This series adds AF_XDP zero coppy support to am65-cpsw driver.
Tests were performed on AM62x-sk with xdpsock application [1].
A clear improvement is seen in 64 byte packets on Transmit (txonly)
and receive (rxdrop).
1500 byte test seems to be limited by line rate (1G link) so no
improvement seen there in packet rate. A test on higher speed link
(or PHY-less setup) might be worthwile.
There is some issue during l2fwd with 64 byte packets and benchmark
results show 0. This issue needs to be debugged further.
A 512 byte l2fwd test result has been added to compare instead.
AF_XDP performance using 64 byte packets in Kpps.
Benchmark: XDP-SKB XDP-Native XDP-Native(ZeroCopy)
rxdrop 322 491 845
txonly 390 394 723
l2fwd 205 257 0
AF_XDP performance using 512 byte packets in Kpps.
l2fwd 140 167 231
AF_XDP performance using 1500 byte packets in Kpps.
Benchmark: XDP-SKB XDP-Native XDP-Native(ZeroCopy)
rxdrop 82 82 82
txonly 82 82 82
l2fwd 82 82 82
[1]: https://github.com/xdp-project/bpf-examples/tree/master/AF_XDP-example
Signed-off-by: Roger Quadros <rogerq(a)kernel.org>
---
Changes in v2:
- Prevent crash on systems with 1 of 2 ports disabled in device tree. check
for valid ndev before registering/unregistering XDP RXQ.
Reported-by: Meghana Malladi <m-malladi(a)ti.com>
- Retain page pool on XDP program exchangae so we don't have to re-alloacate
memory.
- Fix clearing of irq_disabled flag in am65_cpsw_nuss_rx_poll().
- Link to v1: https://lore.kernel.org/r/20250520-am65-cpsw-xdp-zc-v1-0-45558024f566@kerne…
---
Roger Quadros (7):
net: ethernet: ti: am65-cpsw: fix BPF Program change on multi-port CPSW
net: ethernet: ti: am65-cpsw: Retain page_pool on XDP program exchange
net: ethernet: ti: am65-cpsw: add XSK pool helpers
net: ethernet: ti: am65-cpsw: Add AF_XDP zero copy for RX
net: ethernet: ti: am65-cpsw: Add AF_XDP zero copy for TX
net: ethernet: ti: am65-cpsw: enable zero copy in XDP features
net: ethernet: ti: am65-cpsw: Fix clearing of irq_disabled flag in rx_poll
drivers/net/ethernet/ti/Makefile | 2 +-
drivers/net/ethernet/ti/am65-cpsw-nuss.c | 583 ++++++++++++++++++++++++++-----
drivers/net/ethernet/ti/am65-cpsw-nuss.h | 37 +-
drivers/net/ethernet/ti/am65-cpsw-xdp.c | 155 ++++++++
4 files changed, 692 insertions(+), 85 deletions(-)
---
base-commit: a0c3aefb08cd81864b17c23c25b388dba90b9dad
change-id: 20250225-am65-cpsw-xdp-zc-2af9e4be1356
Best regards,
--
Roger Quadros <rogerq(a)kernel.org>
Add missing drm_gem_object_put() call when drm_gem_object_lookup()
successfully returns an object. This fixes a GEM object reference
leak that can prevent driver modules from unloading when using
prime buffers.
Fixes: 53096728b891 ("drm: Add DRM prime interface to reassign GEM handle")
Cc: <stable(a)vger.kernel.org> # v6.18+
Signed-off-by: Karol Wachowski <karol.wachowski(a)linux.intel.com>
---
Changes between v3 and v2:
- correctly add CC: tag this time
Changes between v1 and v2:
- move setting ret value under if branch as suggested in review
- add Cc: stable 6.18+
---
drivers/gpu/drm/drm_gem.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index ca1956608261..bcc08a6aebf8 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1010,8 +1010,10 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
if (!obj)
return -ENOENT;
- if (args->handle == args->new_handle)
- return 0;
+ if (args->handle == args->new_handle) {
+ ret = 0;
+ goto out;
+ }
mutex_lock(&file_priv->prime.lock);
@@ -1043,6 +1045,8 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
out_unlock:
mutex_unlock(&file_priv->prime.lock);
+out:
+ drm_gem_object_put(obj);
return ret;
}
--
2.43.0
If there is a large number (hundreds) of dmabufs allocated, the text
output generated from dmabuf_iter_seq_show can exceed common user buffer
sizes (e.g. PAGE_SIZE) necessitating multiple start/stop cycles to
iterate through all dmabufs. However the dmabuf iterator currently
returns NULL in dmabuf_iter_seq_start for all non-zero pos values, which
results in the truncation of the output before all dmabufs are handled.
