On Tue, May 20, 2025 at 05:16:44PM +0200, Jens Wiklander wrote:

Update the header files describing the secure world ABI, both with and without FF-A. The ABI is extended to deal with protected memory, but as usual backward compatible.

Signed-off-by: Jens Wiklander jens.wiklander@linaro.org

drivers/tee/optee/optee_ffa.h | 27 ++++++++--- drivers/tee/optee/optee_msg.h | 84 ++++++++++++++++++++++++++++++----- drivers/tee/optee/optee_smc.h | 37 ++++++++++++++- 3 files changed, 130 insertions(+), 18 deletions(-)

Reviewed-by: Sumit Garg sumit.garg@oss.qualcomm.com

-Sumit

diff --git a/drivers/tee/optee/optee_ffa.h b/drivers/tee/optee/optee_ffa.h index 257735ae5b56..cc257e7956a3 100644 --- a/drivers/tee/optee/optee_ffa.h +++ b/drivers/tee/optee/optee_ffa.h @@ -81,7 +81,7 @@

•               as the second MSG arg struct for
  

•               OPTEE_FFA_YIELDING_CALL_WITH_ARG.
  

•    Bit[31:8]: Reserved (MBZ)
  

• • w5: Bitfield of secure world capabilities OPTEE_FFA_SEC_CAP_* below,

• • w5: Bitfield of OP-TEE capabilities OPTEE_FFA_SEC_CAP_*
  • w6: The maximum secure world notification number
  • w7: Not used (MBZ)
  */

@@ -94,6 +94,8 @@ #define OPTEE_FFA_SEC_CAP_ASYNC_NOTIF BIT(1) /* OP-TEE supports probing for RPMB device if needed */ #define OPTEE_FFA_SEC_CAP_RPMB_PROBE BIT(2) +/* OP-TEE supports Protected Memory for secure data path */ +#define OPTEE_FFA_SEC_CAP_PROTMEM BIT(3) #define OPTEE_FFA_EXCHANGE_CAPABILITIES OPTEE_FFA_BLOCKING_CALL(2) @@ -108,7 +110,7 @@

• Return register usage:
• w3: Error code, 0 on success

• • w4-w7: Note used (MBZ)

• • w4-w7: Not used (MBZ)
  */

#define OPTEE_FFA_UNREGISTER_SHM OPTEE_FFA_BLOCKING_CALL(3) @@ -119,16 +121,31 @@

• Call register usage:
• w3: Service ID, OPTEE_FFA_ENABLE_ASYNC_NOTIF
• w4: Notification value to request bottom half processing, should be

• •  less than OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE.
    

• •  less than OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE
    

  • w5-w7: Not used (MBZ)
  • Return register usage:
  • w3: Error code, 0 on success

• • w4-w7: Note used (MBZ)

• • w4-w7: Not used (MBZ)
  */

#define OPTEE_FFA_ENABLE_ASYNC_NOTIF OPTEE_FFA_BLOCKING_CALL(5) -#define OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE 64 +#define OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE 64

+/*

• • Release Protected memory
• • Call register usage:
• • w3: Service ID, OPTEE_FFA_RECLAIM_PROTMEM
• • w4: Shared memory handle, lower bits
• • w5: Shared memory handle, higher bits
• • w6-w7: Not used (MBZ)
• • Return register usage:
• • w3: Error code, 0 on success
• • w4-w7: Note used (MBZ)
• */

+#define OPTEE_FFA_RELEASE_PROTMEM OPTEE_FFA_BLOCKING_CALL(8) /*

• Call with struct optee_msg_arg as argument in the supplied shared memory

diff --git a/drivers/tee/optee/optee_msg.h b/drivers/tee/optee/optee_msg.h index e8840a82b983..22130e967dc5 100644 --- a/drivers/tee/optee/optee_msg.h +++ b/drivers/tee/optee/optee_msg.h @@ -133,13 +133,13 @@ struct optee_msg_param_rmem { }; /**

• • struct optee_msg_param_fmem - ffa memory reference parameter

• • struct optee_msg_param_fmem - FF-A memory reference parameter
  • @offs_lower: Lower bits of offset into shared memory reference
  • @offs_upper: Upper bits of offset into shared memory reference
  • @internal_offs: Internal offset into the first page of shared memory

  •    reference
    

  • @size: Size of the buffer

• • @global_id: Global identifier of Shared memory

• • @global_id: Global identifier of the shared memory
  */

struct optee_msg_param_fmem { u32 offs_low; @@ -165,7 +165,7 @@ struct optee_msg_param_value {

• @attr: attributes
• @tmem: parameter by temporary memory reference
• @rmem: parameter by registered memory reference

• • @fmem: parameter by ffa registered memory reference

• • @fmem: parameter by FF-A registered memory reference
  • @value: parameter by opaque value
  • @octets: parameter by octet string

@@ -296,6 +296,18 @@ struct optee_msg_arg { */ #define OPTEE_MSG_FUNCID_GET_OS_REVISION 0x0001 +/*

• • Values used in OPTEE_MSG_CMD_LEND_PROTMEM below
• • OPTEE_MSG_PROTMEM_RESERVED Reserved
• • OPTEE_MSG_PROTMEM_SECURE_VIDEO_PLAY Secure Video Playback
• • OPTEE_MSG_PROTMEM_TRUSTED_UI Trused UI
• • OPTEE_MSG_PROTMEM_SECURE_VIDEO_RECORD Secure Video Recording
• */

+#define OPTEE_MSG_PROTMEM_RESERVED 0 +#define OPTEE_MSG_PROTMEM_SECURE_VIDEO_PLAY 1 +#define OPTEE_MSG_PROTMEM_TRUSTED_UI 2 +#define OPTEE_MSG_PROTMEM_SECURE_VIDEO_RECORD 3

/*

• Do a secure call with struct optee_msg_arg as argument
• The OPTEE_MSG_CMD_* below defines what goes in struct optee_msg_arg::cmd

@@ -337,15 +349,63 @@ struct optee_msg_arg {

• OPTEE_MSG_CMD_STOP_ASYNC_NOTIF informs secure world that from now is
• normal world unable to process asynchronous notifications. Typically
• used when the driver is shut down.

• • OPTEE_MSG_CMD_LEND_PROTMEM lends protected memory. The passed normal
• • physical memory is protected from normal world access. The memory
• • should be unmapped prior to this call since it becomes inaccessible
• • during the request.
• • Parameters are passed as:
• • [in] param[0].attr OPTEE_MSG_ATTR_TYPE_VALUE_INPUT
• • [in] param[0].u.value.a OPTEE_MSG_PROTMEM_* defined above
• • [in] param[1].attr OPTEE_MSG_ATTR_TYPE_TMEM_INPUT
• • [in] param[1].u.tmem.buf_ptr physical address
• • [in] param[1].u.tmem.size size
• • [in] param[1].u.tmem.shm_ref holds protected memory reference
• • OPTEE_MSG_CMD_RECLAIM_PROTMEM reclaims a previously lent protected
• • memory reference. The physical memory is accessible by the normal world
• • after this function has return and can be mapped again. The information
• • is passed as:
• • [in] param[0].attr OPTEE_MSG_ATTR_TYPE_VALUE_INPUT
• • [in] param[0].u.value.a holds protected memory cookie
• • OPTEE_MSG_CMD_GET_PROTMEM_CONFIG get configuration for a specific
• • protected memory use case. Parameters are passed as:
• • [in] param[0].attr OPTEE_MSG_ATTR_TYPE_VALUE_INOUT
• • [in] param[0].value.a OPTEE_MSG_PROTMEM_*
• • [in] param[1].attr OPTEE_MSG_ATTR_TYPE_{R,F}MEM_OUTPUT
• • [in] param[1].u.{r,f}mem Buffer or NULL
• • [in] param[1].u.{r,f}mem.size Provided size of buffer or 0 for query
• • output for the protected use case:
• • [out] param[0].value.a Minimal size of protected memory
• • [out] param[0].value.b Required alignment of size and start of

• • 			protected memory
    

• • [out] param[0].value.c PA width, max 64
• • [out] param[1].{r,f}mem.size Size of output data
• • [out] param[1].{r,f}mem If non-NULL, contains an array of

• • 			uint16_t holding endpoints that
    

• • 			must be included when lending
    

• • 			memory for this use case
    

• • OPTEE_MSG_CMD_ASSIGN_PROTMEM assigns use-case to protected memory
• • previously lent using the FFA_LEND framework ABI. Parameters are passed
• • as:
• • [in] param[0].attr OPTEE_MSG_ATTR_TYPE_VALUE_INPUT
• • [in] param[0].u.value.a holds protected memory cookie
• • [in] param[0].u.value.b OPTEE_MSG_PROTMEM_* defined above
  */

