-backed bio_vec representations. > However, some dmabufs are not memory-based, making page-to-bio_vec > conversion impossible. This suggests adding a callback function in > dma_buf_ops to handle dmabuf- to-bio_vec conversion. bios do support PCI P2P tranfers. This could be fairly easily extended to other peer to peer transfers if we manage to come up with a coherent model for them. No need for a callback.

2 days, 3 hours

Re: [PATCH v4 0/4] Implement dmabuf direct I/O via copy_file_range

by Christoph Hellwig

On Fri, Jun 13, 2025 at 09:43:08AM +0000, wangtao wrote: > Here's my analysis on Linux 6.6 with F2FS/iomap. Linux 6.6 is almost two years old and completely irrelevant. Please provide numbers on 6.16 or current Linus' tree.

2 days, 3 hours

Re: [PATCH v5 03/12] tee: add TEE_IOCTL_PARAM_ATTR_TYPE_UBUF

by Andrew Davis

On 5/27/25 1:56 AM, Amirreza Zarrabi wrote: > For drivers that can transfer data to the TEE without using shared > memory from client, it is necessary to receive the user address > directly, bypassing any processing by the TEE subsystem. Introduce > TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INPUT/OUTPUT/INOUT to represent > userspace buffers. > Could you expand on this, what is the issue with normal MEMREF? Andrew > Reviewed-by: Sumit Garg <sumit.garg(a)oss.qualcomm.com> > Tested-by: Neil Armstrong <neil.armstrong(a)linaro.org> > Signed-off-by: Amirreza Zarrabi <amirreza.zarrabi(a)oss.qualcomm.com> > --- > drivers/tee/tee_core.c | 33 +++++++++++++++++++++++++++++++++ > include/linux/tee_drv.h | 6 ++++++ > include/uapi/linux/tee.h | 22 ++++++++++++++++------ > 3 files changed, 55 insertions(+), 6 deletions(-) > > diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c > index b9ea5a85278c..74e40ed83fa7 100644 > --- a/drivers/tee/tee_core.c > +++ b/drivers/tee/tee_core.c > @@ -387,6 +387,17 @@ static int params_from_user(struct tee_context *ctx, struct tee_param *params, > params[n].u.value.b = ip.b; > params[n].u.value.c = ip.c; > break; > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INPUT: > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_OUTPUT: > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INOUT: > + params[n].u.ubuf.uaddr = u64_to_user_ptr(ip.a); > + params[n].u.ubuf.size = ip.b; > + > + if (!access_ok(params[n].u.ubuf.uaddr, > + params[n].u.ubuf.size)) > + return -EFAULT; > + > + break; > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: > @@ -455,6 +466,11 @@ static int params_to_user(struct tee_ioctl_param __user *uparams, > put_user(p->u.value.c, &up->c)) > return -EFAULT; > break; > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_OUTPUT: > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INOUT: > + if (put_user((u64)p->u.ubuf.size, &up->b)) > + return -EFAULT; > + break; > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: > if (put_user((u64)p->u.memref.size, &up->b)) > @@ -655,6 +671,13 @@ static int params_to_supp(struct tee_context *ctx, > ip.b = p->u.value.b; > ip.c = p->u.value.c; > break; > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INPUT: > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_OUTPUT: > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INOUT: > + ip.a = (u64)p->u.ubuf.uaddr; > + ip.b = p->u.ubuf.size; > + ip.c = 0; > + break; > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: > @@ -757,6 +780,16 @@ static int params_from_supp(struct tee_param *params, size_t num_params, > p->u.value.b = ip.b; > p->u.value.c = ip.c; > break; > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_OUTPUT: > + case TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INOUT: > + p->u.ubuf.uaddr = u64_to_user_ptr(ip.a); > + p->u.ubuf.size = ip.b; > + > + if (!access_ok(params[n].u.ubuf.uaddr, > + params[n].u.ubuf.size)) > + return -EFAULT; > + > + break; > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: > case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: > /* > diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h > index a54c203000ed..78bbf12f02f0 100644 > --- a/include/linux/tee_drv.h > +++ b/include/linux/tee_drv.h > @@ -82,6 +82,11 @@ struct tee_param_memref { > struct tee_shm *shm; > }; > > +struct tee_param_ubuf { > + void * __user uaddr; > + size_t size; > +}; > + > struct tee_param_value { > u64 a; > u64 b; > @@ -92,6 +97,7 @@ struct tee_param { > u64 attr; > union { > struct tee_param_memref memref; > + struct tee_param_ubuf ubuf; > struct tee_param_value value; > } u; > }; > diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h > index d0430bee8292..3e9b1ec5dfde 100644 > --- a/include/uapi/linux/tee.h > +++ b/include/uapi/linux/tee.h > @@ -151,6 +151,13 @@ struct tee_ioctl_buf_data { > #define TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT 6 > #define TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT 7 /* input and output */ > > +/* > + * These defines userspace buffer parameters. > + */ > +#define TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INPUT 8 > +#define TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_OUTPUT 9 > +#define TEE_IOCTL_PARAM_ATTR_TYPE_UBUF_INOUT 10 /* input and output */ > + > /* > * Mask for the type part of the attribute, leaves room for more types > */ > @@ -186,14 +193,17 @@ struct tee_ioctl_buf_data { > /** > * struct tee_ioctl_param - parameter > * @attr: attributes > - * @a: if a memref, offset into the shared memory object, else a value parameter > - * @b: if a memref, size of the buffer, else a value parameter > + * @a: if a memref, offset into the shared memory object, > + * else if a ubuf, address of the user buffer, > + * else a value parameter > + * @b: if a memref or ubuf, size of the buffer, else a value parameter > * @c: if a memref, shared memory identifier, else a value parameter > * > - * @attr & TEE_PARAM_ATTR_TYPE_MASK indicates if memref or value is used in > - * the union. TEE_PARAM_ATTR_TYPE_VALUE_* indicates value and > - * TEE_PARAM_ATTR_TYPE_MEMREF_* indicates memref. TEE_PARAM_ATTR_TYPE_NONE > - * indicates that none of the members are used. > + * @attr & TEE_PARAM_ATTR_TYPE_MASK indicates if memref, ubuf, or value is > + * used in the union. TEE_PARAM_ATTR_TYPE_VALUE_* indicates value, > + * TEE_PARAM_ATTR_TYPE_MEMREF_* indicates memref, and TEE_PARAM_ATTR_TYPE_UBUF_* > + * indicates ubuf. TEE_PARAM_ATTR_TYPE_NONE indicates that none of the members > + * are used. > * > * Shared memory is allocated with TEE_IOC_SHM_ALLOC which returns an > * identifier representing the shared memory object. A memref can reference >

