From nobody Sun Feb 8 15:25:06 2026 Received: from mail-yw1-f170.google.com (mail-yw1-f170.google.com [209.85.128.170]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B097E1C1F02 for ; Sat, 10 Jan 2026 02:19:01 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.170 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011543; cv=none; b=MOdSu0IOz7crODEH6jdcw26RZVXCWYJvlBhVMPaj7i32iXZa33Dm16lZDN+7uSzZEGnoR24lq3bV4Hw61g8e7vav+W3CH1d0X89xhohlOj2Jm2FOO1LTspmg8bDrQegZNDKXXJwwfLe0tbyzFVNuTngrc7Mgr7ndyjXGAUGmWG4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011543; c=relaxed/simple; bh=xiO09bVBGC8/K7L0bw2p16Wp9QD28tXsWfMmjzD/Ua4=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=jfHpLWxmX1Un2qgnzmlgs6bvd/pVag5j4ahjm1xWd42bYdKHbrWcDuWbmCggjnSJJgcy02sEl6fpzrSpR+WkNK7DXIVpI7cWZay+OLmM43AW4HVtJTfLWUm5z8drFremCVsIdQ+sSGZQm+IdJzE47b7ON+YtQ7L/MPSUQWZANP4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=aP3KPlyY; arc=none smtp.client-ip=209.85.128.170 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="aP3KPlyY" Received: by mail-yw1-f170.google.com with SMTP id 00721157ae682-7926d5dbdf7so5392607b3.2 for ; Fri, 09 Jan 2026 18:19:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1768011541; x=1768616341; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=07Oq7s3cDlA8pW6W82CkM0efPRUiBJHxCtezHHHyhNs=; b=aP3KPlyY6zoY7wXyxuDu2CZQUwNdvvHc35TJGW5jxMrfnSDqkZXyLPcBG/23GZsOku +SzTOovsD4ZTn547tqu2cDRpKnMKEbIDBs9G+q1kBW30Ou0bCwPCBKToUtTe9K3DDMMC Ohuzeq6Bh6zK3AFt4y965A0yZlfbmg7XvB/lzx30Qv2e8kOJRUB/6V2PmCPEWYisTc9a ZIaCQRPoXgxxFE1wzWPANO6w1Yctt4oVjzagCSmI5wSSHgVhs/uT+h2mXpScaiKeOspL lIbXHhSREReuTlNknT2UKD+aui96R3GSDLqTRd51j+I4REL5tMJhMYS7npzTAvWIZJtj aSYg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1768011541; x=1768616341; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-gg:x-gm-message-state:from:to :cc:subject:date:message-id:reply-to; bh=07Oq7s3cDlA8pW6W82CkM0efPRUiBJHxCtezHHHyhNs=; b=IbQ1owhakRQ4Oy2wGkiM4Xxt8BWF8XU/mAHVLYxwl7NDXlckgs4FeWznIxk3VzsGwm p0uidSchy2igLXeu8ACfZanuKqw8Ay9nTpEDflnrnKAWXjziR64hyqsGXBibAc/ZHX+W UkEGAKRAx28odc1XvCIrUXDSOMch1R2AOTHxgAZpDCa0RGDOwGUhF/zRj0hiDGBRNW9p 0j9fx2m+obv1Ja+Yz5nwI9DcdgYT6bMjSHRgYEZygumWf5Q8zp1NbOonZWco1VCaMxSz kJAPAbivfWnMevNXmkvP0bT5OkZptI6mYZnpnHgV9h67GaFW99pnI3WoMjvoqA/uVl4h Bo5Q== X-Forwarded-Encrypted: i=1; AJvYcCUQgxBvecZJU2lerxzDkI6FvF0yImHguDuL3jSY4s0ptrV6+T/roLl6zxZqDehm4ELodGNXqHer1E5dbKE=@vger.kernel.org X-Gm-Message-State: AOJu0Yy+/mP2M5EmMyNo8jrkEU1lM60kcuHHuH5Ej5uZKpS7enWxUeME GPVlgavcXuIvqdzE6KxEFdzJq8QUceXnyDT3jCeF7Be5FaxvCufcNJ4M X-Gm-Gg: AY/fxX7TLqpsR1wJblm4d0fAyPIgwwZnrrS7ACD1MRPKeFb1DIHR8SjAbyo66fRehuX 58E66LKTCYLvUkh6qGRuBV9NAuMyfK+Gd3/ryZaHLoBnhsWRsa6t2wkaBNx0cCbpgpzwAfE8hta eGDEJX0R0VJlQ6O1DlnAe8QK4flWzC8T8UYgt3b2kpjUPY/CCpcoDkqL2YLFj3TSAc5fC/4M8E9 /TeuJ2OAUlefJXcI8rIFf4lPtQzu51QHeqv37xEV6hh0nqHbS5WzY2/ein3WMWO3QQe59nKx+x9 2XBqK3c0cKmTJGZkvTNjam6pop4Ee48wyHRcpbaaXYiM/fWrJfBGQ1vTXuDN6LwOhl7qQuDqBbh M5eNgI9s4f96V9DfdSz+5+EN8W6dkXs4/iXPgaZ1s30fFYtgDgQ1ah8gVyD1jNdcudAMQoqtx4o 4R90I7xbMk X-Google-Smtp-Source: AGHT+IGfZcTckoYQm0PZ8TzEz8YmdS7X/s2FUArN0KlH5v6g1oChNJ7JGYZdwCItZFhkXd+klVUdmg== X-Received: by 2002:a05:690c:6704:b0:78c:5bb4:1d27 with SMTP id 00721157ae682-790b568d427mr107537007b3.38.1768011540680; Fri, 09 Jan 2026 18:19:00 -0800 (PST) Received: from localhost ([2a03:2880:25ff:a::]) by smtp.gmail.com with ESMTPSA id 00721157ae682-790aa6713e5sm46527227b3.29.2026.01.09.18.19.00 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 09 Jan 2026 18:19:00 -0800 (PST) From: Bobby Eshleman Date: Fri, 09 Jan 2026 18:18:15 -0800 Subject: [PATCH net-next v9 1/5] net: devmem: rename tx_vec to vec in dmabuf binding Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-1-8042930d00d7@meta.com> References: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> In-Reply-To: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> To: "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Kuniyuki Iwashima , Willem de Bruijn , Neal Cardwell , David Ahern , Mina Almasry , Arnd Bergmann , Jonathan Corbet , Andrew Lunn , Shuah Khan , Donald Hunter Cc: Stanislav Fomichev , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, asml.silence@gmail.com, matttbe@kernel.org, skhawaja@google.com, Bobby Eshleman X-Mailer: b4 0.14.3 From: Bobby Eshleman Rename the 'tx_vec' field in struct net_devmem_dmabuf_binding to 'vec'. This field holds pointers to net_iov structures. The rename prepares for reusing 'vec' for both TX and RX directions. No functional change intended. Reviewed-by: Mina Almasry Signed-off-by: Bobby Eshleman --- net/core/devmem.c | 22 +++++++++++----------- net/core/devmem.h | 2 +- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/net/core/devmem.c b/net/core/devmem.c index ec4217d6c0b4..05a9a9e7abb9 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -75,7 +75,7 @@ void __net_devmem_dmabuf_binding_free(struct work_struct = *wq) dma_buf_detach(binding->dmabuf, binding->attachment); dma_buf_put(binding->dmabuf); xa_destroy(&binding->bound_rxqs); - kvfree(binding->tx_vec); + kvfree(binding->vec); kfree(binding); } =20 @@ -232,10 +232,10 @@ net_devmem_bind_dmabuf(struct net_device *dev, } =20 if (direction =3D=3D DMA_TO_DEVICE) { - binding->tx_vec =3D kvmalloc_array(dmabuf->size / PAGE_SIZE, - sizeof(struct net_iov *), - GFP_KERNEL); - if (!binding->tx_vec) { + binding->vec =3D kvmalloc_array(dmabuf->size / PAGE_SIZE, + sizeof(struct net_iov *), + GFP_KERNEL); + if (!binding->vec) { err =3D -ENOMEM; goto err_unmap; } @@ -249,7 +249,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, dev_to_node(&dev->dev)); if (!binding->chunk_pool) { err =3D -ENOMEM; - goto err_tx_vec; + goto err_vec; } =20 virtual =3D 0; @@ -295,7 +295,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), net_devmem_get_dma_addr(niov)); if (direction =3D=3D DMA_TO_DEVICE) - binding->tx_vec[owner->area.base_virtual / PAGE_SIZE + i] =3D niov; + binding->vec[owner->area.base_virtual / PAGE_SIZE + i] =3D niov; } =20 virtual +=3D len; @@ -315,8 +315,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, gen_pool_for_each_chunk(binding->chunk_pool, net_devmem_dmabuf_free_chunk_owner, NULL); gen_pool_destroy(binding->chunk_pool); -err_tx_vec: - kvfree(binding->tx_vec); +err_vec: + kvfree(binding->vec); err_unmap: dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt, direction); @@ -363,7 +363,7 @@ struct net_devmem_dmabuf_binding *net_devmem_get_bindin= g(struct sock *sk, int err =3D 0; =20 binding =3D net_devmem_lookup_dmabuf(dmabuf_id); - if (!binding || !binding->tx_vec) { + if (!binding || !binding->vec) { err =3D -EINVAL; goto out_err; } @@ -414,7 +414,7 @@ net_devmem_get_niov_at(struct net_devmem_dmabuf_binding= *binding, *off =3D virt_addr % PAGE_SIZE; *size =3D PAGE_SIZE - *off; =20 - return binding->tx_vec[virt_addr / PAGE_SIZE]; + return binding->vec[virt_addr / PAGE_SIZE]; } =20 /*** "Dmabuf devmem memory provider" ***/ diff --git a/net/core/devmem.h b/net/core/devmem.h index 0b43a648cd2e..1ea6228e4f40 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -63,7 +63,7 @@ struct net_devmem_dmabuf_binding { * address. This array is convenient to map the virtual addresses to * net_iovs in the TX path. */ - struct net_iov **tx_vec; + struct net_iov **vec; =20 struct work_struct unbind_w; }; --=20 2.47.3 From nobody Sun Feb 8 15:25:06 2026 Received: from mail-yx1-f44.google.com (mail-yx1-f44.google.com [74.125.224.44]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id CF6AC23E334 for ; Sat, 10 Jan 2026 02:19:02 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.224.44 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011544; cv=none; b=BvxsbKZ4DjMxquxJ+vpbTePRv1kA8Me3E7xzQxsvjBRVg52MZ1ZvZKmgiBrsRl+wHEkjs15OO15NkCApT6XN9FyNmkn4ZYKC9nNZCYhNRGXRDZVEhrqh9q9vgDw8sj4rJH7sPFPIriuvzZWO0N5dhW2qREBRGTs9FP1xST2ACWQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011544; c=relaxed/simple; bh=/8irlWx212MZNFNuTQquG/o/4qXs4GzUcqgDeIkWkeY=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=ZSDyfvOK3D3CvnqaVHtSdRMdAviTTagmC2VoVtfoEzaViPFKrJwetkZhuas1J7qn5Eoqt5V6FYCUmOmJC6n38ZyBXQ8n2ZdkEtbWeY/nyCkmqHeeQPKGuvb2yta5wiiiMS/7iP22YVioup+Oz2pjtvz6kOf6Xic6oLdqd/8brGM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=Pmh4gQv6; arc=none smtp.client-ip=74.125.224.44 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="Pmh4gQv6" Received: by mail-yx1-f44.google.com with SMTP id 956f58d0204a3-644798bb299so4515083d50.3 for ; Fri, 09 Jan 2026 18:19:02 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1768011542; x=1768616342; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=vJwRH55S+4zS4rc7LIeDbyFWVKjFx7zOxvxC4DTtZFU=; b=Pmh4gQv6CDB0sn4MOfoJNJplhGdYkdl806mn+HX/jQdzPnHdNtrmIAkAo6WQeipPFj q9IP8/gve/ApA78ioiaTE2hknb/mgSj2O66aYQia5uxObrhYl3SKgYdWUGtyM9GUoHIp YgdmgchvIoPttlKzKoVZXqls4rg02rtkJuweYqJSeD2oyD5i2I82qZhEKy6Mczv/KMBl CFkzK0QFpNV2jpONeDQsqjBid0Eclzv7/ESnvQriZUGTGIez7szNmuh+x3NKf5eGMRyC bntgEz+0P95+q2V4sfu5TeyGDkHRG9/cwbCJXisuHKvThcw/lwl+Y9e8bkDwUdV2KN07 GNxQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1768011542; x=1768616342; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-gg:x-gm-message-state:from:to :cc:subject:date:message-id:reply-to; bh=vJwRH55S+4zS4rc7LIeDbyFWVKjFx7zOxvxC4DTtZFU=; b=FwGjYttC1fsBwQgMAdC4eWPsGlliuxfJd73+cZ5lccm3f766pdh9DBFfFyi+waviMv