-#define OPTEE_MSG_CMD_OPEN_SESSION 0 -#define OPTEE_MSG_CMD_INVOKE_COMMAND 1 -#define OPTEE_MSG_CMD_CLOSE_SESSION 2 -#define OPTEE_MSG_CMD_CANCEL 3 -#define OPTEE_MSG_CMD_REGISTER_SHM 4 -#define OPTEE_MSG_CMD_UNREGISTER_SHM 5 -#define OPTEE_MSG_CMD_DO_BOTTOM_HALF 6 -#define OPTEE_MSG_CMD_STOP_ASYNC_NOTIF 7 -#define OPTEE_MSG_FUNCID_CALL_WITH_ARG 0x0004 +#define OPTEE_MSG_CMD_OPEN_SESSION 0 +#define OPTEE_MSG_CMD_INVOKE_COMMAND 1 +#define OPTEE_MSG_CMD_CLOSE_SESSION 2 +#define OPTEE_MSG_CMD_CANCEL 3 +#define OPTEE_MSG_CMD_REGISTER_SHM 4 +#define OPTEE_MSG_CMD_UNREGISTER_SHM 5 +#define OPTEE_MSG_CMD_DO_BOTTOM_HALF 6 +#define OPTEE_MSG_CMD_STOP_ASYNC_NOTIF 7 +#define OPTEE_MSG_CMD_LEND_PROTMEM 8 +#define OPTEE_MSG_CMD_RECLAIM_PROTMEM 9 +#define OPTEE_MSG_CMD_GET_PROTMEM_CONFIG 10 +#define OPTEE_MSG_CMD_ASSIGN_PROTMEM 11 +#define OPTEE_MSG_FUNCID_CALL_WITH_ARG 0x0004 #endif /* _OPTEE_MSG_H */ diff --git a/drivers/tee/optee/optee_smc.h b/drivers/tee/optee/optee_smc.h index 879426300821..accf76a99288 100644 --- a/drivers/tee/optee/optee_smc.h +++ b/drivers/tee/optee/optee_smc.h @@ -264,7 +264,6 @@ struct optee_smc_get_shm_config_result { #define OPTEE_SMC_SEC_CAP_HAVE_RESERVED_SHM BIT(0) /* Secure world can communicate via previously unregistered shared memory */ #define OPTEE_SMC_SEC_CAP_UNREGISTERED_SHM BIT(1)

/*

• Secure world supports commands "register/unregister shared memory",
• secure world accepts command buffers located in any parts of non-secure RAM

@@ -280,6 +279,10 @@ struct optee_smc_get_shm_config_result { #define OPTEE_SMC_SEC_CAP_RPC_ARG BIT(6) /* Secure world supports probing for RPMB device if needed */ #define OPTEE_SMC_SEC_CAP_RPMB_PROBE BIT(7) +/* Secure world supports protected memory */ +#define OPTEE_SMC_SEC_CAP_PROTMEM BIT(8) +/* Secure world supports dynamic protected memory */ +#define OPTEE_SMC_SEC_CAP_DYNAMIC_PROTMEM BIT(9) #define OPTEE_SMC_FUNCID_EXCHANGE_CAPABILITIES 9 #define OPTEE_SMC_EXCHANGE_CAPABILITIES \ @@ -451,6 +454,38 @@ struct optee_smc_disable_shm_cache_result { /* See OPTEE_SMC_CALL_WITH_REGD_ARG above */ #define OPTEE_SMC_FUNCID_CALL_WITH_REGD_ARG 19 +/*

• • Get protected memory config
• • Returns the protected memory config.
• • Call register usage:
• • a0 SMC Function ID, OPTEE_SMC_GET_PROTMEM_CONFIG
• • a2-6 Not used, must be zero
• • a7 Hypervisor Client ID register
• • Have config return register usage:
• • a0 OPTEE_SMC_RETURN_OK
• • a1 Physical address of start of protected memory
• • a2 Size of protected memory
• • a3 PA width, max 64
• • a4-7 Preserved
• • Not available register usage:
• • a0 OPTEE_SMC_RETURN_ENOTAVAIL
• • a1-3 Not used
• • a4-7 Preserved
• */

+#define OPTEE_SMC_FUNCID_GET_PROTMEM_CONFIG 20 +#define OPTEE_SMC_GET_PROTMEM_CONFIG \

• OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_GET_PROTMEM_CONFIG)

+struct optee_smc_get_protmem_config_result {

• unsigned long status;
• unsigned long start;
• unsigned long size;
• unsigned long pa_width;

+}; /*

• Resume from RPC (for example after processing a foreign interrupt)

-- 2.43.0

On 5/20/25 17:16, Jens Wiklander wrote:

Export the dma-buf heap functions declared in <linux/dma-heap.h>.

That is what this patch does and that should be obvious by looking at it. You need to explain why you do this.

Looking at the rest of the series it's most likely ok, but this commit message should really be improved.

Regards, Christian.

Signed-off-by: Jens Wiklander jens.wiklander@linaro.org

drivers/dma-buf/dma-heap.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 3cbe87d4a464..cdddf0e24dce 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -202,6 +202,7 @@ void *dma_heap_get_drvdata(struct dma_heap *heap) { return heap->priv; } +EXPORT_SYMBOL(dma_heap_get_drvdata); /**

• dma_heap_get_name - get heap name

@@ -214,6 +215,7 @@ const char *dma_heap_get_name(struct dma_heap *heap) { return heap->name; } +EXPORT_SYMBOL(dma_heap_get_name); /**

• dma_heap_add - adds a heap to dmabuf heaps

@@ -303,6 +305,7 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) kfree(heap); return err_ret; } +EXPORT_SYMBOL(dma_heap_add); static char *dma_heap_devnode(const struct device *dev, umode_t *mode) {

On 5/22/25 08:56, Jens Wiklander wrote:

On Wed, May 21, 2025 at 9:13 AM Christian König christian.koenig@amd.com wrote:

...

On 5/20/25 17:16, Jens Wiklander wrote:

...

Export the dma-buf heap functions declared in <linux/dma-heap.h>.

That is what this patch does and that should be obvious by looking at it. You need to explain why you do this.

Looking at the rest of the series it's most likely ok, but this commit message should really be improved.

I'm considering something like this for the next version: Export the dma-buf heap functions declared in <linux/dma-heap.h> to allow them to be used by kernel modules. This will enable drivers like the OP-TEE driver, to utilize these interfaces for registering and managing their specific DMA heaps.

Works for me, but it doesn't needs to be so detailed.

Something like this here would be optimal I think:

Export the dma-buf heap functions to allow them to be used by the OP-TEE driver. The OP-TEE driver wants to register and manage specific secure DMA heaps with it.

Regards, Christian.

Thanks, Jens

...

Regards, Christian.

...

Signed-off-by: Jens Wiklander jens.wiklander@linaro.org

drivers/dma-buf/dma-heap.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 3cbe87d4a464..cdddf0e24dce 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -202,6 +202,7 @@ void *dma_heap_get_drvdata(struct dma_heap *heap) { return heap->priv; } +EXPORT_SYMBOL(dma_heap_get_drvdata);

/**

• dma_heap_get_name - get heap name

@@ -214,6 +215,7 @@ const char *dma_heap_get_name(struct dma_heap *heap) { return heap->name; } +EXPORT_SYMBOL(dma_heap_get_name);

/**

• dma_heap_add - adds a heap to dmabuf heaps

@@ -303,6 +305,7 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info) kfree(heap); return err_ret; } +EXPORT_SYMBOL(dma_heap_add);

static char *dma_heap_devnode(const struct device *dev, umode_t *mode) {

On Fri, May 23, 2025 at 3:03 PM Sumit Garg sumit.garg@kernel.org wrote:

• Robin

Jens,

I suppose you missed to add Robin who has earlier reviewed this patch.

Yes, you're right, sorry. Thanks for catching this.

On Tue, May 20, 2025 at 05:16:46PM +0200, Jens Wiklander wrote:

...

Implement DMA heap for protected DMA-buf allocation in the TEE subsystem.

Restricted memory refers to memory buffers behind a hardware enforced

s/Restricted/Protected/

...

firewall. It is not accessible to the kernel during normal circumstances but rather only accessible to certain hardware IPs or CPUs executing in higher or differently privileged mode than the kernel itself. This interface allows to allocate and manage such protected memory buffers via interaction with a TEE implementation.

The protected memory is allocated for a specific use-case, like Secure Video Playback, Trusted UI, or Secure Video Recording where certain hardware devices can access the memory.

The DMA-heaps are enabled explicitly by the TEE backend driver. The TEE backend drivers needs to implement protected memory pool to manage the protected memory.

Signed-off-by: Jens Wiklander jens.wiklander@linaro.org

drivers/tee/Makefile | 1 + drivers/tee/tee_heap.c | 487 ++++++++++++++++++++++++++++++++++++++ drivers/tee/tee_private.h | 6 + include/linux/tee_core.h | 65 +++++ 4 files changed, 559 insertions(+) create mode 100644 drivers/tee/tee_heap.c

diff --git a/drivers/tee/Makefile b/drivers/tee/Makefile index 5488cba30bd2..949a6a79fb06 100644 --- a/drivers/tee/Makefile +++ b/drivers/tee/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_TEE) += tee.o tee-objs += tee_core.o +tee-objs += tee_heap.o tee-objs += tee_shm.o tee-objs += tee_shm_pool.o obj-$(CONFIG_OPTEE) += optee/ diff --git a/drivers/tee/tee_heap.c b/drivers/tee/tee_heap.c new file mode 100644 index 000000000000..a332805f9f26 --- /dev/null +++ b/drivers/tee/tee_heap.c @@ -0,0 +1,487 @@ +// SPDX-License-Identifier: GPL-2.0-only +/*

• • Copyright (c) 2025, Linaro Limited
• */

+#include <linux/dma-buf.h> +#include <linux/dma-heap.h> +#include <linux/genalloc.h> +#include <linux/module.h> +#include <linux/scatterlist.h> +#include <linux/slab.h> +#include <linux/tee_core.h> +#include <linux/xarray.h>

+#include "tee_private.h"

+struct tee_dma_heap {

• struct dma_heap *heap;
  

• enum tee_dma_heap_id id;
  

• struct tee_protmem_pool *pool;
  

• struct tee_device *teedev;
  

• /* Protects pool and teedev above */
  

• struct mutex mu;
  

+};

+struct tee_heap_buffer {

• struct tee_protmem_pool *pool;
  

• struct tee_device *teedev;
  

• size_t size;
  

• size_t offs;
  

• struct sg_table table;
  

+};

+struct tee_heap_attachment {

• struct sg_table table;
  

• struct device *dev;
  

+};

+struct tee_protmem_static_pool {

• struct tee_protmem_pool pool;
  

• struct gen_pool *gen_pool;
  

• phys_addr_t pa_base;
  

• void *base;
  

+};

+#if IS_ENABLED(CONFIG_DMABUF_HEAPS) +static DEFINE_XARRAY_ALLOC(tee_dma_heap);

+static int copy_sg_table(struct sg_table *dst, struct sg_table *src) +{

• struct scatterlist *dst_sg;
  

• struct scatterlist *src_sg;
  

• int ret;
  

• int i;
  

• ret = sg_alloc_table(dst, src->orig_nents, GFP_KERNEL);
  

• if (ret)
  

•         return ret;
  

• dst_sg = dst->sgl;
  

• for_each_sgtable_sg(src, src_sg, i) {
  

•         sg_set_page(dst_sg, sg_page(src_sg), src_sg->length,
  

•                     src_sg->offset);
  

•         dst_sg = sg_next(dst_sg);
  

• }
  

• return 0;
  

+}

+static int tee_heap_attach(struct dma_buf *dmabuf,

•                    struct dma_buf_attachment *attachment)
  

+{

• struct tee_heap_buffer *buf = dmabuf->priv;
  

• struct tee_heap_attachment *a;
  

• int ret;
  

• a = kzalloc(sizeof(*a), GFP_KERNEL);
  

• if (!a)
  

•         return -ENOMEM;
  

• ret = copy_sg_table(&a->table, &buf->table);
  

• if (ret) {
  

•         kfree(a);
  

•         return ret;
  

• }
  

• a->dev = attachment->dev;
  

• attachment->priv = a;
  

• return 0;
  

+}

+static void tee_heap_detach(struct dma_buf *dmabuf,

•                     struct dma_buf_attachment *attachment)
  

+{

• struct tee_heap_attachment *a = attachment->priv;
  

• sg_free_table(&a->table);
  

• kfree(a);
  

+}

+static struct sg_table * +tee_heap_map_dma_buf(struct dma_buf_attachment *attachment,

•              enum dma_data_direction direction)
  

+{

• struct tee_heap_attachment *a = attachment->priv;
  

• int ret;
  

• ret = dma_map_sgtable(attachment->dev, &a->table, direction,
  

•                       DMA_ATTR_SKIP_CPU_SYNC);
  

• if (ret)
  

•         return ERR_PTR(ret);
  

• return &a->table;
  

+}

+static void tee_heap_unmap_dma_buf(struct dma_buf_attachment *attachment,

•                            struct sg_table *table,
  

•                            enum dma_data_direction direction)
  

+{

• struct tee_heap_attachment *a = attachment->priv;
  

• WARN_ON(&a->table != table);
  

• dma_unmap_sgtable(attachment->dev, table, direction,
  

•                   DMA_ATTR_SKIP_CPU_SYNC);
  

+}

+static void tee_heap_buf_free(struct dma_buf *dmabuf) +{

• struct tee_heap_buffer *buf = dmabuf->priv;
  

• struct tee_device *teedev = buf->teedev;
  

• buf->pool->ops->free(buf->pool, &buf->table);
  

• tee_device_put(teedev);
  

+}

+static const struct dma_buf_ops tee_heap_buf_ops = {

• .attach = tee_heap_attach,
  

• .detach = tee_heap_detach,
  

• .map_dma_buf = tee_heap_map_dma_buf,
  

• .unmap_dma_buf = tee_heap_unmap_dma_buf,
  

• .release = tee_heap_buf_free,
  

+};

+static struct dma_buf *tee_dma_heap_alloc(struct dma_heap *heap,

•                                   unsigned long len, u32 fd_flags,
  

•                                   u64 heap_flags)
  

+{

• struct tee_dma_heap *h = dma_heap_get_drvdata(heap);
  

• DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
  

• struct tee_device *teedev = NULL;
  

• struct tee_heap_buffer *buf;
  

• struct tee_protmem_pool *pool;
  

• struct dma_buf *dmabuf;
  

• int rc;
  

• mutex_lock(&h->mu);
  

• if (tee_device_get(h->teedev)) {
  

•         teedev = h->teedev;
  

•         pool = h->pool;
  

• }
  

• mutex_unlock(&h->mu);
  

• if (!teedev)
  

•         return ERR_PTR(-EINVAL);
  

• buf = kzalloc(sizeof(*buf), GFP_KERNEL);
  

• if (!buf) {
  

•         dmabuf = ERR_PTR(-ENOMEM);
  

•         goto err;
  

• }
  

• buf->size = len;
  

• buf->pool = pool;
  

• buf->teedev = teedev;
  

• rc = pool->ops->alloc(pool, &buf->table, len, &buf->offs);
  

• if (rc) {
  

•         dmabuf = ERR_PTR(rc);
  

•         goto err_kfree;
  

• }
  

• exp_info.ops = &tee_heap_buf_ops;
  

• exp_info.size = len;
  

• exp_info.priv = buf;
  

• exp_info.flags = fd_flags;
  

• dmabuf = dma_buf_export(&exp_info);
  

• if (IS_ERR(dmabuf))
  

•         goto err_protmem_free;
  

• return dmabuf;
  

+err_protmem_free:

• pool->ops->free(pool, &buf->table);
  

+err_kfree:

• kfree(buf);
  

+err:

• tee_device_put(h->teedev);
  

• return dmabuf;
  

+}

+static const struct dma_heap_ops tee_dma_heap_ops = {

• .allocate = tee_dma_heap_alloc,
  

+};

+static const char *heap_id_2_name(enum tee_dma_heap_id id) +{

• switch (id) {
  

• case TEE_DMA_HEAP_SECURE_VIDEO_PLAY:
  

•         return "protected,secure-video";
  

• case TEE_DMA_HEAP_TRUSTED_UI:
  

•         return "protected,trusted-ui";
  

• case TEE_DMA_HEAP_SECURE_VIDEO_RECORD:
  

•         return "protected,secure-video-record";
  

• default:
  

•         return NULL;
  

• }
  

+}

+static int alloc_dma_heap(struct tee_device *teedev, enum tee_dma_heap_id id,

•                   struct tee_protmem_pool *pool)
  

+{

• struct dma_heap_export_info exp_info = {
  

•         .ops = &tee_dma_heap_ops,
  

•         .name = heap_id_2_name(id),
  

• };
  

• struct tee_dma_heap *h;
  

• int rc;
  

• if (!exp_info.name)
  

•         return -EINVAL;
  

• if (xa_reserve(&tee_dma_heap, id, GFP_KERNEL)) {
  

•         if (!xa_load(&tee_dma_heap, id))
  

•                 return -EEXIST;
  

•         return -ENOMEM;
  

• }
  

• h = kzalloc(sizeof(*h), GFP_KERNEL);
  

• if (!h)
  

•         return -ENOMEM;
  

• h->id = id;
  

• h->teedev = teedev;
  

• h->pool = pool;
  

• mutex_init(&h->mu);
  

• exp_info.priv = h;
  

• h->heap = dma_heap_add(&exp_info);
  

• if (IS_ERR(h->heap)) {
  

•         rc = PTR_ERR(h->heap);
  

•         kfree(h);
  

•         return rc;
  

• }
  

• /* "can't fail" due to the call to xa_reserve() above */
  

• return WARN(xa_store(&tee_dma_heap, id, h, GFP_KERNEL),
  

•             "xa_store() failed");
  

I think this can rather be simplified to:

    return WARN_ON(xa_is_err(xa_store(&tee_dma_heap, id, h, GFP_KERNEL)));

OK

...

+}

+int tee_device_register_dma_heap(struct tee_device *teedev,

•                          enum tee_dma_heap_id id,
  

•                          struct tee_protmem_pool *pool)
  

+{

• struct tee_dma_heap *h;
  

• int rc;
  

• h = xa_load(&tee_dma_heap, id);
  

• if (h) {
  

•         mutex_lock(&h->mu);
  

•         if (h->teedev) {
  

•                 rc = -EBUSY;
  

•         } else {
  

•                 h->teedev = teedev;
  

•                 h->pool = pool;
  

•                 rc = 0;
  

•         }
  

•         mutex_unlock(&h->mu);
  

• } else {
  

•         rc = alloc_dma_heap(teedev, id, pool);
  

• }
  

• if (rc)
  

•         dev_err(&teedev->dev, "can't register DMA heap id %d (%s)\n",
  

•                 id, heap_id_2_name(id));
  

• return rc;
  

+} +EXPORT_SYMBOL_GPL(tee_device_register_dma_heap);

+void tee_device_unregister_all_dma_heaps(struct tee_device *teedev) +{

• struct tee_protmem_pool *pool;
  

• struct tee_dma_heap *h;
  

• u_long i;
  

• xa_for_each(&tee_dma_heap, i, h) {
  

•         if (h) {
  

•                 pool = NULL;
  

•                 mutex_lock(&h->mu);
  

•                 if (h->teedev == teedev) {
  

•                         pool = h->pool;
  

•                         h->teedev = NULL;
  

•                         h->pool = NULL;
  

•                 }
  

•                 mutex_unlock(&h->mu);
  

•                 if (pool)
  

•                         pool->ops->destroy_pool(pool);
  

•         }
  

• }
  

+} +EXPORT_SYMBOL_GPL(tee_device_unregister_all_dma_heaps);

+int tee_heap_update_from_dma_buf(struct tee_device *teedev,

•                          struct dma_buf *dmabuf, size_t *offset,
  

•                          struct tee_shm *shm,
  

•                          struct tee_shm **parent_shm)
  

+{

• struct tee_heap_buffer *buf;
  

• int rc;
  

• /* The DMA-buf must be from our heap */
  

• if (dmabuf->ops != &tee_heap_buf_ops)
  

•         return -EINVAL;
  

• buf = dmabuf->priv;
  

• /* The buffer must be from the same teedev */
  

• if (buf->teedev != teedev)
  

•         return -EINVAL;
  

• shm->size = buf->size;
  

• rc = buf->pool->ops->update_shm(buf->pool, &buf->table, buf->offs, shm,
  

•                                 parent_shm);
  

• if (!rc && *parent_shm)
  

•         *offset = buf->offs;
  

• return rc;
  

+} +#else +int tee_device_register_dma_heap(struct tee_device *teedev __always_unused,

•                          enum tee_dma_heap_id id __always_unused,
  

•                          struct tee_protmem_pool *pool __always_unused)
  

+{

• return -EINVAL;
  

+} +EXPORT_SYMBOL_GPL(tee_device_register_dma_heap);

+void +tee_device_unregister_all_dma_heaps(struct tee_device *teedev __always_unused) +{ +} +EXPORT_SYMBOL_GPL(tee_device_unregister_all_dma_heaps);

+int tee_heap_update_from_dma_buf(struct tee_device *teedev __always_unused,

•                          struct dma_buf *dmabuf __always_unused,
  

•                          size_t *offset __always_unused,
  

•                          struct tee_shm *shm __always_unused,
  

•                          struct tee_shm **parent_shm __always_unused)
  

+{

• return -EINVAL;
  

+} +#endif

+static struct tee_protmem_static_pool * +to_protmem_static_pool(struct tee_protmem_pool *pool) +{

• return container_of(pool, struct tee_protmem_static_pool, pool);
  

+}

+static int protmem_pool_op_static_alloc(struct tee_protmem_pool *pool,

•                                 struct sg_table *sgt, size_t size,
  

•                                 size_t *offs)
  

+{

• struct tee_protmem_static_pool *stp = to_protmem_static_pool(pool);
  

• phys_addr_t pa;
  

• int ret;
  

• pa = gen_pool_alloc(stp->gen_pool, size);
  

• if (!pa)
  

•         return -ENOMEM;
  

• ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
  

• if (ret) {
  

•         gen_pool_free(stp->gen_pool, pa, size);
  

•         return ret;
  

• }
  

• sg_set_page(sgt->sgl, phys_to_page(pa), size, 0);
  

Did you missed pfn_valid() check from prior v8 review comments?

No, I tried it, but pfn_valid() didn't like the address, so I had to find a way to fix it. tee_protmem_static_pool_alloc(), below, calls memremap() on the range, and that should make pfn_valid() redundant.

...

• *offs = pa - stp->pa_base;
  

• return 0;
  

+}

+static void protmem_pool_op_static_free(struct tee_protmem_pool *pool,

•                                 struct sg_table *sgt)
  

+{

• struct tee_protmem_static_pool *stp = to_protmem_static_pool(pool);
  

• struct scatterlist *sg;
  

• int i;
  

• for_each_sgtable_sg(sgt, sg, i)
  

•         gen_pool_free(stp->gen_pool, sg_phys(sg), sg->length);
  

• sg_free_table(sgt);
  

+}

+static int protmem_pool_op_static_update_shm(struct tee_protmem_pool *pool,

•                                      struct sg_table *sgt, size_t offs,
  

•                                      struct tee_shm *shm,
  

•                                      struct tee_shm **parent_shm)
  

+{

• struct tee_protmem_static_pool *stp = to_protmem_static_pool(pool);
  

• shm->paddr = stp->pa_base + offs;
  

• *parent_shm = NULL;
  

• return 0;
  

+}

+static void protmem_pool_op_static_destroy_pool(struct tee_protmem_pool *pool) +{

• struct tee_protmem_static_pool *stp = to_protmem_static_pool(pool);
  

• gen_pool_destroy(stp->gen_pool);
  

• memunmap(stp->base);
  

• kfree(stp);
  

+}

+static struct tee_protmem_pool_ops protmem_pool_ops_static = {

• .alloc = protmem_pool_op_static_alloc,
  

• .free = protmem_pool_op_static_free,
  

• .update_shm = protmem_pool_op_static_update_shm,
  

• .destroy_pool = protmem_pool_op_static_destroy_pool,
  

+};

+struct tee_protmem_pool *tee_protmem_static_pool_alloc(phys_addr_t paddr,

•                                                size_t size)
  

+{

• const size_t page_mask = PAGE_SIZE - 1;
  

• struct tee_protmem_static_pool *stp;
  

• int rc;
  

• /* Check it's page aligned */
  

• if ((paddr | size) & page_mask)
  

•         return ERR_PTR(-EINVAL);
  

• stp = kzalloc(sizeof(*stp), GFP_KERNEL);
  

• if (!stp)
  

•         return ERR_PTR(-ENOMEM);
  

• /*
  

•  * Map the memory as uncached to make sure the kernel can work with
  

•  * __pfn_to_page() and friends since that's needed when passing the
  

•  * protected DMA-buf to a device. The memory should otherwise not
  

•  * be touched by the kernel since it's likely to cause an external
  

•  * abort due to the protection status.
  

•  */
  

• stp->base = memremap(paddr, size, MEMREMAP_WC);
  

• if (!stp->base) {
  

•         rc = -EINVAL;
  

•         goto err_free;
  

• }
  

• stp->gen_pool = gen_pool_create(PAGE_SHIFT, -1);
  

• if (!stp->gen_pool) {
  

•         rc = -ENOMEM;
  

•         goto err_unmap;
  

• }
  

• rc = gen_pool_add(stp->gen_pool, paddr, size, -1);
  

• if (rc)
  

•         goto err_free_pool;
  

• stp->pool.ops = &protmem_pool_ops_static;
  

• stp->pa_base = paddr;
  

• return &stp->pool;
  

+err_free_pool:

• gen_pool_destroy(stp->gen_pool);
  

+err_unmap:

• memunmap(stp->base);
  

+err_free:

• kfree(stp);
  

• return ERR_PTR(rc);
  

+} +EXPORT_SYMBOL_GPL(tee_protmem_static_pool_alloc); diff --git a/drivers/tee/tee_private.h b/drivers/tee/tee_private.h index 9bc50605227c..6c6ff5d5eed2 100644 --- a/drivers/tee/tee_private.h +++ b/drivers/tee/tee_private.h @@ -8,6 +8,7 @@ #include <linux/cdev.h> #include <linux/completion.h> #include <linux/device.h> +#include <linux/dma-buf.h> #include <linux/kref.h> #include <linux/mutex.h> #include <linux/types.h> @@ -24,4 +25,9 @@ struct tee_shm *tee_shm_alloc_user_buf(struct tee_context *ctx, size_t size); struct tee_shm *tee_shm_register_user_buf(struct tee_context *ctx, unsigned long addr, size_t length);

+int tee_heap_update_from_dma_buf(struct tee_device *teedev,

•                          struct dma_buf *dmabuf, size_t *offset,
  

•                          struct tee_shm *shm,
  

•                          struct tee_shm **parent_shm);
  

#endif /*TEE_PRIVATE_H*/ diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h index a38494d6b5f4..b8b99c97e00c 100644 --- a/include/linux/tee_core.h +++ b/include/linux/tee_core.h @@ -8,9 +8,11 @@

#include <linux/cdev.h> #include <linux/device.h> +#include <linux/dma-buf.h> #include <linux/idr.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/scatterlist.h> #include <linux/tee.h> #include <linux/tee_drv.h> #include <linux/types.h> @@ -30,6 +32,12 @@ #define TEE_DEVICE_FLAG_REGISTERED 0x1 #define TEE_MAX_DEV_NAME_LEN 32

+enum tee_dma_heap_id {

• TEE_DMA_HEAP_SECURE_VIDEO_PLAY = 1,
  

• TEE_DMA_HEAP_TRUSTED_UI,
  

• TEE_DMA_HEAP_SECURE_VIDEO_RECORD,
  

+};

/**

• struct tee_device - TEE Device representation
• @name: name of device

@@ -116,6 +124,36 @@ struct tee_desc { u32 flags; };

+/**

• • struct tee_protmem_pool - protected memory pool
• • @ops: operations
• • This is an abstract interface where this struct is expected to be
• • embedded in another struct specific to the implementation.
• */

+struct tee_protmem_pool {

• const struct tee_protmem_pool_ops *ops;
  

+};

+/**

• • struct tee_protmem_pool_ops - protected memory pool operations
• • @alloc: called when allocating protected memory
• • @free: called when freeing protected memory
• • @update_shm: called when registering a dma-buf to update the @shm

• •               with physical address of the buffer or to return the
    

• •               @parent_shm of the memory pool
    

• • @destroy_pool: called when destroying the pool
• */

+struct tee_protmem_pool_ops {

• int (*alloc)(struct tee_protmem_pool *pool, struct sg_table *sgt,
  

•              size_t size, size_t *offs);
  

• void (*free)(struct tee_protmem_pool *pool, struct sg_table *sgt);
  

• int (*update_shm)(struct tee_protmem_pool *pool, struct sg_table *sgt,
  

•                   size_t offs, struct tee_shm *shm,
  

•                   struct tee_shm **parent_shm);
  

• void (*destroy_pool)(struct tee_protmem_pool *pool);
  

+};

/**

• tee_device_alloc() - Allocate a new struct tee_device instance
• @teedesc: Descriptor for this driver

@@ -154,6 +192,11 @@ int tee_device_register(struct tee_device *teedev); */ void tee_device_unregister(struct tee_device *teedev);

+int tee_device_register_dma_heap(struct tee_device *teedev,

•                          enum tee_dma_heap_id id,
  

•                          struct tee_protmem_pool *pool);
  

+void tee_device_unregister_all_dma_heaps(struct tee_device *teedev);

/**

• tee_device_set_dev_groups() - Set device attribute groups
• @teedev: Device to register

@@ -229,6 +272,28 @@ static inline void tee_shm_pool_free(struct tee_shm_pool *pool) pool->ops->destroy_pool(pool); }

+/**

• • tee_protmem_static_pool_alloc() - Create a protected memory manager
• • @paddr: Physical address of start of pool
• • @size: Size in bytes of the pool
• • @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure.

s/tee_shm_pool/tee_protmem_pool/

I'll fix it.

Rest looks fine to me.

Thanks, Jens

-Sumit

...

• */

+struct tee_protmem_pool *tee_protmem_static_pool_alloc(phys_addr_t paddr,

•                                                size_t size);
  

+/**

• • tee_protmem_pool_free() - Free a protected memory pool
• • @pool: The protected memory pool to free
• • There must be no remaining protected memory allocated from this pool
• • when this function is called.
• */

+static inline void tee_protmem_pool_free(struct tee_protmem_pool *pool) +{

• pool->ops->destroy_pool(pool);
  

+}

/**

• tee_get_drvdata() - Return driver_data pointer
• @returns the driver_data pointer supplied to tee_register().

-- 2.43.0

On Tue, May 20, 2025 at 05:16:48PM +0200, Jens Wiklander wrote:

From: Etienne Carriere etienne.carriere@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@foss.st.com Signed-off-by: Olivier Masse olivier.masse@nxp.com Signed-off-by: Jens Wiklander jens.wiklander@linaro.org

---

drivers/tee/tee_core.c | 63 +++++++++++++++++++++- drivers/tee/tee_private.h | 10 ++++ drivers/tee/tee_shm.c | 111 ++++++++++++++++++++++++++++++++++++-- include/linux/tee_core.h | 1 + include/linux/tee_drv.h | 10 ++++ include/uapi/linux/tee.h | 31 +++++++++++ 6 files changed, 221 insertions(+), 5 deletions(-)

With below minor comments fixed, feel free to add:

Reviewed-by: Sumit Garg sumit.garg@oss.qualcomm.com

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;

Is this an issue being detected now? If yes then shouldn't it be a separate fix eligible for backport?

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..e1ed52ee0a16 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 +46,23 @@ 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) {

• struct tee_shm *parent_shm = NULL;
• 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);
  

• parent_shm = ref->parent_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);

@@ -57,9 +74,10 @@ static void tee_shm_release(struct tee_device *teedev, struct tee_shm *shm) release_registered_pages(shm); }

• teedev_ctx_put(shm->ctx);

• if (shm->ctx)

• teedev_ctx_put(shm->ctx);
  

redundant change?

• kfree(shm);

• kfree(p);

tee_device_put(teedev); } @@ -169,7 +187,7 @@ 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 +197,91 @@ 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;
  

• 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 b8b99c97e00c..02c07f661349 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..8ec5f46fbfbe 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -118,6 +118,37 @@ struct tee_ioctl_shm_alloc_data { #define TEE_IOC_SHM_ALLOC _IOWR(TEE_IOC_MAGIC, TEE_IOC_BASE + 1, \ struct tee_ioctl_shm_alloc_data) +/**

• • 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)
  

Please add this IOCTL in correct sequence order.

-Sumit

/**

• struct tee_ioctl_buf_data - Variable sized buffer
• @buf_ptr: [in] A __user pointer to a buffer

-- 2.43.0

On Tue, May 20, 2025 at 05:16:49PM +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@linaro.org

drivers/tee/tee_shm.c | 74 ++++++++++++++++++++++++++++++++++++++-- include/linux/tee_core.h | 5 +++ 2 files changed, 77 insertions(+), 2 deletions(-)

diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index e1ed52ee0a16..92a6a35e1a1e 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; @@ -49,7 +56,14 @@ static void tee_shm_release(struct tee_device *teedev, struct tee_shm *shm) struct tee_shm *parent_shm = NULL; void *p = shm;

• if (shm->flags & TEE_SHM_DMA_BUF) {

• if (shm->flags & TEE_SHM_DMA_MEM) {

• 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);
  

Although the kernel bot already found a randconfig issue, it looks like we need to add Kconfig dependencies like HAS_DMA, DMA_CMA etc.

Also, I was thinking if we should rather add a new TEE subsystem specific Kconfig option like: TEE_DMABUF_HEAPS which can then be used to select whatever dependency is needed as well as act as a gating Kconfig for relevant features.

-Sumit

• } else if (shm->flags & TEE_SHM_DMA_BUF) { struct tee_shm_dmabuf_ref *ref;

ref = container_of(shm, struct tee_shm_dmabuf_ref, shm); @@ -306,6 +320,62 @@ struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size) } EXPORT_SYMBOL_GPL(tee_shm_alloc_priv_buf); +/**

• • 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);

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 02c07f661349..925690e1020b 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

On Mon, May 26, 2025 at 11:21:47AM +0200, Jens Wiklander wrote:

On Mon, May 26, 2025 at 9:22 AM Sumit Garg sumit.garg@kernel.org wrote:

...

On Tue, May 20, 2025 at 05:16:49PM +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@linaro.org

drivers/tee/tee_shm.c | 74 ++++++++++++++++++++++++++++++++++++++-- include/linux/tee_core.h | 5 +++ 2 files changed, 77 insertions(+), 2 deletions(-)

diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index e1ed52ee0a16..92a6a35e1a1e 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; @@ -49,7 +56,14 @@ static void tee_shm_release(struct tee_device *teedev, struct tee_shm *shm) struct tee_shm *parent_shm = NULL; void *p = shm;

• if (shm->flags & TEE_SHM_DMA_BUF) {
  

• if (shm->flags & TEE_SHM_DMA_MEM) {
  

•         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);
  

Although the kernel bot already found a randconfig issue, it looks like we need to add Kconfig dependencies like HAS_DMA, DMA_CMA etc.

Also, I was thinking if we should rather add a new TEE subsystem specific Kconfig option like: TEE_DMABUF_HEAPS which can then be used to select whatever dependency is needed as well as act as a gating Kconfig for relevant features.

You mean something like this?

--- a/drivers/tee/Kconfig +++ b/drivers/tee/Kconfig @@ -13,6 +13,14 @@ menuconfig TEE

if TEE

+config TEE_DMABUF_HEAPS

•   bool
  

•   depends on HAS_DMA && DMABUF_HEAPS
  

Yeah this looks fine to me but needs to be tested if DMA_CMA is a dependency here too.

+config TEE_STATIC_PROTMEM_POOL

•   bool
  

•   depends on HAS_IOMEM && TEE_DMABUF_HEAPS
  

The static and dynamic protected memory pools should get auto enabled if TEE_DMABUF_HEAPS is enabled since they are pre-requisite to provide the protected heaps support. Something like:

+config TEE_STATIC_PROTMEM_POOL + bool + default y if TEE_DMABUF_HEAPS + depends on HAS_IOMEM

-Sumit

Cheers, Jens

...

-Sumit

...

• } else if (shm->flags & TEE_SHM_DMA_BUF) {
          struct tee_shm_dmabuf_ref *ref;
  
          ref = container_of(shm, struct tee_shm_dmabuf_ref, shm);
  

@@ -306,6 +320,62 @@ struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size) } EXPORT_SYMBOL_GPL(tee_shm_alloc_priv_buf);

+/**

• • 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);

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 02c07f661349..925690e1020b 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

On Mon, May 26, 2025 at 9:33 AM Sumit Garg sumit.garg@kernel.org wrote:

On Tue, May 20, 2025 at 05:16:50PM +0200, Jens Wiklander wrote:

...

Add support in the OP-TEE backend driver for protected memory allocation. The support is limited to only the SMC ABI and for secure video buffers.

OP-TEE is probed for the range of protected physical memory and a memory pool allocator is initialized if OP-TEE have support for such memory.

Signed-off-by: Jens Wiklander jens.wiklander@linaro.org

drivers/tee/optee/core.c | 10 +++++++ drivers/tee/optee/optee_private.h | 2 ++ drivers/tee/optee/smc_abi.c | 45 +++++++++++++++++++++++++++++-- 3 files changed, 55 insertions(+), 2 deletions(-)

diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index c75fddc83576..4b14a7ac56f9 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -56,6 +56,15 @@ int optee_rpmb_intf_rdev(struct notifier_block *intf, unsigned long action, return 0; }

+int optee_set_dma_mask(struct optee *optee, u_int pa_width) +{

• u64 mask = DMA_BIT_MASK(min(64, pa_width));
  

• optee->teedev->dev.dma_mask = &optee->teedev->dev.coherent_dma_mask;
  

• return dma_set_mask_and_coherent(&optee->teedev->dev, mask);
  

+}

static void optee_bus_scan(struct work_struct *work) { WARN_ON(optee_enumerate_devices(PTA_CMD_GET_DEVICES_SUPP)); @@ -181,6 +190,7 @@ void optee_remove_common(struct optee *optee) tee_device_unregister(optee->supp_teedev); tee_device_unregister(optee->teedev);

• tee_device_unregister_all_dma_heaps(optee->teedev);
  tee_shm_pool_free(optee->pool);
  optee_supp_uninit(&optee->supp);
  mutex_destroy(&optee->call_queue.mutex);
  

diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h index dc0f355ef72a..5e3c34802121 100644 --- a/drivers/tee/optee/optee_private.h +++ b/drivers/tee/optee/optee_private.h @@ -272,6 +272,8 @@ struct optee_call_ctx {

extern struct blocking_notifier_head optee_rpmb_intf_added;

+int optee_set_dma_mask(struct optee *optee, u_int pa_width);

int optee_notif_init(struct optee *optee, u_int max_key); void optee_notif_uninit(struct optee *optee); int optee_notif_wait(struct optee *optee, u_int key, u32 timeout); diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c index f0c3ac1103bb..f3cae8243785 100644 --- a/drivers/tee/optee/smc_abi.c +++ b/drivers/tee/optee/smc_abi.c @@ -1584,6 +1584,42 @@ static inline int optee_load_fw(struct platform_device *pdev, } #endif

+static int optee_protmem_pool_init(struct optee *optee) +{

• enum tee_dma_heap_id heap_id = TEE_DMA_HEAP_SECURE_VIDEO_PLAY;
  

• struct tee_protmem_pool *pool;
  

• int rc;
  

• if (optee->smc.sec_caps & OPTEE_SMC_SEC_CAP_PROTMEM) {
  

•         union {
  

•                 struct arm_smccc_res smccc;
  

•                 struct optee_smc_get_protmem_config_result result;
  

•         } res;
  

•         optee->smc.invoke_fn(OPTEE_SMC_GET_PROTMEM_CONFIG, 0, 0, 0, 0,
  

•                              0, 0, 0, &res.smccc);
  

•         if (res.result.status != OPTEE_SMC_RETURN_OK) {
  

•                 pr_err("Secure Data Path service not available\n");
  

•                 return 0;
  

•         }
  

•         rc = optee_set_dma_mask(optee, res.result.pa_width);
  

•         if (!rc)
  

•                 pool = tee_protmem_static_pool_alloc(res.result.start,
  

•                                                      res.result.size);
  

•         if (IS_ERR(pool))
  

•                 return PTR_ERR(pool);
  

•         rc = tee_device_register_dma_heap(optee->teedev, heap_id, pool);
  

•         if (rc)
  

•                 goto err;
  

• }
  

• return 0;
  

+err:

• pool->ops->destroy_pool(pool);
  

• return rc;
  

+}

static int optee_probe(struct platform_device *pdev) { optee_invoke_fn *invoke_fn; @@ -1679,7 +1715,7 @@ static int optee_probe(struct platform_device *pdev) optee = kzalloc(sizeof(*optee), GFP_KERNEL); if (!optee) { rc = -ENOMEM;

•         goto err_free_pool;
  

•         goto err_free_shm_pool;
  }
  
  optee->ops = &optee_ops;
  

@@ -1752,6 +1788,10 @@ static int optee_probe(struct platform_device *pdev) pr_info("Asynchronous notifications enabled\n"); }

• rc = optee_protmem_pool_init(optee);
  

Here we should do a Kconfig check for CONFIG_DMABUF_HEAPS so that we don't proceed any further with initialization.

Why? If OP-TEE is configured for protected memory but the kernel isn't, something isn't right, and a print could be useful.

Cheers, Jens

Rest looks good to me.

-Sumit

...

• if (rc)
  

•         goto err_notif_uninit;
  

• /*
   * Ensure that there are no pre-existing shm objects before enabling
   * the shm cache so that there's no chance of receiving an invalid
  

@@ -1787,6 +1827,7 @@ static int optee_probe(struct platform_device *pdev) optee_disable_shm_cache(optee); optee_smc_notif_uninit_irq(optee); optee_unregister_devices();

• tee_device_unregister_all_dma_heaps(optee->teedev);
  

err_notif_uninit: optee_notif_uninit(optee); err_close_ctx: @@ -1803,7 +1844,7 @@ static int optee_probe(struct platform_device *pdev) tee_device_unregister(optee->teedev); err_free_optee: kfree(optee); -err_free_pool: +err_free_shm_pool: tee_shm_pool_free(pool); if (memremaped_shm) memunmap(memremaped_shm); -- 2.43.0

On Tue, May 20, 2025 at 05:16:51PM +0200, Jens Wiklander wrote:

Add support in the OP-TEE backend driver dynamic protected memory allocation with FF-A.

The protected memory pools for dynamically allocated protected memory are instantiated when requested by user-space. This instantiation can fail if OP-TEE doesn't support the requested use-case of protected memory.

Restricted memory pools based on a static carveout or dynamic allocation can coexist for different use-cases. We use only dynamic allocation with FF-A.

Signed-off-by: Jens Wiklander jens.wiklander@linaro.org

drivers/tee/optee/Makefile | 1 + drivers/tee/optee/ffa_abi.c | 147 ++++++++++++- drivers/tee/optee/optee_private.h | 13 +- drivers/tee/optee/protmem.c | 332 ++++++++++++++++++++++++++++++ 4 files changed, 490 insertions(+), 3 deletions(-) create mode 100644 drivers/tee/optee/protmem.c

diff --git a/drivers/tee/optee/Makefile b/drivers/tee/optee/Makefile index a6eff388d300..ad7049c1c107 100644 --- a/drivers/tee/optee/Makefile +++ b/drivers/tee/optee/Makefile @@ -4,6 +4,7 @@ optee-objs += core.o optee-objs += call.o optee-objs += notif.o optee-objs += rpc.o +optee-objs += protmem.o optee-objs += supp.o optee-objs += device.o optee-objs += smc_abi.o diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c index f3af5666bb11..b9cbd733e5c6 100644 --- a/drivers/tee/optee/ffa_abi.c +++ b/drivers/tee/optee/ffa_abi.c @@ -649,6 +649,124 @@ static int optee_ffa_do_call_with_arg(struct tee_context *ctx, return optee_ffa_yielding_call(ctx, &data, rpc_arg, system_thread); } +static int do_call_lend_protmem(struct optee *optee, u64 cookie, u32 use_case) +{

• struct optee_shm_arg_entry *entry;
• struct optee_msg_arg *msg_arg;
• struct tee_shm *shm;
• u_int offs;
• int rc;
• msg_arg = optee_get_msg_arg(optee->ctx, 1, &entry, &shm, &offs);
• if (IS_ERR(msg_arg))

• return PTR_ERR(msg_arg);
  

• msg_arg->cmd = OPTEE_MSG_CMD_ASSIGN_PROTMEM;
• msg_arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT;
• msg_arg->params[0].u.value.a = cookie;
• msg_arg->params[0].u.value.b = use_case;
• rc = optee->ops->do_call_with_arg(optee->ctx, shm, offs, false);
• if (rc)

• goto out;
  

• if (msg_arg->ret != TEEC_SUCCESS) {

• rc = -EINVAL;
  

• goto out;
  

• }

+out:

• optee_free_msg_arg(optee->ctx, entry, offs);
• return rc;

+}

+static int optee_ffa_lend_protmem(struct optee *optee, struct tee_shm *protmem,

• 		  u16 *end_points, unsigned int ep_count,
  

• 		  u32 use_case)
  

+{

• struct ffa_device *ffa_dev = optee->ffa.ffa_dev;
• const struct ffa_mem_ops *mem_ops = ffa_dev->ops->mem_ops;
• const struct ffa_msg_ops *msg_ops = ffa_dev->ops->msg_ops;
• struct ffa_send_direct_data data;
• struct ffa_mem_region_attributes *mem_attr;
• struct ffa_mem_ops_args args = {