6 days, 10 hours

Re: [PATCH v6 1/4] sync_file: Protect access to driver and timeline name

by Christian König

On 6/10/25 18:42, Tvrtko Ursulin wrote: > Protect the access to driver and timeline name which otherwise could be > freed as dma-fence exported is signalling fences. > > This prepares the code for incoming dma-fence API changes which will start > asserting these accesses are done from a RCU locked section. > > Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Reviewed-by: Christian König <christian.koenig(a)amd.com> > --- > drivers/dma-buf/sync_file.c | 24 ++++++++++++++++++++---- > 1 file changed, 20 insertions(+), 4 deletions(-) > > diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c > index 212df4b849fe..747e377fb954 100644 > --- a/drivers/dma-buf/sync_file.c > +++ b/drivers/dma-buf/sync_file.c > @@ -135,12 +135,18 @@ char *sync_file_get_name(struct sync_file *sync_file, char *buf, int len) > strscpy(buf, sync_file->user_name, len); > } else { > struct dma_fence *fence = sync_file->fence; > + const char __rcu *timeline; > + const char __rcu *driver; > > + rcu_read_lock(); > + driver = dma_fence_driver_name(fence); > + timeline = dma_fence_timeline_name(fence); > snprintf(buf, len, "%s-%s%llu-%lld", > - dma_fence_driver_name(fence), > - dma_fence_timeline_name(fence), > + rcu_dereference(driver), > + rcu_dereference(timeline), > fence->context, > fence->seqno); > + rcu_read_unlock(); > } > > return buf; > @@ -262,9 +268,17 @@ static long sync_file_ioctl_merge(struct sync_file *sync_file, > static int sync_fill_fence_info(struct dma_fence *fence, > struct sync_fence_info *info) > { > - strscpy(info->obj_name, dma_fence_timeline_name(fence), > + const char __rcu *timeline; > + const char __rcu *driver; > + > + rcu_read_lock(); > + > + driver = dma_fence_driver_name(fence); > + timeline = dma_fence_timeline_name(fence); > + > + strscpy(info->obj_name, rcu_dereference(timeline), > sizeof(info->obj_name)); > - strscpy(info->driver_name, dma_fence_driver_name(fence), > + strscpy(info->driver_name, rcu_dereference(driver), > sizeof(info->driver_name)); > > info->status = dma_fence_get_status(fence); > @@ -273,6 +287,8 @@ static int sync_fill_fence_info(struct dma_fence *fence, > ktime_to_ns(dma_fence_timestamp(fence)) : > ktime_set(0, 0); > > + rcu_read_unlock(); > + > return info->status; > } >

