* [PATCH v2 1/3] rpmsg: virtio_rpmsg_bus: allow different size of tx and rx bufs
2026-04-29 16:10 [PATCH v2 0/3] Enhance RPMsg buffer management Tanmay Shah
@ 2026-04-29 16:10 ` Tanmay Shah
2026-04-29 16:10 ` [PATCH v2 2/3] rpmsg: virtio_rpmsg_bus: get buffer size from config space Tanmay Shah
2026-04-29 16:10 ` [PATCH v2 3/3] samples: rpmsg: add mtu size info Tanmay Shah
2 siblings, 0 replies; 4+ messages in thread
From: Tanmay Shah @ 2026-04-29 16:10 UTC (permalink / raw)
To: andersson, mathieu.poirier, arnaud.pouliquen
Cc: linux-kernel, linux-remoteproc, Tanmay Shah
Current design allocates memory for tx and rx buffers equally. The
throughput can be increased if the user is allowed to configure number
of tx and rx buffers as required. Hence, do not split number of tx & rx
buffers into half, but decide based on respective vring size.
Signed-off-by: Tanmay Shah <tanmay.shah@amd.com>
---
Test performed:
- Test this patch with existing firmware as it is, rpmsg working.
Changes in v2:
- Change author
- fix commit message with better explanation
- %s/sbuf/tx_buf
- %s/rbuf/rx_buf
- %s/num_rbuf/num_rx_buf/
- %s/num_sbuf/num_tx_buf/
drivers/rpmsg/virtio_rpmsg_bus.c | 68 ++++++++++++++++----------------
1 file changed, 34 insertions(+), 34 deletions(-)
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index 5ae15111fb4f..e59d8cf9b975 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -35,13 +35,14 @@
* @vdev: the virtio device
* @rvq: rx virtqueue
* @svq: tx virtqueue
- * @rbufs: kernel address of rx buffers
- * @sbufs: kernel address of tx buffers
- * @num_bufs: total number of buffers for rx and tx
- * @buf_size: size of one rx or tx buffer
+ * @rx_bufs: kernel address of rx buffers
+ * @tx_bufs: kernel address of tx buffers
+ * @num_rx_buf: total number of buffers for rx
+ * @num_tx_buf: total number of buffers for tx
+ * @buf_size: size of one rx or tx buffer
* @last_sbuf: index of last tx buffer used
* @bufs_dma: dma base addr of the buffers
- * @tx_lock: protects svq and sbufs, to allow concurrent senders.
+ * @tx_lock: protects svq and tx_bufs, to allow concurrent senders.
* sending a message might require waking up a dozing remote
* processor, which involves sleeping, hence the mutex.
* @endpoints: idr of local endpoints, allows fast retrieval
@@ -55,8 +56,9 @@
struct virtproc_info {
struct virtio_device *vdev;
struct virtqueue *rvq, *svq;
- void *rbufs, *sbufs;
- unsigned int num_bufs;
+ void *rx_bufs, *tx_bufs;
+ unsigned int num_rx_buf;
+ unsigned int num_tx_buf;
unsigned int buf_size;
int last_sbuf;
dma_addr_t bufs_dma;
@@ -110,7 +112,7 @@ struct virtio_rpmsg_channel {
/*
* We're allocating buffers of 512 bytes each for communications. The
* number of buffers will be computed from the number of buffers supported
- * by the vring, upto a maximum of 512 buffers (256 in each direction).
+ * by the vring, up to a maximum of 256 in each direction.
*
* Each buffer will have 16 bytes for the msg header and 496 bytes for
* the payload.
@@ -125,7 +127,7 @@ struct virtio_rpmsg_channel {
* can change this without changing anything in the firmware of the remote
* processor.