• .use_txbuf = true,
  

• .tag = use_case,
  

• };
• struct page *page;
• struct scatterlist sgl;
• unsigned int n;
• int rc;
• mem_attr = kcalloc(ep_count, sizeof(*mem_attr), GFP_KERNEL);
• for (n = 0; n < ep_count; n++) {

• mem_attr[n].receiver = end_points[n];
  

• mem_attr[n].attrs = FFA_MEM_RW;
  

• }
• args.attrs = mem_attr;
• args.nattrs = ep_count;
• page = phys_to_page(protmem->paddr);
• sg_init_table(&sgl, 1);
• sg_set_page(&sgl, page, protmem->size, 0);
• args.sg = &sgl;
• rc = mem_ops->memory_lend(&args);
• kfree(mem_attr);
• if (rc)

• return rc;
  

• rc = do_call_lend_protmem(optee, args.g_handle, use_case);
• if (rc)

• goto err_reclaim;
  

• rc = optee_shm_add_ffa_handle(optee, protmem, args.g_handle);
• if (rc)

• goto err_unreg;
  

• protmem->sec_world_id = args.g_handle;
• return 0;

+err_unreg:

• data = (struct ffa_send_direct_data){

• .data0 = OPTEE_FFA_RELEASE_PROTMEM,
  

• .data1 = (u32)args.g_handle,
  

• .data2 = (u32)(args.g_handle >> 32),
  

• };
• msg_ops->sync_send_receive(ffa_dev, &data);

+err_reclaim:

• mem_ops->memory_reclaim(args.g_handle, 0);
• return rc;

+}

+static int optee_ffa_reclaim_protmem(struct optee *optee,

• 		     struct tee_shm *protmem)
  

+{

• struct ffa_device *ffa_dev = optee->ffa.ffa_dev;
• const struct ffa_msg_ops *msg_ops = ffa_dev->ops->msg_ops;
• const struct ffa_mem_ops *mem_ops = ffa_dev->ops->mem_ops;
• u64 global_handle = protmem->sec_world_id;
• struct ffa_send_direct_data data = {

• .data0 = OPTEE_FFA_RELEASE_PROTMEM,
  

• .data1 = (u32)global_handle,
  

• .data2 = (u32)(global_handle >> 32)
  

• };
• int rc;
• optee_shm_rem_ffa_handle(optee, global_handle);
• protmem->sec_world_id = 0;
• rc = msg_ops->sync_send_receive(ffa_dev, &data);
• if (rc)

• pr_err("Release SHM id 0x%llx rc %d\n", global_handle, rc);
  

• rc = mem_ops->memory_reclaim(global_handle, 0);
• if (rc)

• pr_err("mem_reclaim: 0x%llx %d", global_handle, rc);
  

• return rc;

+}

/*

• 6. Driver initialization

@@ -810,6 +928,8 @@ static const struct optee_ops optee_ffa_ops = { .do_call_with_arg = optee_ffa_do_call_with_arg, .to_msg_param = optee_ffa_to_msg_param, .from_msg_param = optee_ffa_from_msg_param,

• .lend_protmem = optee_ffa_lend_protmem,
• .reclaim_protmem = optee_ffa_reclaim_protmem,

}; static void optee_ffa_remove(struct ffa_device *ffa_dev) @@ -868,6 +988,25 @@ static int optee_ffa_async_notif_init(struct ffa_device *ffa_dev, return rc; } +static int optee_ffa_protmem_pool_init(struct optee *optee, u32 sec_caps) +{

• enum tee_dma_heap_id id = TEE_DMA_HEAP_SECURE_VIDEO_PLAY;
• struct tee_protmem_pool *pool;
• int rc = 0;
• if (sec_caps & OPTEE_FFA_SEC_CAP_PROTMEM) {

• pool = optee_protmem_alloc_dyn_pool(optee, id);
  

• if (IS_ERR(pool))
  

• 	return PTR_ERR(pool);
  

• rc = tee_device_register_dma_heap(optee->teedev, id, pool);
  

• if (rc)
  

• 	pool->ops->destroy_pool(pool);
  

• }
• return rc;

+}

static int optee_ffa_probe(struct ffa_device *ffa_dev) { const struct ffa_notifier_ops *notif_ops; @@ -918,7 +1057,7 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev) optee); if (IS_ERR(teedev)) { rc = PTR_ERR(teedev);

• goto err_free_pool;
  

• goto err_free_shm_pool;
  

  } optee->teedev = teedev;

@@ -965,6 +1104,9 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev) rc); }

• if (optee_ffa_protmem_pool_init(optee, sec_caps))

Let's add a Kconfig check for DMABUF heaps support here as well.

• pr_info("Protected memory service not available\n");
  

• rc = optee_enumerate_devices(PTA_CMD_GET_DEVICES); if (rc) goto err_unregister_devices;

@@ -978,6 +1120,7 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev) err_unregister_devices: optee_unregister_devices();

• tee_device_unregister_all_dma_heaps(optee->teedev); if (optee->ffa.bottom_half_value != U32_MAX) notif_ops->notify_relinquish(ffa_dev, optee->ffa.bottom_half_value);

@@ -995,7 +1138,7 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev) tee_device_unregister(optee->supp_teedev); err_unreg_teedev: tee_device_unregister(optee->teedev); -err_free_pool: +err_free_shm_pool: tee_shm_pool_free(pool); err_free_optee: kfree(optee); diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h index 5e3c34802121..68e94856205c 100644 --- a/drivers/tee/optee/optee_private.h +++ b/drivers/tee/optee/optee_private.h @@ -174,9 +174,14 @@ struct optee;

• @do_call_with_arg: enters OP-TEE in secure world
• @to_msg_param: converts from struct tee_param to OPTEE_MSG parameters
• @from_msg_param: converts from OPTEE_MSG parameters to struct tee_param

• • @lend_protmem: lends physically contiguous memory as restricted

• • 	memory, inaccessible by the kernel
    

• • @reclaim_protmem: reclaims restricted memory previously lent with

• • 	@lend_protmem() and makes it accessible by the
    

• • 	kernel again
    

  • These OPs are only supposed to be used internally in the OP-TEE driver

• • as a way of abstracting the different methogs of entering OP-TEE in

• • as a way of abstracting the different methods of entering OP-TEE in
  • secure world.
  */

struct optee_ops { @@ -189,6 +194,10 @@ struct optee_ops { int (*from_msg_param)(struct optee *optee, struct tee_param *params, size_t num_params, const struct optee_msg_param *msg_params);

• int (*lend_protmem)(struct optee *optee, struct tee_shm *protmem,

• 	    u16 *end_points, unsigned int ep_count,
  

• 	    u32 use_case);
  

• int (*reclaim_protmem)(struct optee *optee, struct tee_shm *protmem);

}; /** @@ -285,6 +294,8 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params, void optee_supp_init(struct optee_supp *supp); void optee_supp_uninit(struct optee_supp *supp); void optee_supp_release(struct optee_supp *supp); +struct tee_protmem_pool *optee_protmem_alloc_dyn_pool(struct optee *optee,

• 				      enum tee_dma_heap_id id);
  

int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params, struct tee_param *param); diff --git a/drivers/tee/optee/protmem.c b/drivers/tee/optee/protmem.c new file mode 100644 index 000000000000..f7e4f1068ef1 --- /dev/null +++ b/drivers/tee/optee/protmem.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-only +/*

• • Copyright (c) 2025, Linaro Limited
• */

+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

+#include <linux/errno.h> +#include <linux/genalloc.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/tee_core.h> +#include <linux/types.h> +#include "optee_private.h"

+struct optee_protmem_dyn_pool {

• struct tee_protmem_pool pool;
• struct gen_pool *gen_pool;
• struct optee *optee;
• size_t page_count;
• u16 *end_points;
• u_int end_point_count;
• refcount_t refcount;
• u32 use_case;
• struct tee_shm *protmem;
• /* Protects when initializing and tearing down this struct */
• struct mutex mutex;

+};

+static struct optee_protmem_dyn_pool * +to_protmem_dyn_pool(struct tee_protmem_pool *pool) +{

• return container_of(pool, struct optee_protmem_dyn_pool, pool);

+}

+static int init_dyn_protmem(struct optee_protmem_dyn_pool *rp) +{

• int rc;
• rp->protmem = tee_shm_alloc_dma_mem(rp->optee->ctx, rp->page_count);
• if (IS_ERR(rp->protmem)) {

• rc = PTR_ERR(rp->protmem);
  

• goto err_null_protmem;
  

• }
• /*

• * TODO unmap the memory range since the physical memory will
  

• * become inaccesible after the lend_protmem() call.
  

Let's ellaborate this comment to also say that unmap isn't strictly needed here in case a platform supports hypervisor in EL2 which can perform unmapping as part for memory lending to secure world as that will avoid any cache pre-fetch of memory lent to secure world.

With that I can live with this as a ToDo in kernel which can be implemented once we see platforms requiring this change to happen.