6 days, 21 hours

Re: [PATCH v6 3/4] dma-fence: Add safe access helpers and document the rules

by Christian König

On 6/10/25 18:42, Tvrtko Ursulin wrote: > Dma-fence objects currently suffer from a potential use after free problem > where fences exported to userspace and other drivers can outlive the > exporting driver, or the associated data structures. > > The discussion on how to address this concluded that adding reference > counting to all the involved objects is not desirable, since it would need > to be very wide reaching and could cause unloadable drivers if another > entity would be holding onto a signaled fence reference potentially > indefinitely. > > This patch enables the safe access by introducing and documenting a > contract between fence exporters and users. It documents a set of > contraints and adds helpers which a) drivers with potential to suffer from > the use after free must use and b) users of the dma-fence API must use as > well. > > Premise of the design has multiple sides: > > 1. Drivers (fence exporters) MUST ensure a RCU grace period between > signalling a fence and freeing the driver private data associated with it. > > The grace period does not have to follow the signalling immediately but > HAS to happen before data is freed. > > 2. Users of the dma-fence API marked with such requirement MUST contain > the complete access to the data within a single code block guarded by > rcu_read_lock() and rcu_read_unlock(). > > The combination of the two ensures that whoever sees the > DMA_FENCE_FLAG_SIGNALED_BIT not set is guaranteed to have access to a > valid fence->lock and valid data potentially accessed by the fence->ops > virtual functions, until the call to rcu_read_unlock(). > > 3. Module unload (fence->ops) disappearing is for now explicitly not > handled. That would required a more complex protection, possibly needing > SRCU instead of RCU to handle callers such as dma_fence_release() and > dma_fence_wait_timeout(), where race between > dma_fence_enable_sw_signaling, signalling, and dereference of > fence->ops->wait() would need a sleeping SRCU context. > > Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Reviewed-by: Christian König <christian.koenig(a)amd.com> > --- > drivers/dma-buf/dma-fence.c | 111 ++++++++++++++++++++++++++++--- > include/linux/dma-fence.h | 31 ++++++--- > include/trace/events/dma_fence.h | 38 +++++++++-- > 3 files changed, 157 insertions(+), 23 deletions(-) > > diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c > index 74f9e4b665e3..3f78c56b58dc 100644 > --- a/drivers/dma-buf/dma-fence.c > +++ b/drivers/dma-buf/dma-fence.c > @@ -511,12 +511,20 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout) > > dma_fence_enable_sw_signaling(fence); > > - trace_dma_fence_wait_start(fence); > + if (trace_dma_fence_wait_start_enabled()) { > + rcu_read_lock(); > + trace_dma_fence_wait_start(fence); > + rcu_read_unlock(); > + } > if (fence->ops->wait) > ret = fence->ops->wait(fence, intr, timeout); > else > ret = dma_fence_default_wait(fence, intr, timeout); > - trace_dma_fence_wait_end(fence); > + if (trace_dma_fence_wait_end_enabled()) { > + rcu_read_lock(); > + trace_dma_fence_wait_end(fence); > + rcu_read_unlock(); > + } > return ret; > } > EXPORT_SYMBOL(dma_fence_wait_timeout); > @@ -533,16 +541,23 @@ void dma_fence_release(struct kref *kref) > struct dma_fence *fence = > container_of(kref, struct dma_fence, refcount); > > + rcu_read_lock(); > trace_dma_fence_destroy(fence); > > - if (WARN(!list_empty(&fence->cb_list) && > - !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags), > - "Fence %s:%s:%llx:%llx released with pending signals!