*/
-#define MAX_RPMSG_NUM_BUFS (512)
+#define MAX_RPMSG_NUM_BUFS (256)
#define MAX_RPMSG_BUF_SIZE (512)
/*
@@ -440,12 +442,9 @@ static void *get_a_tx_buf(struct virtproc_info *vrp)
mutex_lock(&vrp->tx_lock);
- /*
- * either pick the next unused tx buffer
- * (half of our buffers are used for sending messages)
- */
- if (vrp->last_sbuf < vrp->num_bufs / 2)
- ret = vrp->sbufs + vrp->buf_size * vrp->last_sbuf++;
+ /* either pick the next unused tx buffer */
+ if (vrp->last_sbuf < vrp->num_tx_buf)
+ ret = vrp->tx_bufs + vrp->buf_size * vrp->last_sbuf++;
/* or recycle a used one */
else
ret = virtqueue_get_buf(vrp->svq, &len);
@@ -631,11 +630,10 @@ static __poll_t virtio_rpmsg_poll(struct rpmsg_endpoint *ept, struct file *filp,
/*
* check for a free buffer, either:
- * - we haven't used all of the available transmit buffers (half of the
- * allocated buffers are used for transmit, hence num_bufs / 2), or,
+ * - we haven't used all of the available transmit buffers or,
* - we ask the virtqueue if there's a buffer available
*/
- if (vrp->last_sbuf < vrp->num_bufs / 2 ||
+ if (vrp->last_sbuf < vrp->num_tx_buf ||
!virtqueue_enable_cb(vrp->svq))
mask |= EPOLLOUT;
@@ -846,19 +844,20 @@ static int rpmsg_probe(struct virtio_device *vdev)
vrp->rvq = vqs[0];
vrp->svq = vqs[1];
- /* we expect symmetric tx/rx vrings */
- WARN_ON(virtqueue_get_vring_size(vrp->rvq) !=
- virtqueue_get_vring_size(vrp->svq));
-
/* we need less buffers if vrings are small */
- if (virtqueue_get_vring_size(vrp->rvq) < MAX_RPMSG_NUM_BUFS / 2)
- vrp->num_bufs = virtqueue_get_vring_size(vrp->rvq) * 2;
+ if (virtqueue_get_vring_size(vrp->rvq) < MAX_RPMSG_NUM_BUFS)
+ vrp->num_rx_buf = virtqueue_get_vring_size(vrp->rvq);
+ else
+ vrp->num_rx_buf = MAX_RPMSG_NUM_BUFS;
+
+ if (virtqueue_get_vring_size(vrp->svq) < MAX_RPMSG_NUM_BUFS)
+ vrp->num_tx_buf = virtqueue_get_vring_size(vrp->svq);
else
- vrp->num_bufs = MAX_RPMSG_NUM_BUFS;
+ vrp->num_tx_buf = MAX_RPMSG_NUM_BUFS;
vrp->buf_size = MAX_RPMSG_BUF_SIZE;
- total_buf_space = vrp->num_bufs * vrp->buf_size;
+ total_buf_space = (vrp->num_rx_buf + vrp->num_tx_buf) * vrp->buf_size;
/* allocate coherent memory for the buffers */
bufs_va = dma_alloc_coherent(vdev->dev.parent,
@@ -872,16 +871,16 @@ static int rpmsg_probe(struct virtio_device *vdev)
dev_dbg(&vdev->dev, "buffers: va %p, dma %pad\n",
bufs_va, &vrp->bufs_dma);
- /* half of the buffers is dedicated for RX */
- vrp->rbufs = bufs_va;
+ /* first part of the buffers is dedicated for RX */
+ vrp->rx_bufs = bufs_va;
- /* and half is dedicated for TX */
- vrp->sbufs = bufs_va + total_buf_space / 2;
+ /* and second part is dedicated for TX */
+ vrp->tx_bufs = bufs_va + vrp->num_rx_buf * vrp->buf_size;
/* set up the receive buffers */
- for (i = 0; i < vrp->num_bufs / 2; i++) {
+ for (i = 0; i < vrp->num_rx_buf; i++) {
struct scatterlist sg;
- void *cpu_addr = vrp->rbufs + i * vrp->buf_size;
+ void *cpu_addr = vrp->rx_bufs + i * vrp->buf_size;
rpmsg_sg_init(&sg, cpu_addr, vrp->buf_size);
@@ -966,7 +965,8 @@ static int rpmsg_remove_device(struct device *dev, void *data)
static void rpmsg_remove(struct virtio_device *vdev)
{
struct virtproc_info *vrp = vdev->priv;
- size_t total_buf_space = vrp->num_bufs * vrp->buf_size;
+ unsigned int num_bufs = vrp->num_rx_buf + vrp->num_tx_buf;
+ size_t total_buf_space = num_bufs * vrp->buf_size;
int ret;
virtio_reset_device(vdev);
@@ -980,7 +980,7 @@ static void rpmsg_remove(struct virtio_device *vdev)
vdev->config->del_vqs(vrp->vdev);
dma_free_coherent(vdev->dev.parent, total_buf_space,
- vrp->rbufs, vrp->bufs_dma);
+ vrp->rx_bufs, vrp->bufs_dma);
kfree(vrp);
}
--
2.34.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH v2 2/3] rpmsg: virtio_rpmsg_bus: get buffer size from config space
2026-04-29 16:10 [PATCH v2 0/3] Enhance RPMsg buffer management Tanmay Shah
2026-04-29 16:10 ` [PATCH v2 1/3] rpmsg: virtio_rpmsg_bus: allow different size of tx and rx bufs Tanmay Shah
@ 2026-04-29 16:10 ` Tanmay Shah
2026-04-29 16:10 ` [PATCH v2 3/3] samples: rpmsg: add mtu size info Tanmay Shah
2 siblings, 0 replies; 4+ messages in thread
From: Tanmay Shah @ 2026-04-29 16:10 UTC (permalink / raw)
To: andersson, mathieu.poirier, arnaud.pouliquen
Cc: linux-kernel, linux-remoteproc, Tanmay Shah
512 bytes isn't always suitable for all case, let firmware
maker decide the best value from resource table.
enable by VIRTIO_RPMSG_F_BUFSZ feature bit.
Signed-off-by: Tanmay Shah <tanmay.shah@amd.com>
---
Test done:
- Verify this patch works with the existing firmware
- Verify this patch works with the firmware that configures
differt tx & rx buf size
Changes in v2:
- %s/sbuf_size/tx_buf_size/
- %s/rbuf_size/rx_buf_size/
- fix typo
- do not use ALIGN on buf size, rely on allocator
- make err msg more explicit, %s/vdev config:/bad vdev config/
- fix license and add AMD copyrights in the header virtio_rpmsg.h
- Assign bit 1 to VIRTIO_RPMSG_F_BUFSZ feature
- use __virtio32 over __u32
- add version field to virtio rpmsg config structure
- move linux/virtio_rpmsg.h to linux/rpmsg/virtio_rpmsg.h
drivers/rpmsg/virtio_rpmsg_bus.c | 70 ++++++++++++++++++++++--------
include/linux/rpmsg/virtio_rpmsg.h | 27 ++++++++++++
2 files changed, 79 insertions(+), 18 deletions(-)
create mode 100644 include/linux/rpmsg/virtio_rpmsg.h
diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c
index e59d8cf9b975..8116d94413cc 100644
--- a/drivers/rpmsg/virtio_rpmsg_bus.c
+++ b/drivers/rpmsg/virtio_rpmsg_bus.c
@@ -20,6 +20,7 @@
#include <linux/rpmsg.h>
#include <linux/rpmsg/byteorder.h>
#include <linux/rpmsg/ns.h>
+#include <linux/rpmsg/virtio_rpmsg.h>
#include <linux/scatterlist.h>
#include <linux/slab.h>
#include <linux/sched.h>
@@ -39,7 +40,8 @@
* @tx_bufs: kernel address of tx buffers
* @num_rx_buf: total number of buffers for rx
* @num_tx_buf: total number of buffers for tx
- * @buf_size: size of one rx or tx buffer
+ * @rx_buf_size: size of one rx buffer
+ * @tx_buf_size: size of one tx buffer
* @last_sbuf: index of last tx buffer used
* @bufs_dma: dma base addr of the buffers
* @tx_lock: protects svq and tx_bufs, to allow concurrent senders.
@@ -59,7 +61,8 @@ struct virtproc_info {
void *rx_bufs, *tx_bufs;
unsigned int num_rx_buf;
unsigned int num_tx_buf;
- unsigned int buf_size;
+ unsigned int rx_buf_size;
+ unsigned int tx_buf_size;
int last_sbuf;
dma_addr_t bufs_dma;
struct mutex tx_lock;
@@ -68,9 +71,6 @@ struct virtproc_info {
wait_queue_head_t sendq;
};
-/* The feature bitmap for virtio rpmsg */
-#define VIRTIO_RPMSG_F_NS 0 /* RP supports name service notifications */
-
/**
* struct rpmsg_hdr - common header for all rpmsg messages
* @src: source address
@@ -128,7 +128,7 @@ struct virtio_rpmsg_channel {
* processor.
*/
#define MAX_RPMSG_NUM_BUFS (256)
-#define MAX_RPMSG_BUF_SIZE (512)
+#define DEFAULT_RPMSG_BUF_SIZE (512)
/*
* Local addresses are dynamically allocated on-demand.
@@ -444,7 +444,7 @@ static void *get_a_tx_buf(struct virtproc_info *vrp)
/* either pick the next unused tx buffer */
if (vrp->last_sbuf < vrp->num_tx_buf)
- ret = vrp->tx_bufs + vrp->buf_size * vrp->last_sbuf++;
+ ret = vrp->tx_bufs + vrp->tx_buf_size * vrp->last_sbuf++;
/* or recycle a used one */
else
ret = virtqueue_get_buf(vrp->svq, &len);
@@ -514,7 +514,7 @@ static int rpmsg_send_offchannel_raw(struct rpmsg_device *rpdev,
* messaging), or to improve the buffer allocator, to support
* variable-length buffer sizes.
*/
- if (len > vrp->buf_size - sizeof(struct rpmsg_hdr)) {
+ if (len > vrp->tx_buf_size - sizeof(struct rpmsg_hdr)) {
dev_err(dev, "message is too big (%d)\n", len);
return -EMSGSIZE;
}
@@ -647,7 +647,7 @@ static ssize_t virtio_rpmsg_get_mtu(struct rpmsg_endpoint *ept)
struct rpmsg_device *rpdev = ept->rpdev;
struct virtio_rpmsg_channel *vch = to_virtio_rpmsg_channel(rpdev);
- return vch->vrp->buf_size - sizeof(struct rpmsg_hdr);
+ return vch->vrp->tx_buf_size - sizeof(struct rpmsg_hdr);
}
static int rpmsg_recv_single(struct virtproc_info *vrp, struct device *dev,
@@ -673,7 +673,7 @@ static int rpmsg_recv_single(struct virtproc_info *vrp, struct device *dev,
* We currently use fixed-sized buffers, so trivially sanitize
* the reported payload length.
*/
- if (len > vrp->buf_size ||
+ if (len > vrp->rx_buf_size ||
msg_len > (len - sizeof(struct rpmsg_hdr))) {
dev_warn(dev, "inbound msg too big: (%d, %d)\n", len, msg_len);
return -EINVAL;
@@ -706,7 +706,7 @@ static int rpmsg_recv_single(struct virtproc_info *vrp, struct device *dev,
dev_warn_ratelimited(dev, "msg received with no recipient\n");
/* publish the real size of the buffer */
- rpmsg_sg_init(&sg, msg, vrp->buf_size);
+ rpmsg_sg_init(&sg, msg, vrp->rx_buf_size);
/* add the buffer back to the remote processor's virtqueue */
err = virtqueue_add_inbuf(vrp->rvq, &sg, 1, msg, GFP_KERNEL);
@@ -824,6 +824,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
int err = 0, i;
size_t total_buf_space;
bool notify;
+ u16 version;
vrp = kzalloc_obj(*vrp);
if (!vrp)
@@ -855,9 +856,41 @@ static int rpmsg_probe(struct virtio_device *vdev)
else
vrp->num_tx_buf = MAX_RPMSG_NUM_BUFS;
- vrp->buf_size = MAX_RPMSG_BUF_SIZE;
+ /*
+ * If VIRTIO_RPMSG_F_BUFSZ feature is supported, then configure buf
+ * size from virtio device config space from the resource table.
+ * If the feature is not supported, then assign default buf size.
+ */
+ if (virtio_has_feature(vdev, VIRTIO_RPMSG_F_BUFSZ)) {
+ /* note: virtio_rpmsg_config is defined from remote view */
+ version = 0;
+ virtio_cread(vdev, struct virtio_rpmsg_config,
+ version, &version);
+ virtio_cread(vdev, struct virtio_rpmsg_config,
+ txbuf_size, &vrp->rx_buf_size);
+ virtio_cread(vdev, struct virtio_rpmsg_config,
+ rxbuf_size, &vrp->tx_buf_size);
+
+ /* The buffers must hold at least the rpmsg header */
+ if (vrp->rx_buf_size < sizeof(struct rpmsg_hdr) ||
+ vrp->tx_buf_size < sizeof(struct rpmsg_hdr)) {
+ dev_err(&vdev->dev,
+ "bad vdev config: rx buf sz = %d, tx buf sz = %d\n",
+ vrp->rx_buf_size, vrp->tx_buf_size);
+ err = -EINVAL;
+ goto vqs_del;
+ }
+
+ dev_dbg(&vdev->dev,
+ "vdev config: version=%d, rx buf sz = 0x%x, tx buf sz = 0x%x\n",
+ version, vrp->rx_buf_size, vrp->tx_buf_size);
+ } else {
+ vrp->rx_buf_size = DEFAULT_RPMSG_BUF_SIZE;
+ vrp->tx_buf_size = DEFAULT_RPMSG_BUF_SIZE;
+ }
- total_buf_space = (vrp->num_rx_buf + vrp->num_tx_buf) * vrp->buf_size;
+ total_buf_space = (vrp->num_rx_buf * vrp->rx_buf_size) +
+ (vrp->num_tx_buf * vrp->tx_buf_size);
/* allocate coherent memory for the buffers */
bufs_va = dma_alloc_coherent(vdev->dev.parent,
@@ -875,14 +908,14 @@ static int rpmsg_probe(struct virtio_device *vdev)
vrp->rx_bufs = bufs_va;
/* and second part is dedicated for TX */
- vrp->tx_bufs = bufs_va + vrp->num_rx_buf * vrp->buf_size;
+ vrp->tx_bufs = bufs_va + (vrp->num_rx_buf * vrp->rx_buf_size);
/* set up the receive buffers */
for (i = 0; i < vrp->num_rx_buf; i++) {
struct scatterlist sg;
- void *cpu_addr = vrp->rx_bufs + i * vrp->buf_size;
+ void *cpu_addr = vrp->rx_bufs + i * vrp->rx_buf_size;
- rpmsg_sg_init(&sg, cpu_addr, vrp->buf_size);
+ rpmsg_sg_init(&sg, cpu_addr, vrp->rx_buf_size);
err = virtqueue_add_inbuf(vrp->rvq, &sg, 1, cpu_addr,
GFP_KERNEL);
@@ -965,8 +998,8 @@ static int rpmsg_remove_device(struct device *dev, void *data)
static void rpmsg_remove(struct virtio_device *vdev)
{
struct virtproc_info *vrp = vdev->priv;
- unsigned int num_bufs = vrp->num_rx_buf + vrp->num_tx_buf;
- size_t total_buf_space = num_bufs * vrp->buf_size;
+ size_t total_buf_space = (vrp->num_rx_buf * vrp->rx_buf_size) +
+ (vrp->num_tx_buf * vrp->tx_buf_size);
int ret;
virtio_reset_device(vdev);
@@ -992,6 +1025,7 @@ static struct virtio_device_id id_table[] = {
static unsigned int features[] = {
VIRTIO_RPMSG_F_NS,
+ VIRTIO_RPMSG_F_BUFSZ,
};
static struct virtio_driver virtio_ipc_driver = {
diff --git a/include/linux/rpmsg/virtio_rpmsg.h b/include/linux/rpmsg/virtio_rpmsg.h
new file mode 100644
index 000000000000..285918be68b9
--- /dev/null
+++ b/include/linux/rpmsg/virtio_rpmsg.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) Pinecone Inc. 2019
+ * Copyright (C) Xiang Xiao <xiaoxiang@pinecone.net>
+ * Copyright (C) Advanced Micro Devices, Inc.
+ */
+
+#ifndef _LINUX_VIRTIO_RPMSG_H
+#define _LINUX_VIRTIO_RPMSG_H
+
+#include <linux/types.h>
+#include <linux/virtio_types.h>
+
+/* The feature bitmap for virtio rpmsg */
+#define VIRTIO_RPMSG_F_NS 0 /* RP supports name service notifications */
+#define VIRTIO_RPMSG_F_BUFSZ 1 /* RP get buffer size from config space */
+
+struct virtio_rpmsg_config {
+ __virtio16 version;
+ /* The tx/rx individual buffer size(if VIRTIO_RPMSG_F_BUFSZ) */
+ __virtio32 txbuf_size;
+ __virtio32 rxbuf_size;
+ __virtio32 reserved[14]; /* Reserve for the future use */
+ /* Put the customize config here */
+} __packed;
+
+#endif /* _LINUX_VIRTIO_RPMSG_H */
--
2.34.1
^ permalink raw reply related [flat|nested] 4+ messages in thread