After dma_buf_iter_begin / dma_buf_iter_next, the refcount of the buffer
is elevated so that the BPF iterator program can run without holding any
locks. When a stop occurs, instead of immediately dropping the reference
on the buffer, stash a pointer to the buffer in seq->priv until
either start is called or the iterator is released. This also enables
the resumption of iteration without first walking through the list of
dmabufs based on the pos value.
Fixes: 76ea95534995 ("bpf: Add dmabuf iterator")
Signed-off-by: T.J. Mercier <tjmercier(a)google.com>
---
kernel/bpf/dmabuf_iter.c | 56 +++++++++++++++++++++++++++++++++++-----
1 file changed, 49 insertions(+), 7 deletions(-)
diff --git a/kernel/bpf/dmabuf_iter.c b/kernel/bpf/dmabuf_iter.c
index 4dd7ef7c145c..cd500248abd9 100644
--- a/kernel/bpf/dmabuf_iter.c
+++ b/kernel/bpf/dmabuf_iter.c
@@ -6,10 +6,33 @@
#include <linux/kernel.h>
#include <linux/seq_file.h>
+struct dmabuf_iter_priv {
+ /*
+ * If this pointer is non-NULL, the buffer's refcount is elevated to
+ * prevent destruction between stop/start. If reading is not resumed and
+ * start is never called again, then dmabuf_iter_seq_fini drops the
+ * reference when the iterator is released.
+ */
+ struct dma_buf *dmabuf;
+};
+
static void *dmabuf_iter_seq_start(struct seq_file *seq, loff_t *pos)
{
- if (*pos)
- return NULL;
+ struct dmabuf_iter_priv *p = seq->private;
+
+ if (*pos) {
+ struct dma_buf *dmabuf = p->dmabuf;
+
+ if (!dmabuf)
+ return NULL;
+
+ /*
+ * Always resume from where we stopped, regardless of the value
+ * of pos.
+ */
+ p->dmabuf = NULL;
+ return dmabuf;
+ }
return dma_buf_iter_begin();
}
@@ -54,8 +77,11 @@ static void dmabuf_iter_seq_stop(struct seq_file *seq, void *v)
{
struct dma_buf *dmabuf = v;
- if (dmabuf)
- dma_buf_put(dmabuf);
+ if (dmabuf) {
+ struct dmabuf_iter_priv *p = seq->private;
+
+ p->dmabuf = dmabuf;
+ }
}
static const struct seq_operations dmabuf_iter_seq_ops = {
@@ -71,11 +97,27 @@ static void bpf_iter_dmabuf_show_fdinfo(const struct bpf_iter_aux_info *aux,
seq_puts(seq, "dmabuf iter\n");
}
+static int dmabuf_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux)
+{
+ struct dmabuf_iter_priv *p = (struct dmabuf_iter_priv *)priv;
+
+ p->dmabuf = NULL;
+ return 0;
+}
+
+static void dmabuf_iter_seq_fini(void *priv)
+{
+ struct dmabuf_iter_priv *p = (struct dmabuf_iter_priv *)priv;
+
+ if (p->dmabuf)
+ dma_buf_put(p->dmabuf);
+}
+
static const struct bpf_iter_seq_info dmabuf_iter_seq_info = {
.seq_ops = &dmabuf_iter_seq_ops,
- .init_seq_private = NULL,
- .fini_seq_private = NULL,
- .seq_priv_size = 0,
+ .init_seq_private = dmabuf_iter_seq_init,
+ .fini_seq_private = dmabuf_iter_seq_fini,
+ .seq_priv_size = sizeof(struct dmabuf_iter_priv),
};
static struct bpf_iter_reg bpf_dmabuf_reg_info = {
base-commit: 30f09200cc4aefbd8385b01e41bde2e4565a6f0e
--
2.52.0.177.g9f829587af-goog