\n", > - dma_fence_driver_name(fence), > - dma_fence_timeline_name(fence), > - fence->context, fence->seqno)) { > + if (!list_empty(&fence->cb_list) && > + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) { > + const char __rcu *timeline; > + const char __rcu *driver; > unsigned long flags; > > + driver = dma_fence_driver_name(fence); > + timeline = dma_fence_timeline_name(fence); > + > + WARN(1, > + "Fence %s:%s:%llx:%llx released with pending signals!\n", > + rcu_dereference(driver), rcu_dereference(timeline), > + fence->context, fence->seqno); > + > /* > * Failed to signal before release, likely a refcounting issue. > * > @@ -556,6 +571,8 @@ void dma_fence_release(struct kref *kref) > spin_unlock_irqrestore(fence->lock, flags); > } > > + rcu_read_unlock(); > + > if (fence->ops->release) > fence->ops->release(fence); > else > @@ -982,11 +999,21 @@ EXPORT_SYMBOL(dma_fence_set_deadline); > */ > void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq) > { > + const char __rcu *timeline; > + const char __rcu *driver; > + > + rcu_read_lock(); > + > + timeline = dma_fence_timeline_name(fence); > + driver = dma_fence_driver_name(fence); > + > seq_printf(seq, "%s %s seq %llu %ssignalled\n", > - dma_fence_driver_name(fence), > - dma_fence_timeline_name(fence), > + rcu_dereference(driver), > + rcu_dereference(timeline), > fence->seqno, > dma_fence_is_signaled(fence) ? "" : "un"); > + > + rcu_read_unlock(); > } > EXPORT_SYMBOL(dma_fence_describe); > > @@ -1055,3 +1082,67 @@ dma_fence_init64(struct dma_fence *fence, const struct dma_fence_ops *ops, > BIT(DMA_FENCE_FLAG_SEQNO64_BIT)); > } > EXPORT_SYMBOL(dma_fence_init64); > + > +/** > + * dma_fence_driver_name - Access the driver name > + * @fence: the fence to query > + * > + * Returns a driver name backing the dma-fence implementation. > + * > + * IMPORTANT CONSIDERATION: > + * Dma-fence contract stipulates that access to driver provided data (data not > + * directly embedded into the object itself), such as the &dma_fence.lock and > + * memory potentially accessed by the &dma_fence.ops functions, is forbidden > + * after the fence has been signalled. Drivers are allowed to free that data, > + * and some do. > + * > + * To allow safe access drivers are mandated to guarantee a RCU grace period > + * between signalling the fence and freeing said data. > + * > + * As such access to the driver name is only valid inside a RCU locked section. > + * The pointer MUST be both queried and USED ONLY WITHIN a SINGLE block guarded > + * by the &rcu_read_lock and &rcu_read_unlock pair. > + */ > +const char __rcu *dma_fence_driver_name(struct dma_fence *fence) > +{ > + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), > + "RCU protection is required for safe access to returned string"); > + > + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) > + return fence->ops->get_driver_name(fence); > + else > + return "detached-driver"; > +} > +EXPORT_SYMBOL(dma_fence_driver_name); > + > +/** > + * dma_fence_timeline_name - Access the timeline name > + * @fence: the fence to query > + * > + * Returns a timeline name provided by the dma-fence implementation. > + * > + * IMPORTANT CONSIDERATION: > + * Dma-fence contract stipulates that access to driver provided data (data not > + * directly embedded into the object itself), such as the &dma_fence.lock and > + * memory potentially accessed by the &dma_fence.ops functions, is forbidden > + * after the fence has been signalled. Drivers are allowed to free that data, > + * and some do. > + * > + * To allow safe access drivers are mandated to guarantee a RCU grace period > + * between signalling the fence and freeing said data. > + * > + * As such access to the driver name is only valid inside a RCU locked section. > + * The pointer MUST be both queried and USED ONLY WITHIN a SINGLE block guarded > + * by the &rcu_read_lock and &rcu_read_unlock pair. > + */ > +const char __rcu *dma_fence_timeline_name(struct dma_fence *fence) > +{ > + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), > + "RCU protection is required for safe access to returned