On 2023-11-05 18:44, Mina Almasry wrote:
> Add a netdev_dmabuf_binding struct which represents the
> dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to
> rx queues on the netdevice. On the binding, the dma_buf_attach
> & dma_buf_map_attachment will occur. The entries in the sg_t
On 2023-11-07 14:55, David Ahern wrote:
> On 11/7/23 3:10 PM, Mina Almasry wrote:
>> On Mon, Nov 6, 2023 at 3:44 PM David Ahern wrote:
>>>
>>> On 11/5/23 7:44 PM, Mina Almasry wrote:
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index eeeda849115c..1c351c138a5b 10064
On 2023-11-07 15:03, Mina Almasry wrote:
> On Tue, Nov 7, 2023 at 2:55 PM David Ahern wrote:
>>
>> On 11/7/23 3:10 PM, Mina Almasry wrote:
>>> On Mon, Nov 6, 2023 at 3:44 PM David Ahern wrote:
On 11/5/23 7:44 PM, Mina Almasry wrote:
> diff --git a/include/linux/netdevice.h b/include
On 2024-03-04 18:01, Mina Almasry wrote:
> +struct memory_provider_ops {
> + int (*init)(struct page_pool *pool);
> + void (*destroy)(struct page_pool *pool);
> + struct page *(*alloc_pages)(struct page_pool *pool, gfp_t gfp);
> + bool (*release_page)(struct page_pool *pool, struct
On 2024-03-04 18:01, Mina Almasry wrote:
> + if (pool->p.queue)
> + binding = READ_ONCE(pool->p.queue->binding);
> +
> + if (binding) {
> + pool->mp_ops = &dmabuf_devmem_ops;
> + pool->mp_priv = binding;
> + }
This is specific to TCP devmem. For ZC R
On 2024-03-05 18:42, Mina Almasry wrote:
> On Tue, Mar 5, 2024 at 6:28 PM David Wei wrote:
>>
>> On 2024-03-04 18:01, Mina Almasry wrote:
>>> + if (pool->p.queue)
>>> + binding = READ_ONCE(pool->p.queue->binding);
>>> +
>
On 2024-03-04 18:01, Mina Almasry wrote:
> From: Jakub Kicinski
>
> The page providers which try to reuse the same pages will
> need to hold onto the ref, even if page gets released from
> the pool - as in releasing the page from the pp just transfers
> the "ownership" reference from pp to the pr
On 2024-03-04 18:01, Mina Almasry wrote:
> This API enables the net stack to reset the queues used for devmem.
>
> Signed-off-by: Mina Almasry
>
> ---
> include/linux/netdevice.h | 24
> 1 file changed, 24 insertions(+)
>
> diff --git a/include/linux/netdevice.h b/incl
On 2024-03-17 19:02, Christoph Hellwig wrote:
> On Mon, Mar 04, 2024 at 06:01:37PM -0800, Mina Almasry wrote:
>> From: Jakub Kicinski
>>
>> The page providers which try to reuse the same pages will
>> need to hold onto the ref, even if page gets released from
>> the pool - as in releasing the page
On 2024-04-01 18:05, Jakub Kicinski wrote:
> Add glue code for accessing the YNL library which lives under
> tools/net and YAML spec files from under Documentation/.
> Automatically figure out if tests are run in tree or not.
> Since we'll want to use this library both from net and
> drivers/net te
On 2024-04-01 18:05, Jakub Kicinski wrote:
> Add a trivial test using YNL.
>
> $ ./tools/testing/selftests/net/nl_netdev.py
> KTAP version 1
> 1..2
> ok 1 nl_netdev.empty_check
> ok 2 nl_netdev.lo_check
>
> Instantiate the family once, it takes longer than the test itself.
>
> Signed-o
On 2024-04-01 18:05, Jakub Kicinski wrote:
> Real devices should implement qstats. Devices which support
> pause or FEC configuration should also report the relevant stats.
>
> nsim was missing FEC stats completely, some of the qstats
> and pause stats required toggling a debugfs knob.
>
> Note t
On 2024-04-01 18:05, Jakub Kicinski wrote:
> Add drivers/net as a target for mixed-use tests.
> The setup is expected to work similarly to the forwarding tests.
> Since we only need one interface (unlike forwarding tests)
> read the target device name from NETIF. If not present we'll
> try to run t
On 2024-04-01 18:05, Jakub Kicinski wrote:
> Add a very simple test to make sure drivers report expected
> stats. Drivers which implement FEC or pause configuration
> should report relevant stats. Qstats must be reported,
> at least packet and byte counts, and they must match
> total device stats.
On 2024-04-02 10:31, Jakub Kicinski wrote:
> On Tue, 2 Apr 2024 18:37:44 +0200 Petr Machata wrote:
>> Yeah, this would be usually done through context managers, as I mention
>> in the other e-mail. But then cfg would be lexically scoped, which IMHO
>> is a good thing, but then it needs to be passed
On 2024-06-07 17:27, David Ahern wrote:
> I also do not understand why the ifq cache and overloading xdp functions
> have stuck around; I always thought both were added by Jonathan to
> simplify kernel ports during early POC days.
Setting up an Rx queue for ZC w/ a different pp will be done proper
On 2024-06-07 17:52, Jason Gunthorpe wrote:
> IMHO it seems to compose poorly if you can only use the io_uring
> lifecycle model with io_uring registered memory, and not with DMABUF
> memory registered through Mina's mechanism.
By this, do you mean io_uring must be exclusively used to use this
fea
On 2024-04-02 5:20 pm, Mina Almasry wrote:
> Add a netdev_dmabuf_binding struct which represents the
> dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to
> rx queues on the netdevice. On the binding, the dma_buf_attach
> & dma_buf_map_attachment will occur. The entries in the sg
On 2024-04-02 5:20 pm, Mina Almasry wrote:
> @@ -69,20 +106,26 @@ net_iov_binding(const struct net_iov *niov)
> */
> typedef unsigned long __bitwise netmem_ref;
>
> +static inline bool netmem_is_net_iov(const netmem_ref netmem)
> +{
> +#if defined(CONFIG_PAGE_POOL) && defined(CONFIG_DMA_SHARED
On 2024-05-01 00:55, Christoph Hellwig wrote:
> On Fri, Apr 26, 2024 at 05:17:52PM -0700, David Wei wrote:
>> On 2024-04-02 5:20 pm, Mina Almasry wrote:
>>> @@ -69,20 +106,26 @@ net_iov_binding(const struct net_iov *niov)
>>> */
>>> typedef unsigned long __b
On 2024-05-10 16:21, Mina Almasry wrote:
> +/* This returns the absolute dma_addr_t calculated from
> + * net_iov_owner(niov)->owner->base_dma_addr, not the page_pool-owned
> + * niov->dma_addr.
> + *
> + * The absolute dma_addr_t is a dma_addr_t that is always uncompressed.
> + *
> + * The page_po
On 2024-05-10 16:21, Mina Almasry wrote:
> +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
> +{
> + struct netdev_rx_queue *rxq;
> + unsigned long xa_idx;
> + unsigned int rxq_idx;
> +
> + if (!binding)
> + return;
> +
> + if (binding->list.
On 2024-05-10 16:21, Mina Almasry wrote:
> -/* Stub */
> int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
> {
> - return 0;
> + struct nlattr *tb[ARRAY_SIZE(netdev_queue_dmabuf_nl_policy)];
> + struct net_devmem_dmabuf_binding *out_binding;
> + struct list_h
On 2024-05-10 16:21, Mina Almasry wrote:
> +/* On error, returns the -errno. On success, returns number of bytes sent to
> the
> + * user. May not consume all of @remaining_len.
> + */
> +static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
> + unsign
On 2024-05-30 13:16, Mina Almasry wrote:
[...]
> +err_start_queue:
> + /* Restarting the queue with old_mem should be successful as we haven't
> + * changed any of the queue configuration, and there is not much we can
> + * do to recover from a failure here.
> + *
> + * WARN
On 5/5/25 10:47, Jakub Kicinski wrote:
On Fri, 2 May 2025 21:54:11 -0700 David Wei wrote:
def _test_v4(cfg) -> None:
-cfg.require_ipver("4")
+if not cfg.addr_v["4"]:
+return
What if cfg.remote_addr_v['4'] doesn't exist?
Not sure if i
On 5/5/25 11:12, David Wei wrote:
On 5/5/25 10:47, Jakub Kicinski wrote:
On Fri, 2 May 2025 21:54:11 -0700 David Wei wrote:
def _test_v4(cfg) -> None:
- cfg.require_ipver("4")
+ if not cfg.addr_v["4"]:
+ return
What if cfg.remote_addr_v['4']
On 5/5/25 10:49, Jakub Kicinski wrote:
On Fri, 2 May 2025 22:02:43 -0700 David Wei wrote:
-def test_default(cfg, netnl) -> None:
+def test_default_v4(cfg, netnl) -> None:
+cfg.require_ipver("4")
With this patch, is the previous patch and this hunk still needed? I
think yo
loaded XDP
Totals: pass:0 fail:0 xfail:0 xpass:0 skip:6 error:0
Fixes: 75cc19c8ff89 ("selftests: drv-net: add xdp cases for ping.py")
Signed-off-by: Mohsin Bashir
Unrelated to this patch, but there is an ip() helper already. Can it be
used instead of cmd() with shell=True?
Reviewed-by: David Wei
On 5/2/25 18:35, Mohsin Bashir wrote:
On a system with either of the ipv4 or ipv6 information missing, tests
are currently skipped. Ideally, the test should run as long as at least
one address family is present. This patch make test run whenever
possible.
Before:
./drivers/net/ping.py
TAP versio
On 5/2/25 18:35, Mohsin Bashir wrote:
Currently, the test result does not differentiate between the cases when
either one of the address families are configured or if both the address
families are configured. Ideally, the result should report if a
particular case was skipped.
./drivers/net/ping.
doesn't have any way of excluding broken tests, remove these
for now to stop the random pollution of results due to broken env.
We can always add them back once / if fixed.
Signed-off-by: Jakub Kicinski
Reviewed-by: David Wei
On 5/8/25 14:40, Jakub Kicinski wrote:
The ping test flips checksum offload on and off.
Make sure the original value is restored if test fails.
Signed-off-by: Jakub Kicinski
---
CC: sh...@kernel.org
CC: linux-kselftest@vger.kernel.org
---
tools/testing/selftests/drivers/net/ping.py | 16 +
On 5/8/25 18:37, Jakub Kicinski wrote:
On Thu, 8 May 2025 14:59:12 -0700 David Wei wrote:
+def _schedule_checksum_reset(cfg, netnl) -> None:
+features = ethtool(f"-k {cfg.ifname}", json=True)
+setting = ""
+for side in ["tx", "rx"]:
+
34 matches
Mail list logo