• */
  

• rc = rp->optee->ops->lend_protmem(rp->optee, rp->protmem,

• 			  rp->end_points,
  

• 			  rp->end_point_count, rp->use_case);
  

• if (rc)

• goto err_put_shm;
  

• rp->protmem->flags |= TEE_SHM_DYNAMIC;
• rp->gen_pool = gen_pool_create(PAGE_SHIFT, -1);
• if (!rp->gen_pool) {

• rc = -ENOMEM;
  

• goto err_reclaim;
  

• }
• rc = gen_pool_add(rp->gen_pool, rp->protmem->paddr,

• 	  rp->protmem->size, -1);
  

• if (rc)

• goto err_free_pool;
  

• refcount_set(&rp->refcount, 1);
• return 0;

+err_free_pool:

• gen_pool_destroy(rp->gen_pool);
• rp->gen_pool = NULL;

+err_reclaim:

• rp->optee->ops->reclaim_protmem(rp->optee, rp->protmem);

+err_put_shm:

• tee_shm_put(rp->protmem);

+err_null_protmem:

• rp->protmem = NULL;
• return rc;

+}

+static int get_dyn_protmem(struct optee_protmem_dyn_pool *rp) +{

• int rc = 0;
• if (!refcount_inc_not_zero(&rp->refcount)) {

• mutex_lock(&rp->mutex);
  

• if (rp->gen_pool) {
  

• 	/*
  

• 	 * Another thread has already initialized the pool
  

• 	 * before us, or the pool was just about to be torn
  

• 	 * down. Either way we only need to increase the
  

• 	 * refcount and we're done.
  

• 	 */
  

• 	refcount_inc(&rp->refcount);
  

• } else {
  

• 	rc = init_dyn_protmem(rp);
  

• }
  

• mutex_unlock(&rp->mutex);
  

• }
• return rc;

+}

+static void release_dyn_protmem(struct optee_protmem_dyn_pool *rp) +{

• gen_pool_destroy(rp->gen_pool);
• rp->gen_pool = NULL;
• rp->optee->ops->reclaim_protmem(rp->optee, rp->protmem);
• rp->protmem->flags &= ~TEE_SHM_DYNAMIC;
• WARN(refcount_read(&rp->protmem->refcount) != 1, "Unexpected refcount");
• tee_shm_put(rp->protmem);
• rp->protmem = NULL;

+}

+static void put_dyn_protmem(struct optee_protmem_dyn_pool *rp) +{

• if (refcount_dec_and_test(&rp->refcount)) {

• mutex_lock(&rp->mutex);
  

• if (rp->gen_pool)
  

• 	release_dyn_protmem(rp);
  

• mutex_unlock(&rp->mutex);
  

• }

+}

+static int protmem_pool_op_dyn_alloc(struct tee_protmem_pool *pool,

• 		     struct sg_table *sgt, size_t size,
  

• 		     size_t *offs)
  

+{

• struct optee_protmem_dyn_pool *rp = to_protmem_dyn_pool(pool);
• size_t sz = ALIGN(size, PAGE_SIZE);
• phys_addr_t pa;
• int rc;
• rc = get_dyn_protmem(rp);
• if (rc)

• return rc;
  

• pa = gen_pool_alloc(rp->gen_pool, sz);
• if (!pa) {

• rc = -ENOMEM;
  

• goto err_put;
  

• }
• rc = sg_alloc_table(sgt, 1, GFP_KERNEL);
• if (rc)

• goto err_free;
  

• sg_set_page(sgt->sgl, phys_to_page(pa), size, 0);
• *offs = pa - rp->protmem->paddr;
• return 0;

+err_free:

• gen_pool_free(rp->gen_pool, pa, size);

+err_put:

• put_dyn_protmem(rp);
• return rc;

+}

+static void protmem_pool_op_dyn_free(struct tee_protmem_pool *pool,

• 		     struct sg_table *sgt)
  

+{

• struct optee_protmem_dyn_pool *rp = to_protmem_dyn_pool(pool);
• struct scatterlist *sg;
• int i;
• for_each_sgtable_sg(sgt, sg, i)

• gen_pool_free(rp->gen_pool, sg_phys(sg), sg->length);
  

• sg_free_table(sgt);
• put_dyn_protmem(rp);

+}

+static int protmem_pool_op_dyn_update_shm(struct tee_protmem_pool *pool,

• 			  struct sg_table *sgt, size_t offs,
  

• 			  struct tee_shm *shm,
  

• 			  struct tee_shm **parent_shm)
  

+{

• struct optee_protmem_dyn_pool *rp = to_protmem_dyn_pool(pool);
• *parent_shm = rp->protmem;
• return 0;

+}

+static void pool_op_dyn_destroy_pool(struct tee_protmem_pool *pool) +{

• struct optee_protmem_dyn_pool *rp = to_protmem_dyn_pool(pool);
• mutex_destroy(&rp->mutex);
• kfree(rp);

+}

+static struct tee_protmem_pool_ops protmem_pool_ops_dyn = {

• .alloc = protmem_pool_op_dyn_alloc,
• .free = protmem_pool_op_dyn_free,
• .update_shm = protmem_pool_op_dyn_update_shm,
• .destroy_pool = pool_op_dyn_destroy_pool,

+};

+static int get_protmem_config(struct optee *optee, u32 use_case,

• 	      size_t *min_size, u_int *pa_width,
  

• 	      u16 *end_points, u_int *ep_count)
  

+{

• struct tee_param params[2] = {

• [0] = {
  

• 	.attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT,
  

• 	.u.value.a = use_case,
  

• },
  

• [1] = {
  

• 	.attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT,
  

• },
  

• };
• struct optee_shm_arg_entry *entry;
• struct tee_shm *shm_param = NULL;
• struct optee_msg_arg *msg_arg;
• struct tee_shm *shm;
• u_int offs;
• int rc;
• if (end_points && *ep_count) {

• params[1].u.memref.size = *ep_count * sizeof(*end_points);
  

• shm_param = tee_shm_alloc_priv_buf(optee->ctx,
  

• 				   params[1].u.memref.size);
  

• if (IS_ERR(shm_param))
  

• 	return PTR_ERR(shm_param);
  

• params[1].u.memref.shm = shm_param;
  

• }
• msg_arg = optee_get_msg_arg(optee->ctx, ARRAY_SIZE(params), &entry,

• 		    &shm, &offs);
  

• if (IS_ERR(msg_arg)) {

• rc = PTR_ERR(msg_arg);
  

• goto out_free_shm;
  

• }
• msg_arg->cmd = OPTEE_MSG_CMD_GET_PROTMEM_CONFIG;
• rc = optee->ops->to_msg_param(optee, msg_arg->params,

• 		      ARRAY_SIZE(params), params);
  

• if (rc)

• goto out_free_msg;
  

• rc = optee->ops->do_call_with_arg(optee->ctx, shm, offs, false);
• if (rc)

• goto out_free_msg;
  

• if (msg_arg->ret && msg_arg->ret != TEEC_ERROR_SHORT_BUFFER) {

• rc = -EINVAL;
  

• goto out_free_msg;
  

• }
• rc = optee->ops->from_msg_param(optee, params, ARRAY_SIZE(params),

• 			msg_arg->params);
  

• if (rc)

• goto out_free_msg;
  

• if (!msg_arg->ret && end_points &&

•    *ep_count < params[1].u.memref.size / sizeof(u16)) {
  

• rc = -EINVAL;
  

• goto out_free_msg;
  

• }
• *min_size = params[0].u.value.a;
• *pa_width = params[0].u.value.c;
• *ep_count = params[1].u.memref.size / sizeof(u16);
• if (msg_arg->ret == TEEC_ERROR_SHORT_BUFFER) {

• rc = -ENOSPC;
  

• goto out_free_msg;
  

• }
• if (end_points)

• memcpy(end_points, tee_shm_get_va(shm_param, 0),
  

•        params[1].u.memref.size);
  

+out_free_msg:

• optee_free_msg_arg(optee->ctx, entry, offs);

+out_free_shm:

• if (shm_param)

• tee_shm_free(shm_param);
  

• return rc;

+}

+struct tee_protmem_pool *optee_protmem_alloc_dyn_pool(struct optee *optee,

• 				      enum tee_dma_heap_id id)
  

+{

• struct optee_protmem_dyn_pool *rp;
• u32 use_case = id;

Here we can get rid of redundant extra variable with s/id/use_case/.

-Sumit

• size_t min_size;
• u_int pa_width;
• int rc;
• rp = kzalloc(sizeof(*rp), GFP_KERNEL);
• if (!rp)

• return ERR_PTR(-ENOMEM);
  

• rp->use_case = use_case;
• rc = get_protmem_config(optee, use_case, &min_size, &pa_width, NULL,

• 		&rp->end_point_count);
  

• if (rc) {

• if (rc != -ENOSPC)
  

• 	goto err;
  

• rp->end_points = kcalloc(rp->end_point_count,
  

• 			 sizeof(*rp->end_points), GFP_KERNEL);
  

• if (!rp->end_points) {
  

• 	rc = -ENOMEM;
  

• 	goto err;
  

• }
  

• rc = get_protmem_config(optee, use_case, &min_size, &pa_width,
  

• 			rp->end_points, &rp->end_point_count);
  

• if (rc)
  

• 	goto err_kfree_eps;
  

• }
• rc = optee_set_dma_mask(optee, pa_width);
• if (rc)

• goto err_kfree_eps;
  

• rp->pool.ops = &protmem_pool_ops_dyn;
• rp->optee = optee;
• rp->page_count = min_size / PAGE_SIZE;
• mutex_init(&rp->mutex);
• return &rp->pool;

+err_kfree_eps:

• kfree(rp->end_points);

+err:

• kfree(rp);
• return ERR_PTR(rc);

+}

2.43.0