string"); > + > + if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) > + return fence->ops->get_driver_name(fence); > + else > + return "signaled-timeline"; > +} > +EXPORT_SYMBOL(dma_fence_timeline_name); > diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h > index 10a849cb2d3f..64639e104110 100644 > --- a/include/linux/dma-fence.h > +++ b/include/linux/dma-fence.h > @@ -378,15 +378,28 @@ bool dma_fence_remove_callback(struct dma_fence *fence, > struct dma_fence_cb *cb); > void dma_fence_enable_sw_signaling(struct dma_fence *fence); > > -static inline const char *dma_fence_driver_name(struct dma_fence *fence) > -{ > - return fence->ops->get_driver_name(fence); > -} > - > -static inline const char *dma_fence_timeline_name(struct dma_fence *fence) > -{ > - return fence->ops->get_timeline_name(fence); > -} > +/** > + * DOC: Safe external access to driver provided object members > + * > + * All data not stored directly in the dma-fence object, such as the > + * &dma_fence.lock and memory potentially accessed by functions in the > + * &dma_fence.ops table, MUST NOT be accessed after the fence has been signalled > + * because after that point drivers are allowed to free it. > + * > + * All code accessing that data via the dma-fence API (or directly, which is > + * discouraged), MUST make sure to contain the complete access within a > + * &rcu_read_lock and &rcu_read_unlock pair. > + * > + * Some dma-fence API handles this automatically, while other, as for example > + * &dma_fence_driver_name and &dma_fence_timeline_name, leave that > + * responsibility to the caller. > + * > + * To enable this scheme to work drivers MUST ensure a RCU grace period elapses > + * between signalling the fence and freeing the said data. > + * > + */ > +const char __rcu *dma_fence_driver_name(struct dma_fence *fence); > +const char __rcu *dma_fence_timeline_name(struct dma_fence *fence); > > /** > * dma_fence_is_signaled_locked - Return an indication if the fence > diff --git a/include/trace/events/dma_fence.h b/include/trace/events/dma_fence.h > index 84c83074ee81..4814a65b68dc 100644 > --- a/include/trace/events/dma_fence.h > +++ b/include/trace/events/dma_fence.h > @@ -34,14 +34,44 @@ DECLARE_EVENT_CLASS(dma_fence, > __entry->seqno) > ); > > -DEFINE_EVENT(dma_fence, dma_fence_emit, > +/* > + * Safe only for call sites which are guaranteed to not race with fence > + * signaling,holding the fence->lock and having checked for not signaled, or the > + * signaling path itself. > + */ > +DECLARE_EVENT_CLASS(dma_fence_unsignaled, > + > + TP_PROTO(struct dma_fence *fence), > + > + TP_ARGS(fence), > + > + TP_STRUCT__entry( > + __string(driver, fence->ops->get_driver_name(fence)) > + __string(timeline, fence->ops->get_timeline_name(fence)) > + __field(unsigned int, context) > + __field(unsigned int, seqno) > + ), > + > + TP_fast_assign( > + __assign_str(driver); > + __assign_str(timeline); > + __entry->context = fence->context; > + __entry->seqno = fence->seqno; > + ), > + > + TP_printk("driver=%s timeline=%s context=%u seqno=%u", > + __get_str(driver), __get_str(timeline), __entry->context, > + __entry->seqno) > +); > + > +DEFINE_EVENT(dma_fence_unsignaled, dma_fence_emit, > > TP_PROTO(struct dma_fence *fence), > > TP_ARGS(fence) > ); > > -DEFINE_EVENT(dma_fence, dma_fence_init, > +DEFINE_EVENT(dma_fence_unsignaled, dma_fence_init, > > TP_PROTO(struct dma_fence *fence), > > @@ -55,14 +85,14 @@ DEFINE_EVENT(dma_fence, dma_fence_destroy, > TP_ARGS(fence) > ); > > -DEFINE_EVENT(dma_fence, dma_fence_enable_signal, > +DEFINE_EVENT(dma_fence_unsignaled, dma_fence_enable_signal, > > TP_PROTO(struct dma_fence *fence), > > TP_ARGS(fence) > ); > > -DEFINE_EVENT(dma_fence, dma_fence_signaled, > +DEFINE_EVENT(dma_fence_unsignaled, dma_fence_signaled, > > TP_PROTO(struct dma_fence *fence), >

6 days, 21 hours

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig