[PATCH v5 0/4] misc: fastrpc: Add polling mode support

[PATCH v5 0/4] misc: fastrpc: Add polling mode support

[Ekansh Gupta]

This patch series adds polling mode feature that have been missing in
upstream FastRPC driver.

- Add changes to move fdlist to ctx structure to avoid code duplicacy.
- Update context mask to support polling mode.
- Add changes to support polling feature.

Userspace change: https://github.com/qualcomm/fastrpc/pull/258
Patch [v4]: https://lore.kernel.org/all/20251128050534.437755-1-ekansh.gupta@oss.qualcomm.com/

Changes in v5:
  - Add more details in commit text.

Changes in v4:
  - Replace hardcoded ctxid mask with GENMASK.
  - Fixed commit text.

Changes in v3:
  - Resolve compilation warning.

Changes in v2:
  - Added comments and fixed commit text.
  - Defined context id position as a macro.
  - Added new IOCTL to control polling mode as always enabling
    it might cause excess power consumption.
  - Cleaned up polling mode implementation.

Ekansh Gupta (4):
  misc: fastrpc: Move fdlist to invoke context structure
  misc: fastrpc: Replace hardcoded ctxid mask with GENMASK
  misc: fastrpc: Expand context ID mask for DSP polling mode support
  misc: fastrpc: Add polling mode support for fastRPC driver

 drivers/misc/fastrpc.c      | 164 +++++++++++++++++++++++++++++++-----
 include/uapi/misc/fastrpc.h |   9 ++
 2 files changed, 151 insertions(+), 22 deletions(-)

-- 
2.34.1

[PATCH v5 1/4] misc: fastrpc: Move fdlist to invoke context structure

[Ekansh Gupta]

The fdlist is currently part of the meta buffer, computed during
put_args. This leads to code duplication when preparing and reading
critical meta buffer contents used by the FastRPC driver.

Move fdlist to the invoke context structure to improve maintainability
and reduce redundancy. This centralizes its handling and simplifies
meta buffer preparation and reading logic.

Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
---
 drivers/misc/fastrpc.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index ee652ef01534..679cd8997a00 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -233,6 +233,7 @@ struct fastrpc_invoke_ctx {
 	int pid;
 	int client_id;
 	u32 sc;
+	u64 *fdlist;
 	u32 *crc;
 	u64 ctxid;
 	u64 msg_sz;
@@ -987,6 +988,7 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
 	rpra = ctx->buf->virt;
 	list = fastrpc_invoke_buf_start(rpra, ctx->nscalars);
 	pages = fastrpc_phy_page_start(list, ctx->nscalars);
+	ctx->fdlist = (u64 *)(pages + ctx->nscalars);
 	args = (uintptr_t)ctx->buf->virt + metalen;
 	rlen = pkt_size - metalen;
 	ctx->rpra = rpra;
@@ -1089,18 +1091,10 @@ static int fastrpc_put_args(struct fastrpc_invoke_ctx *ctx,
 	union fastrpc_remote_arg *rpra = ctx->rpra;
 	struct fastrpc_user *fl = ctx->fl;
 	struct fastrpc_map *mmap = NULL;
-	struct fastrpc_invoke_buf *list;
-	struct fastrpc_phy_page *pages;
-	u64 *fdlist;
-	int i, inbufs, outbufs, handles;
+	int i, inbufs;
 	int ret = 0;
 
 	inbufs = REMOTE_SCALARS_INBUFS(ctx->sc);
-	outbufs = REMOTE_SCALARS_OUTBUFS(ctx->sc);
-	handles = REMOTE_SCALARS_INHANDLES(ctx->sc) + REMOTE_SCALARS_OUTHANDLES(ctx->sc);
-	list = fastrpc_invoke_buf_start(rpra, ctx->nscalars);
-	pages = fastrpc_phy_page_start(list, ctx->nscalars);
-	fdlist = (uint64_t *)(pages + inbufs + outbufs + handles);
 
 	for (i = inbufs; i < ctx->nbufs; ++i) {
 		if (!ctx->maps[i]) {
@@ -1122,9 +1116,9 @@ static int fastrpc_put_args(struct fastrpc_invoke_ctx *ctx,
 cleanup_fdlist:
 	/* Clean up fdlist which is updated by DSP */
 	for (i = 0; i < FASTRPC_MAX_FDLIST; i++) {
-		if (!fdlist[i])
+		if (!ctx->fdlist[i])
 			break;
-		if (!fastrpc_map_lookup(fl, (int)fdlist[i], &mmap))
+		if (!fastrpc_map_lookup(fl, (int)ctx->fdlist[i], &mmap))
 			fastrpc_map_put(mmap);
 	}
 
-- 
2.34.1

[PATCH v5 2/4] misc: fastrpc: Replace hardcoded ctxid mask with GENMASK

[Ekansh Gupta]

Replace the hardcoded context ID mask (0xFF0) with GENMASK(11, 4) to
improve readability and follow kernel bitfield conventions. Use
FIELD_PREP and FIELD_GET instead of manual shifts for setting and
extracting ctxid values.

Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
---
 drivers/misc/fastrpc.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 679cd8997a00..f7fb44a8e9c0 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -22,6 +22,7 @@
 #include <linux/firmware/qcom/qcom_scm.h>
 #include <uapi/misc/fastrpc.h>
 #include <linux/of_reserved_mem.h>
+#include <linux/bitfield.h>
 
 #define ADSP_DOMAIN_ID (0)
 #define MDSP_DOMAIN_ID (1)
@@ -37,7 +38,7 @@
 #define FASTRPC_CTX_MAX (256)
 #define FASTRPC_INIT_HANDLE	1
 #define FASTRPC_DSP_UTILITIES_HANDLE	2
-#define FASTRPC_CTXID_MASK (0xFF0)
+#define FASTRPC_CTXID_MASK GENMASK(11, 4)
 #define INIT_FILELEN_MAX (2 * 1024 * 1024)
 #define INIT_FILE_NAMELEN_MAX (128)
 #define FASTRPC_DEVICE_NAME	"fastrpc"
@@ -489,7 +490,7 @@ static void fastrpc_context_free(struct kref *ref)
 		fastrpc_buf_free(ctx->buf);
 
 	spin_lock_irqsave(&cctx->lock, flags);
-	idr_remove(&cctx->ctx_idr, ctx->ctxid >> 4);
+	idr_remove(&cctx->ctx_idr, FIELD_GET(FASTRPC_CTXID_MASK, ctx->ctxid));
 	spin_unlock_irqrestore(&cctx->lock, flags);
 
 	kfree(ctx->maps);
@@ -625,7 +626,7 @@ static struct fastrpc_invoke_ctx *fastrpc_context_alloc(
 		spin_unlock_irqrestore(&cctx->lock, flags);
 		goto err_idr;
 	}
-	ctx->ctxid = ret << 4;
+	ctx->ctxid = FIELD_PREP(FASTRPC_CTXID_MASK, ret);
 	spin_unlock_irqrestore(&cctx->lock, flags);
 
 	kref_init(&ctx->refcount);
@@ -2451,7 +2452,7 @@ static int fastrpc_rpmsg_callback(struct rpmsg_device *rpdev, void *data,
 	if (len < sizeof(*rsp))
 		return -EINVAL;
 
-	ctxid = ((rsp->ctx & FASTRPC_CTXID_MASK) >> 4);
+	ctxid = FIELD_GET(FASTRPC_CTXID_MASK, rsp->ctx);
 
 	spin_lock_irqsave(&cctx->lock, flags);
 	ctx = idr_find(&cctx->ctx_idr, ctxid);
-- 
2.34.1

Re: [PATCH v5 2/4] misc: fastrpc: Replace hardcoded ctxid mask with GENMASK

[Konrad Dybcio]

On 12/30/25 7:28 AM, Ekansh Gupta wrote:
> Replace the hardcoded context ID mask (0xFF0) with GENMASK(11, 4) to
> improve readability and follow kernel bitfield conventions. Use
> FIELD_PREP and FIELD_GET instead of manual shifts for setting and
> extracting ctxid values.
> 
> Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
> ---
>  drivers/misc/fastrpc.c | 9 +++++----
>  1 file changed, 5 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
> index 679cd8997a00..f7fb44a8e9c0 100644
> --- a/drivers/misc/fastrpc.c
> +++ b/drivers/misc/fastrpc.c
> @@ -22,6 +22,7 @@
>  #include <linux/firmware/qcom/qcom_scm.h>
>  #include <uapi/misc/fastrpc.h>
>  #include <linux/of_reserved_mem.h>
> +#include <linux/bitfield.h>

nit: these are best when sorted

Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>

Konrad

[PATCH v5 3/4] misc: fastrpc: Expand context ID mask for DSP polling mode support

[Ekansh Gupta]

Current FastRPC context uses a 12-bit mask:
  [ID(8 bits)][PD type(4 bits)] = GENMASK(11, 4)

This works for normal calls but fails for DSP polling mode.
Polling mode expects a 16-bit layout:
  [15:8] = context ID (8 bits)
  [7:5]  = reserved
  [4]    = async mode bit
  [3:0]  = PD type (4 bits)

If async bit (bit 4) is set, DSP disables polling. With current
mask, odd IDs can set this bit, causing DSP to skip poll updates.

Update FASTRPC_CTXID_MASK to GENMASK(15, 8) so IDs occupy upper
byte and lower byte is left for DSP flags and PD type.

Reserved bits remain unused. This change is compatible with
polling mode and does not break non-polling behavior.

Bit layout:
  [15:8] = CCCCCCCC (context ID)
  [7:5]  = xxx (reserved)
  [4]    = A (async mode)
  [3:0]  = PPPP (PD type)

Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
---
 drivers/misc/fastrpc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index f7fb44a8e9c0..222ff15e04bd 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -38,7 +38,7 @@
 #define FASTRPC_CTX_MAX (256)
 #define FASTRPC_INIT_HANDLE	1
 #define FASTRPC_DSP_UTILITIES_HANDLE	2
-#define FASTRPC_CTXID_MASK GENMASK(11, 4)
+#define FASTRPC_CTXID_MASK GENMASK(15, 8)
 #define INIT_FILELEN_MAX (2 * 1024 * 1024)
 #define INIT_FILE_NAMELEN_MAX (128)
 #define FASTRPC_DEVICE_NAME	"fastrpc"
-- 
2.34.1

Re: [PATCH v5 3/4] misc: fastrpc: Expand context ID mask for DSP polling mode support

[Dmitry Baryshkov]

On Tue, Dec 30, 2025 at 11:58:30AM +0530, Ekansh Gupta wrote:
> Current FastRPC context uses a 12-bit mask:
>   [ID(8 bits)][PD type(4 bits)] = GENMASK(11, 4)

Is it Linux-only representation or is it also used by the DSP? Will it
work with MSM8916?

> 
> This works for normal calls but fails for DSP polling mode.
> Polling mode expects a 16-bit layout:
>   [15:8] = context ID (8 bits)
>   [7:5]  = reserved
>   [4]    = async mode bit
>   [3:0]  = PD type (4 bits)
> 
> If async bit (bit 4) is set, DSP disables polling. With current
> mask, odd IDs can set this bit, causing DSP to skip poll updates.
> 
> Update FASTRPC_CTXID_MASK to GENMASK(15, 8) so IDs occupy upper
> byte and lower byte is left for DSP flags and PD type.
> 
> Reserved bits remain unused. This change is compatible with
> polling mode and does not break non-polling behavior.
> 
> Bit layout:
>   [15:8] = CCCCCCCC (context ID)
>   [7:5]  = xxx (reserved)
>   [4]    = A (async mode)
>   [3:0]  = PPPP (PD type)
> 
> Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
> ---
>  drivers/misc/fastrpc.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 

-- 
With best wishes
Dmitry

Re: [PATCH v5 3/4] misc: fastrpc: Expand context ID mask for DSP polling mode support

[Ekansh Gupta]

On 1/6/2026 8:23 AM, Dmitry Baryshkov wrote:
> On Tue, Dec 30, 2025 at 11:58:30AM +0530, Ekansh Gupta wrote:
>> Current FastRPC context uses a 12-bit mask:
>>   [ID(8 bits)][PD type(4 bits)] = GENMASK(11, 4)
> Is it Linux-only representation or is it also used by the DSP? Will it
> work with MSM8916?
Apologies for the delay in response, had to go back to check on older DSP software.

DSP will also use this but it handled properly across platforms. DSP get PD details from PD bits
and mask it to use further for async call checks. Other than async call check, the context ID is
majorly used for book-keeping on DSP side(no functional utility).

So, it should also work on MSM8916,
>
>> This works for normal calls but fails for DSP polling mode.
>> Polling mode expects a 16-bit layout:
>>   [15:8] = context ID (8 bits)
>>   [7:5]  = reserved
>>   [4]    = async mode bit
>>   [3:0]  = PD type (4 bits)
>>
>> If async bit (bit 4) is set, DSP disables polling. With current
>> mask, odd IDs can set this bit, causing DSP to skip poll updates.
>>
>> Update FASTRPC_CTXID_MASK to GENMASK(15, 8) so IDs occupy upper
>> byte and lower byte is left for DSP flags and PD type.
>>
>> Reserved bits remain unused. This change is compatible with
>> polling mode and does not break non-polling behavior.
>>
>> Bit layout:
>>   [15:8] = CCCCCCCC (context ID)
>>   [7:5]  = xxx (reserved)
>>   [4]    = A (async mode)
>>   [3:0]  = PPPP (PD type)
>>
>> Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
>> ---
>>  drivers/misc/fastrpc.c | 2 +-
>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>

Re: [PATCH v5 3/4] misc: fastrpc: Expand context ID mask for DSP polling mode support

[Dmitry Baryshkov]

On Thu, Jan 29, 2026 at 03:56:55PM +0530, Ekansh Gupta wrote:
> 
> 
> On 1/6/2026 8:23 AM, Dmitry Baryshkov wrote:
> > On Tue, Dec 30, 2025 at 11:58:30AM +0530, Ekansh Gupta wrote:
> >> Current FastRPC context uses a 12-bit mask:
> >>   [ID(8 bits)][PD type(4 bits)] = GENMASK(11, 4)
> > Is it Linux-only representation or is it also used by the DSP? Will it
> > work with MSM8916?
> Apologies for the delay in response, had to go back to check on older DSP software.
> 
> DSP will also use this but it handled properly across platforms. DSP get PD details from PD bits
> and mask it to use further for async call checks. Other than async call check, the context ID is
> majorly used for book-keeping on DSP side(no functional utility).
> 
> So, it should also work on MSM8916,

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>



> >
> >> This works for normal calls but fails for DSP polling mode.
> >> Polling mode expects a 16-bit layout:
> >>   [15:8] = context ID (8 bits)
> >>   [7:5]  = reserved
> >>   [4]    = async mode bit
> >>   [3:0]  = PD type (4 bits)
> >>
> >> If async bit (bit 4) is set, DSP disables polling. With current
> >> mask, odd IDs can set this bit, causing DSP to skip poll updates.
> >>
> >> Update FASTRPC_CTXID_MASK to GENMASK(15, 8) so IDs occupy upper
> >> byte and lower byte is left for DSP flags and PD type.
> >>
> >> Reserved bits remain unused. This change is compatible with
> >> polling mode and does not break non-polling behavior.
> >>
> >> Bit layout:
> >>   [15:8] = CCCCCCCC (context ID)
> >>   [7:5]  = xxx (reserved)
> >>   [4]    = A (async mode)
> >>   [3:0]  = PPPP (PD type)
> >>
> >> Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
> >> ---
> >>  drivers/misc/fastrpc.c | 2 +-
> >>  1 file changed, 1 insertion(+), 1 deletion(-)
> >>
> 

-- 
With best wishes
Dmitry

[PATCH v5 4/4] misc: fastrpc: Add polling mode support for fastRPC driver

[Ekansh Gupta]

For any remote call to DSP, after sending an invocation message,
fastRPC driver waits for glink response and during this time the
CPU can go into low power modes. This adds latency to overall fastrpc
call as CPU wakeup and scheduling latencies are included. Add polling
mode support with which fastRPC driver will poll continuously on a
memory after sending a message to remote subsystem which will eliminate
CPU wakeup and scheduling latencies and reduce fastRPC overhead. Poll
mode can be enabled by user by using FASTRPC_IOCTL_SET_OPTION ioctl
request with FASTRPC_POLL_MODE request id.

Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
---
 drivers/misc/fastrpc.c      | 139 ++++++++++++++++++++++++++++++++++--
 include/uapi/misc/fastrpc.h |   9 +++
 2 files changed, 141 insertions(+), 7 deletions(-)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 222ff15e04bd..d95d31d27b82 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -22,6 +22,8 @@
 #include <linux/firmware/qcom/qcom_scm.h>
 #include <uapi/misc/fastrpc.h>
 #include <linux/of_reserved_mem.h>
+#include <linux/compiler.h>
+#include <linux/iopoll.h>
 #include <linux/bitfield.h>
 
 #define ADSP_DOMAIN_ID (0)
@@ -38,6 +40,7 @@
 #define FASTRPC_CTX_MAX (256)
 #define FASTRPC_INIT_HANDLE	1
 #define FASTRPC_DSP_UTILITIES_HANDLE	2
+#define FASTRPC_MAX_STATIC_HANDLE (20)
 #define FASTRPC_CTXID_MASK GENMASK(15, 8)
 #define INIT_FILELEN_MAX (2 * 1024 * 1024)
 #define INIT_FILE_NAMELEN_MAX (128)
@@ -106,6 +109,12 @@
 
 #define miscdev_to_fdevice(d) container_of(d, struct fastrpc_device, miscdev)
 
+/* Poll response number from remote processor for call completion */
+#define FASTRPC_POLL_RESPONSE (0xdecaf)
+
+/* Polling mode timeout limit */
+#define FASTRPC_POLL_MAX_TIMEOUT_US (10000)
+
 struct fastrpc_phy_page {
 	u64 addr;		/* physical address */
 	u64 size;		/* size of contiguous region */
@@ -236,8 +245,14 @@ struct fastrpc_invoke_ctx {
 	u32 sc;
 	u64 *fdlist;
 	u32 *crc;
+	/* Poll memory that DSP updates */
+	u32 *poll;
 	u64 ctxid;
 	u64 msg_sz;
+	/* work done status flag */
+	bool is_work_done;
+	/* process updates poll memory instead of glink response */
+	bool is_polled;
 	struct kref refcount;
 	struct list_head node; /* list of ctxs */
 	struct completion work;
@@ -301,6 +316,8 @@ struct fastrpc_user {
 	int client_id;
 	int pd;
 	bool is_secure_dev;
+	/* Flags poll mode state */
+	bool poll_mode;
 	/* Lock for lists */
 	spinlock_t lock;
 	/* lock for allocations */
@@ -894,7 +911,8 @@ static int fastrpc_get_meta_size(struct fastrpc_invoke_ctx *ctx)
 		sizeof(struct fastrpc_invoke_buf) +
 		sizeof(struct fastrpc_phy_page)) * ctx->nscalars +
 		sizeof(u64) * FASTRPC_MAX_FDLIST +
-		sizeof(u32) * FASTRPC_MAX_CRCLIST;
+		sizeof(u32) * FASTRPC_MAX_CRCLIST +
+		sizeof(u32);
 
 	return size;
 }
@@ -990,6 +1008,7 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
 	list = fastrpc_invoke_buf_start(rpra, ctx->nscalars);
 	pages = fastrpc_phy_page_start(list, ctx->nscalars);
 	ctx->fdlist = (u64 *)(pages + ctx->nscalars);
+	ctx->poll = (u32 *)(ctx->fdlist + FASTRPC_MAX_FDLIST + FASTRPC_MAX_CRCLIST);
 	args = (uintptr_t)ctx->buf->virt + metalen;
 	rlen = pkt_size - metalen;
 	ctx->rpra = rpra;
@@ -1158,6 +1177,75 @@ static int fastrpc_invoke_send(struct fastrpc_session_ctx *sctx,
 
 }
 
+static inline u32 fastrpc_poll_op(void *p)
+{
+	struct fastrpc_invoke_ctx *ctx = p;
+
+	dma_rmb();
+	return READ_ONCE(*ctx->poll);
+}
+
+static int poll_for_remote_response(struct fastrpc_invoke_ctx *ctx)
+{
+	u32 val;
+	int ret;
+
+	/*
+	 * Poll until DSP writes FASTRPC_POLL_RESPONSE into *ctx->poll
+	 * or until another path marks the work done.
+	 */
+	ret = read_poll_timeout_atomic(fastrpc_poll_op, val,
+				       (val == FASTRPC_POLL_RESPONSE) ||
+				       ctx->is_work_done, 1,
+				       FASTRPC_POLL_MAX_TIMEOUT_US, false, ctx);
+
+	if (!ret && val == FASTRPC_POLL_RESPONSE) {
+		ctx->is_work_done = true;
+		ctx->retval = 0;
+	}
+
+	if (ret == -ETIMEDOUT)
+		ret = -EIO;
+
+	return ret;
+}
+
+static inline int fastrpc_wait_for_response(struct fastrpc_invoke_ctx *ctx,
+					    u32 kernel)
+{
+	int err = 0;
+
+	if (kernel) {
+		if (!wait_for_completion_timeout(&ctx->work, 10 * HZ))
+			err = -ETIMEDOUT;
+	} else {
+		err = wait_for_completion_interruptible(&ctx->work);
+	}
+
+	return err;
+}
+
+static int fastrpc_wait_for_completion(struct fastrpc_invoke_ctx *ctx,
+				       u32 kernel)
+{
+	int err;
+
+	do {
+		if (ctx->is_polled) {
+			err = poll_for_remote_response(ctx);
+			/* If polling timed out, move to normal response mode */
+			if (err)
+				ctx->is_polled = false;
+		} else {
+			err = fastrpc_wait_for_response(ctx, kernel);
+			if (err)
+				return err;
+		}
+	} while (!ctx->is_work_done);
+
+	return err;
+}
+
 static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
 				   u32 handle, u32 sc,
 				   struct fastrpc_invoke_args *args)
@@ -1193,16 +1281,25 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
 	if (err)
 		goto bail;
 
-	if (kernel) {
-		if (!wait_for_completion_timeout(&ctx->work, 10 * HZ))
-			err = -ETIMEDOUT;
-	} else {
-		err = wait_for_completion_interruptible(&ctx->work);
-	}
+	/*
+	 * Set message context as polled if the call is for a user PD
+	 * dynamic module and user has enabled poll mode.
+	 */
+	if (handle > FASTRPC_MAX_STATIC_HANDLE && fl->pd == USER_PD &&
+	    fl->poll_mode)
+		ctx->is_polled = true;
+
+	err = fastrpc_wait_for_completion(ctx, kernel);
 
 	if (err)
 		goto bail;
 
+	if (!ctx->is_work_done) {
+		err = -ETIMEDOUT;
+		dev_dbg(fl->sctx->dev, "Invalid workdone state for handle 0x%x, sc 0x%x\n",
+			handle, sc);
+		goto bail;
+	}
 	/* make sure that all memory writes by DSP are seen by CPU */
 	dma_rmb();
 	/* populate all the output buffers with results */
@@ -1780,6 +1877,30 @@ static int fastrpc_get_info_from_kernel(struct fastrpc_ioctl_capability *cap,
 	return 0;
 }
 
+static int fastrpc_set_option(struct fastrpc_user *fl, char __user *argp)
+{
+	struct fastrpc_ioctl_set_option opt = {0};
+	int i;
+
+	if (copy_from_user(&opt, argp, sizeof(opt)))
+		return -EFAULT;
+
+	for (i = 0; i < ARRAY_SIZE(opt.reserved); i++) {
+		if (opt.reserved[i] != 0)
+			return -EINVAL;
+	}
+
+	if (opt.req != FASTRPC_POLL_MODE)
+		return -EINVAL;
+
+	if (opt.value)
+		fl->poll_mode = true;
+	else
+		fl->poll_mode = false;
+
+	return 0;
+}
+
 static int fastrpc_get_dsp_info(struct fastrpc_user *fl, char __user *argp)
 {
 	struct fastrpc_ioctl_capability cap = {0};
@@ -2134,6 +2255,9 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
 	case FASTRPC_IOCTL_MEM_UNMAP:
 		err = fastrpc_req_mem_unmap(fl, argp);
 		break;
+	case FASTRPC_IOCTL_SET_OPTION:
+		err = fastrpc_set_option(fl, argp);
+		break;
 	case FASTRPC_IOCTL_GET_DSP_INFO:
 		err = fastrpc_get_dsp_info(fl, argp);
 		break;
@@ -2465,6 +2589,7 @@ static int fastrpc_rpmsg_callback(struct rpmsg_device *rpdev, void *data,
 
 	ctx->retval = rsp->retval;
 	complete(&ctx->work);
+	ctx->is_work_done = true;
 
 	/*
 	 * The DMA buffer associated with the context cannot be freed in
diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
index c6e2925f47e6..3207c42fb318 100644
--- a/include/uapi/misc/fastrpc.h
+++ b/include/uapi/misc/fastrpc.h
@@ -16,6 +16,7 @@
 #define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)
 #define FASTRPC_IOCTL_MEM_MAP		_IOWR('R', 10, struct fastrpc_mem_map)
 #define FASTRPC_IOCTL_MEM_UNMAP		_IOWR('R', 11, struct fastrpc_mem_unmap)
+#define FASTRPC_IOCTL_SET_OPTION	_IOWR('R', 12, struct fastrpc_ioctl_set_option)
 #define FASTRPC_IOCTL_GET_DSP_INFO	_IOWR('R', 13, struct fastrpc_ioctl_capability)
 
 /**
@@ -66,6 +67,8 @@ enum fastrpc_proc_attr {
 
 /* Fastrpc attribute for memory protection of buffers */
 #define FASTRPC_ATTR_SECUREMAP	(1)
+/* Set option request ID to enable poll mode */
+#define FASTRPC_POLL_MODE	(1)
 
 struct fastrpc_invoke_args {
 	__u64 ptr;
@@ -133,6 +136,12 @@ struct fastrpc_mem_unmap {
 	__s32 reserved[5];
 };
 
+struct fastrpc_ioctl_set_option {
+	__u32 req;	/* request id */
+	__u32 value;	/* value */
+	__s32 reserved[6];
+};
+
 struct fastrpc_ioctl_capability {
 	__u32 unused; /* deprecated, ignored by the kernel */
 	__u32 attribute_id;
-- 
2.34.1

Re: [PATCH v5 4/4] misc: fastrpc: Add polling mode support for fastRPC driver

[Dmitry Baryshkov]

On Tue, Dec 30, 2025 at 11:58:31AM +0530, Ekansh Gupta wrote:
> For any remote call to DSP, after sending an invocation message,
> fastRPC driver waits for glink response and during this time the
> CPU can go into low power modes. This adds latency to overall fastrpc
> call as CPU wakeup and scheduling latencies are included. Add polling
> mode support with which fastRPC driver will poll continuously on a
> memory after sending a message to remote subsystem which will eliminate
> CPU wakeup and scheduling latencies and reduce fastRPC overhead. Poll
> mode can be enabled by user by using FASTRPC_IOCTL_SET_OPTION ioctl
> request with FASTRPC_POLL_MODE request id.
> 
> Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
> ---
>  drivers/misc/fastrpc.c      | 139 ++++++++++++++++++++++++++++++++++--
>  include/uapi/misc/fastrpc.h |   9 +++
>  2 files changed, 141 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
> index 222ff15e04bd..d95d31d27b82 100644
> --- a/drivers/misc/fastrpc.c
> +++ b/drivers/misc/fastrpc.c
> @@ -22,6 +22,8 @@
>  #include <linux/firmware/qcom/qcom_scm.h>
>  #include <uapi/misc/fastrpc.h>
>  #include <linux/of_reserved_mem.h>
> +#include <linux/compiler.h>
> +#include <linux/iopoll.h>
>  #include <linux/bitfield.h>
>  
>  #define ADSP_DOMAIN_ID (0)
> @@ -38,6 +40,7 @@
>  #define FASTRPC_CTX_MAX (256)
>  #define FASTRPC_INIT_HANDLE	1
>  #define FASTRPC_DSP_UTILITIES_HANDLE	2
> +#define FASTRPC_MAX_STATIC_HANDLE (20)
>  #define FASTRPC_CTXID_MASK GENMASK(15, 8)
>  #define INIT_FILELEN_MAX (2 * 1024 * 1024)
>  #define INIT_FILE_NAMELEN_MAX (128)
> @@ -106,6 +109,12 @@
>  
>  #define miscdev_to_fdevice(d) container_of(d, struct fastrpc_device, miscdev)
>  
> +/* Poll response number from remote processor for call completion */
> +#define FASTRPC_POLL_RESPONSE (0xdecaf)
> +
> +/* Polling mode timeout limit */
> +#define FASTRPC_POLL_MAX_TIMEOUT_US (10000)
> +
>  struct fastrpc_phy_page {
>  	u64 addr;		/* physical address */
>  	u64 size;		/* size of contiguous region */
> @@ -236,8 +245,14 @@ struct fastrpc_invoke_ctx {
>  	u32 sc;
>  	u64 *fdlist;
>  	u32 *crc;
> +	/* Poll memory that DSP updates */
> +	u32 *poll;
>  	u64 ctxid;
>  	u64 msg_sz;
> +	/* work done status flag */
> +	bool is_work_done;
> +	/* process updates poll memory instead of glink response */
> +	bool is_polled;
>  	struct kref refcount;
>  	struct list_head node; /* list of ctxs */
>  	struct completion work;
> @@ -301,6 +316,8 @@ struct fastrpc_user {
>  	int client_id;
>  	int pd;
>  	bool is_secure_dev;
> +	/* Flags poll mode state */
> +	bool poll_mode;
>  	/* Lock for lists */
>  	spinlock_t lock;
>  	/* lock for allocations */
> @@ -894,7 +911,8 @@ static int fastrpc_get_meta_size(struct fastrpc_invoke_ctx *ctx)
>  		sizeof(struct fastrpc_invoke_buf) +
>  		sizeof(struct fastrpc_phy_page)) * ctx->nscalars +
>  		sizeof(u64) * FASTRPC_MAX_FDLIST +
> -		sizeof(u32) * FASTRPC_MAX_CRCLIST;
> +		sizeof(u32) * FASTRPC_MAX_CRCLIST +
> +		sizeof(u32);
>  
>  	return size;
>  }
> @@ -990,6 +1008,7 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
>  	list = fastrpc_invoke_buf_start(rpra, ctx->nscalars);
>  	pages = fastrpc_phy_page_start(list, ctx->nscalars);
>  	ctx->fdlist = (u64 *)(pages + ctx->nscalars);
> +	ctx->poll = (u32 *)(ctx->fdlist + FASTRPC_MAX_FDLIST + FASTRPC_MAX_CRCLIST);

This doesn't seem to match the calculation few lines ago. fdlist is a
pointer. On 64-bit systems ctx->poll will point to (uintptr_t)ctx->fdlist +
sizeof(u64) * FASTRPC_MAX_FDLIST + (sizeof u64) * FASTRPC_MAX_CRCLIST,
while in fastrpc_get_meta_size it was ... + sizeof(u32) *
FASTRPC_MAX_CRCLIST.

Am I missing something?

>  	args = (uintptr_t)ctx->buf->virt + metalen;
>  	rlen = pkt_size - metalen;
>  	ctx->rpra = rpra;
> @@ -1158,6 +1177,75 @@ static int fastrpc_invoke_send(struct fastrpc_session_ctx *sctx,
>  
>  }
>  
> +static inline u32 fastrpc_poll_op(void *p)
> +{
> +	struct fastrpc_invoke_ctx *ctx = p;
> +
> +	dma_rmb();
> +	return READ_ONCE(*ctx->poll);
> +}
> +
> +static int poll_for_remote_response(struct fastrpc_invoke_ctx *ctx)
> +{
> +	u32 val;
> +	int ret;
> +
> +	/*
> +	 * Poll until DSP writes FASTRPC_POLL_RESPONSE into *ctx->poll
> +	 * or until another path marks the work done.
> +	 */
> +	ret = read_poll_timeout_atomic(fastrpc_poll_op, val,
> +				       (val == FASTRPC_POLL_RESPONSE) ||
> +				       ctx->is_work_done, 1,
> +				       FASTRPC_POLL_MAX_TIMEOUT_US, false, ctx);
> +
> +	if (!ret && val == FASTRPC_POLL_RESPONSE) {
> +		ctx->is_work_done = true;
> +		ctx->retval = 0;
> +	}
> +
> +	if (ret == -ETIMEDOUT)
> +		ret = -EIO;
> +
> +	return ret;
> +}
> +
> +static inline int fastrpc_wait_for_response(struct fastrpc_invoke_ctx *ctx,
> +					    u32 kernel)
> +{
> +	int err = 0;
> +
> +	if (kernel) {
> +		if (!wait_for_completion_timeout(&ctx->work, 10 * HZ))
> +			err = -ETIMEDOUT;
> +	} else {
> +		err = wait_for_completion_interruptible(&ctx->work);
> +	}
> +
> +	return err;
> +}
> +
> +static int fastrpc_wait_for_completion(struct fastrpc_invoke_ctx *ctx,
> +				       u32 kernel)
> +{
> +	int err;
> +
> +	do {
> +		if (ctx->is_polled) {
> +			err = poll_for_remote_response(ctx);
> +			/* If polling timed out, move to normal response mode */
> +			if (err)
> +				ctx->is_polled = false;
> +		} else {
> +			err = fastrpc_wait_for_response(ctx, kernel);
> +			if (err)
> +				return err;
> +		}
> +	} while (!ctx->is_work_done);
> +
> +	return err;
> +}
> +
>  static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
>  				   u32 handle, u32 sc,
>  				   struct fastrpc_invoke_args *args)
> @@ -1193,16 +1281,25 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
>  	if (err)
>  		goto bail;
>  
> -	if (kernel) {
> -		if (!wait_for_completion_timeout(&ctx->work, 10 * HZ))
> -			err = -ETIMEDOUT;
> -	} else {
> -		err = wait_for_completion_interruptible(&ctx->work);
> -	}
> +	/*
> +	 * Set message context as polled if the call is for a user PD
> +	 * dynamic module and user has enabled poll mode.
> +	 */
> +	if (handle > FASTRPC_MAX_STATIC_HANDLE && fl->pd == USER_PD &&
> +	    fl->poll_mode)
> +		ctx->is_polled = true;
> +
> +	err = fastrpc_wait_for_completion(ctx, kernel);
>  
>  	if (err)
>  		goto bail;
>  
> +	if (!ctx->is_work_done) {
> +		err = -ETIMEDOUT;
> +		dev_dbg(fl->sctx->dev, "Invalid workdone state for handle 0x%x, sc 0x%x\n",
> +			handle, sc);
> +		goto bail;
> +	}
>  	/* make sure that all memory writes by DSP are seen by CPU */
>  	dma_rmb();
>  	/* populate all the output buffers with results */
> @@ -1780,6 +1877,30 @@ static int fastrpc_get_info_from_kernel(struct fastrpc_ioctl_capability *cap,
>  	return 0;
>  }
>  
> +static int fastrpc_set_option(struct fastrpc_user *fl, char __user *argp)
> +{
> +	struct fastrpc_ioctl_set_option opt = {0};
> +	int i;
> +
> +	if (copy_from_user(&opt, argp, sizeof(opt)))
> +		return -EFAULT;
> +
> +	for (i = 0; i < ARRAY_SIZE(opt.reserved); i++) {
> +		if (opt.reserved[i] != 0)
> +			return -EINVAL;
> +	}
> +
> +	if (opt.req != FASTRPC_POLL_MODE)
> +		return -EINVAL;
> +
> +	if (opt.value)
> +		fl->poll_mode = true;
> +	else
> +		fl->poll_mode = false;

Is poll_mode supported on MSM8916?

> +
> +	return 0;
> +}
> +
>  static int fastrpc_get_dsp_info(struct fastrpc_user *fl, char __user *argp)
>  {
>  	struct fastrpc_ioctl_capability cap = {0};
> @@ -2134,6 +2255,9 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
>  	case FASTRPC_IOCTL_MEM_UNMAP:
>  		err = fastrpc_req_mem_unmap(fl, argp);
>  		break;
> +	case FASTRPC_IOCTL_SET_OPTION:
> +		err = fastrpc_set_option(fl, argp);
> +		break;
>  	case FASTRPC_IOCTL_GET_DSP_INFO:
>  		err = fastrpc_get_dsp_info(fl, argp);
>  		break;
> @@ -2465,6 +2589,7 @@ static int fastrpc_rpmsg_callback(struct rpmsg_device *rpdev, void *data,
>  
>  	ctx->retval = rsp->retval;
>  	complete(&ctx->work);
> +	ctx->is_work_done = true;
>  
>  	/*
>  	 * The DMA buffer associated with the context cannot be freed in
> diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
> index c6e2925f47e6..3207c42fb318 100644
> --- a/include/uapi/misc/fastrpc.h
> +++ b/include/uapi/misc/fastrpc.h
> @@ -16,6 +16,7 @@
>  #define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)
>  #define FASTRPC_IOCTL_MEM_MAP		_IOWR('R', 10, struct fastrpc_mem_map)
>  #define FASTRPC_IOCTL_MEM_UNMAP		_IOWR('R', 11, struct fastrpc_mem_unmap)
> +#define FASTRPC_IOCTL_SET_OPTION	_IOWR('R', 12, struct fastrpc_ioctl_set_option)
>  #define FASTRPC_IOCTL_GET_DSP_INFO	_IOWR('R', 13, struct fastrpc_ioctl_capability)
>  
>  /**
> @@ -66,6 +67,8 @@ enum fastrpc_proc_attr {
>  
>  /* Fastrpc attribute for memory protection of buffers */
>  #define FASTRPC_ATTR_SECUREMAP	(1)
> +/* Set option request ID to enable poll mode */
> +#define FASTRPC_POLL_MODE	(1)

Is it related to FASTRPC_ATTR_SECUREMAP? Why is it a part of the same
visual block?

>  
>  struct fastrpc_invoke_args {
>  	__u64 ptr;
> @@ -133,6 +136,12 @@ struct fastrpc_mem_unmap {
>  	__s32 reserved[5];
>  };
>  
> +struct fastrpc_ioctl_set_option {
> +	__u32 req;	/* request id */
> +	__u32 value;	/* value */
> +	__s32 reserved[6];

What are you reserving it for?

> +};
> +
>  struct fastrpc_ioctl_capability {
>  	__u32 unused; /* deprecated, ignored by the kernel */
>  	__u32 attribute_id;
> -- 
> 2.34.1
> 

-- 
With best wishes
Dmitry

Re: [PATCH v5 4/4] misc: fastrpc: Add polling mode support for fastRPC driver

[Ekansh Gupta]

On 1/6/2026 8:29 AM, Dmitry Baryshkov wrote:
> On Tue, Dec 30, 2025 at 11:58:31AM +0530, Ekansh Gupta wrote:
>> For any remote call to DSP, after sending an invocation message,
>> fastRPC driver waits for glink response and during this time the
>> CPU can go into low power modes. This adds latency to overall fastrpc
>> call as CPU wakeup and scheduling latencies are included. Add polling
>> mode support with which fastRPC driver will poll continuously on a
>> memory after sending a message to remote subsystem which will eliminate
>> CPU wakeup and scheduling latencies and reduce fastRPC overhead. Poll
>> mode can be enabled by user by using FASTRPC_IOCTL_SET_OPTION ioctl
>> request with FASTRPC_POLL_MODE request id.
>>
>> Signed-off-by: Ekansh Gupta <ekansh.gupta@oss.qualcomm.com>
>> ---
>>  drivers/misc/fastrpc.c      | 139 ++++++++++++++++++++++++++++++++++--
>>  include/uapi/misc/fastrpc.h |   9 +++
>>  2 files changed, 141 insertions(+), 7 deletions(-)
>>
>> diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
>> index 222ff15e04bd..d95d31d27b82 100644
>> --- a/drivers/misc/fastrpc.c
>> +++ b/drivers/misc/fastrpc.c
>> @@ -22,6 +22,8 @@
>>  #include <linux/firmware/qcom/qcom_scm.h>
>>  #include <uapi/misc/fastrpc.h>
>>  #include <linux/of_reserved_mem.h>
>> +#include <linux/compiler.h>
>> +#include <linux/iopoll.h>
>>  #include <linux/bitfield.h>
>>  
>>  #define ADSP_DOMAIN_ID (0)
>> @@ -38,6 +40,7 @@
>>  #define FASTRPC_CTX_MAX (256)
>>  #define FASTRPC_INIT_HANDLE	1
>>  #define FASTRPC_DSP_UTILITIES_HANDLE	2
>> +#define FASTRPC_MAX_STATIC_HANDLE (20)
>>  #define FASTRPC_CTXID_MASK GENMASK(15, 8)
>>  #define INIT_FILELEN_MAX (2 * 1024 * 1024)
>>  #define INIT_FILE_NAMELEN_MAX (128)
>> @@ -106,6 +109,12 @@
>>  
>>  #define miscdev_to_fdevice(d) container_of(d, struct fastrpc_device, miscdev)
>>  
>> +/* Poll response number from remote processor for call completion */
>> +#define FASTRPC_POLL_RESPONSE (0xdecaf)
>> +
>> +/* Polling mode timeout limit */
>> +#define FASTRPC_POLL_MAX_TIMEOUT_US (10000)
>> +
>>  struct fastrpc_phy_page {
>>  	u64 addr;		/* physical address */
>>  	u64 size;		/* size of contiguous region */
>> @@ -236,8 +245,14 @@ struct fastrpc_invoke_ctx {
>>  	u32 sc;
>>  	u64 *fdlist;
>>  	u32 *crc;
>> +	/* Poll memory that DSP updates */
>> +	u32 *poll;
>>  	u64 ctxid;
>>  	u64 msg_sz;
>> +	/* work done status flag */
>> +	bool is_work_done;
>> +	/* process updates poll memory instead of glink response */
>> +	bool is_polled;
>>  	struct kref refcount;
>>  	struct list_head node; /* list of ctxs */
>>  	struct completion work;
>> @@ -301,6 +316,8 @@ struct fastrpc_user {
>>  	int client_id;
>>  	int pd;
>>  	bool is_secure_dev;
>> +	/* Flags poll mode state */
>> +	bool poll_mode;
>>  	/* Lock for lists */
>>  	spinlock_t lock;
>>  	/* lock for allocations */
>> @@ -894,7 +911,8 @@ static int fastrpc_get_meta_size(struct fastrpc_invoke_ctx *ctx)
>>  		sizeof(struct fastrpc_invoke_buf) +
>>  		sizeof(struct fastrpc_phy_page)) * ctx->nscalars +
>>  		sizeof(u64) * FASTRPC_MAX_FDLIST +
>> -		sizeof(u32) * FASTRPC_MAX_CRCLIST;
>> +		sizeof(u32) * FASTRPC_MAX_CRCLIST +
>> +		sizeof(u32);
>>  
>>  	return size;
>>  }
>> @@ -990,6 +1008,7 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx)
>>  	list = fastrpc_invoke_buf_start(rpra, ctx->nscalars);
>>  	pages = fastrpc_phy_page_start(list, ctx->nscalars);
>>  	ctx->fdlist = (u64 *)(pages + ctx->nscalars);
>> +	ctx->poll = (u32 *)(ctx->fdlist + FASTRPC_MAX_FDLIST + FASTRPC_MAX_CRCLIST);
> This doesn't seem to match the calculation few lines ago. fdlist is a
> pointer. On 64-bit systems ctx->poll will point to (uintptr_t)ctx->fdlist +
> sizeof(u64) * FASTRPC_MAX_FDLIST + (sizeof u64) * FASTRPC_MAX_CRCLIST,
> while in fastrpc_get_meta_size it was ... + sizeof(u32) *
> FASTRPC_MAX_CRCLIST.
>
> Am I missing something?
I should be:

(uintptr_t)ctx->fdlist + sizeof(u64) * FASTRPC_MAX_FDLIST + (sizeof u32) * FASTRPC_MAX_CRCLIST

based on the fastrpc_get_meta_size calculation, I'll correct this calculation.

>
>>  	args = (uintptr_t)ctx->buf->virt + metalen;
>>  	rlen = pkt_size - metalen;
>>  	ctx->rpra = rpra;
>> @@ -1158,6 +1177,75 @@ static int fastrpc_invoke_send(struct fastrpc_session_ctx *sctx,
>>  
>>  }
>>  
>> +static inline u32 fastrpc_poll_op(void *p)
>> +{
>> +	struct fastrpc_invoke_ctx *ctx = p;
>> +
>> +	dma_rmb();
>> +	return READ_ONCE(*ctx->poll);
>> +}
>> +
>> +static int poll_for_remote_response(struct fastrpc_invoke_ctx *ctx)
>> +{
>> +	u32 val;
>> +	int ret;
>> +
>> +	/*
>> +	 * Poll until DSP writes FASTRPC_POLL_RESPONSE into *ctx->poll
>> +	 * or until another path marks the work done.
>> +	 */
>> +	ret = read_poll_timeout_atomic(fastrpc_poll_op, val,
>> +				       (val == FASTRPC_POLL_RESPONSE) ||
>> +				       ctx->is_work_done, 1,
>> +				       FASTRPC_POLL_MAX_TIMEOUT_US, false, ctx);
>> +
>> +	if (!ret && val == FASTRPC_POLL_RESPONSE) {
>> +		ctx->is_work_done = true;
>> +		ctx->retval = 0;
>> +	}
>> +
>> +	if (ret == -ETIMEDOUT)
>> +		ret = -EIO;
>> +
>> +	return ret;
>> +}
>> +
>> +static inline int fastrpc_wait_for_response(struct fastrpc_invoke_ctx *ctx,
>> +					    u32 kernel)
>> +{
>> +	int err = 0;
>> +
>> +	if (kernel) {
>> +		if (!wait_for_completion_timeout(&ctx->work, 10 * HZ))
>> +			err = -ETIMEDOUT;
>> +	} else {
>> +		err = wait_for_completion_interruptible(&ctx->work);
>> +	}
>> +
>> +	return err;
>> +}
>> +
>> +static int fastrpc_wait_for_completion(struct fastrpc_invoke_ctx *ctx,
>> +				       u32 kernel)
>> +{
>> +	int err;
>> +
>> +	do {
>> +		if (ctx->is_polled) {
>> +			err = poll_for_remote_response(ctx);
>> +			/* If polling timed out, move to normal response mode */
>> +			if (err)
>> +				ctx->is_polled = false;
>> +		} else {
>> +			err = fastrpc_wait_for_response(ctx, kernel);
>> +			if (err)
>> +				return err;
>> +		}
>> +	} while (!ctx->is_work_done);
>> +
>> +	return err;
>> +}
>> +
>>  static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
>>  				   u32 handle, u32 sc,
>>  				   struct fastrpc_invoke_args *args)
>> @@ -1193,16 +1281,25 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl,  u32 kernel,
>>  	if (err)
>>  		goto bail;
>>  
>> -	if (kernel) {
>> -		if (!wait_for_completion_timeout(&ctx->work, 10 * HZ))
>> -			err = -ETIMEDOUT;
>> -	} else {
>> -		err = wait_for_completion_interruptible(&ctx->work);
>> -	}
>> +	/*
>> +	 * Set message context as polled if the call is for a user PD
>> +	 * dynamic module and user has enabled poll mode.
>> +	 */
>> +	if (handle > FASTRPC_MAX_STATIC_HANDLE && fl->pd == USER_PD &&
>> +	    fl->poll_mode)
>> +		ctx->is_polled = true;
>> +
>> +	err = fastrpc_wait_for_completion(ctx, kernel);
>>  
>>  	if (err)
>>  		goto bail;
>>  
>> +	if (!ctx->is_work_done) {
>> +		err = -ETIMEDOUT;
>> +		dev_dbg(fl->sctx->dev, "Invalid workdone state for handle 0x%x, sc 0x%x\n",
>> +			handle, sc);
>> +		goto bail;
>> +	}
>>  	/* make sure that all memory writes by DSP are seen by CPU */
>>  	dma_rmb();
>>  	/* populate all the output buffers with results */
>> @@ -1780,6 +1877,30 @@ static int fastrpc_get_info_from_kernel(struct fastrpc_ioctl_capability *cap,
>>  	return 0;
>>  }
>>  
>> +static int fastrpc_set_option(struct fastrpc_user *fl, char __user *argp)
>> +{
>> +	struct fastrpc_ioctl_set_option opt = {0};
>> +	int i;
>> +
>> +	if (copy_from_user(&opt, argp, sizeof(opt)))
>> +		return -EFAULT;
>> +
>> +	for (i = 0; i < ARRAY_SIZE(opt.reserved); i++) {
>> +		if (opt.reserved[i] != 0)
>> +			return -EINVAL;
>> +	}
>> +
>> +	if (opt.req != FASTRPC_POLL_MODE)
>> +		return -EINVAL;
>> +
>> +	if (opt.value)
>> +		fl->poll_mode = true;
>> +	else
>> +		fl->poll_mode = false;
> Is poll_mode supported on MSM8916?
No, but it will fallback to rpmsg_callback in case polling is enabled from kernel but
not enabled from DSP.
>
>> +
>> +	return 0;
>> +}
>> +
>>  static int fastrpc_get_dsp_info(struct fastrpc_user *fl, char __user *argp)
>>  {
>>  	struct fastrpc_ioctl_capability cap = {0};
>> @@ -2134,6 +2255,9 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
>>  	case FASTRPC_IOCTL_MEM_UNMAP:
>>  		err = fastrpc_req_mem_unmap(fl, argp);
>>  		break;
>> +	case FASTRPC_IOCTL_SET_OPTION:
>> +		err = fastrpc_set_option(fl, argp);
>> +		break;
>>  	case FASTRPC_IOCTL_GET_DSP_INFO:
>>  		err = fastrpc_get_dsp_info(fl, argp);
>>  		break;
>> @@ -2465,6 +2589,7 @@ static int fastrpc_rpmsg_callback(struct rpmsg_device *rpdev, void *data,
>>  
>>  	ctx->retval = rsp->retval;
>>  	complete(&ctx->work);
>> +	ctx->is_work_done = true;
>>  
>>  	/*
>>  	 * The DMA buffer associated with the context cannot be freed in
>> diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
>> index c6e2925f47e6..3207c42fb318 100644
>> --- a/include/uapi/misc/fastrpc.h
>> +++ b/include/uapi/misc/fastrpc.h
>> @@ -16,6 +16,7 @@
>>  #define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)
>>  #define FASTRPC_IOCTL_MEM_MAP		_IOWR('R', 10, struct fastrpc_mem_map)
>>  #define FASTRPC_IOCTL_MEM_UNMAP		_IOWR('R', 11, struct fastrpc_mem_unmap)
>> +#define FASTRPC_IOCTL_SET_OPTION	_IOWR('R', 12, struct fastrpc_ioctl_set_option)
>>  #define FASTRPC_IOCTL_GET_DSP_INFO	_IOWR('R', 13, struct fastrpc_ioctl_capability)
>>  
>>  /**
>> @@ -66,6 +67,8 @@ enum fastrpc_proc_attr {
>>  
>>  /* Fastrpc attribute for memory protection of buffers */
>>  #define FASTRPC_ATTR_SECUREMAP	(1)
>> +/* Set option request ID to enable poll mode */
>> +#define FASTRPC_POLL_MODE	(1)
> Is it related to FASTRPC_ATTR_SECUREMAP? Why is it a part of the same
> visual block?
I'll create a separation here.
>
>>  
>>  struct fastrpc_invoke_args {
>>  	__u64 ptr;
>> @@ -133,6 +136,12 @@ struct fastrpc_mem_unmap {
>>  	__s32 reserved[5];
>>  };
>>  
>> +struct fastrpc_ioctl_set_option {
>> +	__u32 req;	/* request id */
>> +	__u32 value;	/* value */
>> +	__s32 reserved[6];
> What are you reserving it for?
In case there are any more options that we want to control from here.
As it's more of a generic set_option request.
>
>> +};
>> +
>>  struct fastrpc_ioctl_capability {
>>  	__u32 unused; /* deprecated, ignored by the kernel */
>>  	__u32 attribute_id;
>> -- 
>> 2.34.1
>>