U8LPi+nDbKxXNc9J3FD/HFmwEDGIeLOstNpkKNKjmh+yr1xDl07lhpOXtBLRkmVcMntq 0Kzudbz05Teiz8JR1zPFTar9t8QKPuZFB0XQNPrYrNxfGpUXya0uei6y9fJ0OL5FxrAT OpFWZLyz8bGV3wtwGj1YR7GX7n6EZEyH93wBy7qVgqOUImpkHrr2E+TgFcvtiXRjgFBu Gq/eUCDV5XWqm5zcfFyvjQ8qfi99KovqCCAdwndcwNwltP92cADZ04ibUYzYPgvNU5gO yokQ== X-Forwarded-Encrypted: i=1; AJvYcCU8TOXTdWVnBdKQWrAShMPTch5UPDdwrSi0labUfDcMX4kAP1EUluym+XG8MDt1OyAs3SVf6CwrDavkDbE=@vger.kernel.org X-Gm-Message-State: AOJu0YzAnxEzMFQOJlBGWrn8ByD+3LWdYZY4zAcdldEcJ9vHtL4jofmN 2oV6b/toj0t9mk2C1Fx5PEFoBs36p/hRm7yYa1YzKGfqsdPQWggco8wi X-Gm-Gg: AY/fxX6b5wJCt38F38uvL6fPSdsw35yUQkF6LTN70rJE7SzlQxtIXQbVlke9E1+bA0c yGL5POE9UzCs4exRam1+/HjuF9eTELKy/Me+QoZMIDxd5Cl/TEq37dmm9tvQt2uNA8V/csKnrwJ FBAQ7vapqUOjFBfxDjeGw879cAyik5rwQ80p0uMl50MbCQf29RDPKQA0ldjtoeXtWmicVaC9x5B oRKGCod6QODFp0SahCe/D6+TtkNu1pfEibf9HRJn1qv1+9z7N1lg6lgjwHROunbW0Hnd59ZENwS ow98UWh6qhBitQggsp3allQLPdQeEedhuQzncgsNdyjNwy+HjM3/RLQNdQzzdKybAWkqB9XcIYx muaRx3lcGLbXTzlYjKpUEZLuZkQ5XGDt3AQTqLhVLCFZZHeJZQl1iA4ACkUlM9A2NqOtvzwgN5k yrrTpsdC6ggw== X-Google-Smtp-Source: AGHT+IFOmZSfq1+B/UIacsFnpLVgmv9FPVdwArttfHVymmNEdJMthIaDrn+0zcXw3EHB1ioYKpS2zw== X-Received: by 2002:a53:e319:0:b0:644:7b34:7bd2 with SMTP id 956f58d0204a3-64716c804d2mr7062728d50.75.1768011541886; Fri, 09 Jan 2026 18:19:01 -0800 (PST) Received: from localhost ([2a03:2880:25ff:70::]) by smtp.gmail.com with ESMTPSA id 956f58d0204a3-6470d8b241csm5204761d50.19.2026.01.09.18.19.01 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 09 Jan 2026 18:19:01 -0800 (PST) From: Bobby Eshleman Date: Fri, 09 Jan 2026 18:18:16 -0800 Subject: [PATCH net-next v9 2/5] net: devmem: refactor sock_devmem_dontneed for autorelease split Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-2-8042930d00d7@meta.com> References: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> In-Reply-To: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> To: "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Kuniyuki Iwashima , Willem de Bruijn , Neal Cardwell , David Ahern , Mina Almasry , Arnd Bergmann , Jonathan Corbet , Andrew Lunn , Shuah Khan , Donald Hunter Cc: Stanislav Fomichev , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, asml.silence@gmail.com, matttbe@kernel.org, skhawaja@google.com, Bobby Eshleman X-Mailer: b4 0.14.3 From: Bobby Eshleman Refactor sock_devmem_dontneed() in preparation for supporting both autorelease and manual token release modes. Split the function into two parts: - sock_devmem_dontneed(): handles input validation, token allocation, and copying from userspace - sock_devmem_dontneed_autorelease(): performs the actual token release via xarray lookup and page pool put This separation allows a future commit to add a parallel sock_devmem_dontneed_manual_release() function that uses a different token tracking mechanism (per-niov reference counting) without duplicating the input validation logic. The refactoring is purely mechanical with no functional change. Only intended to minimize the noise in subsequent patches. Reviewed-by: Mina Almasry Signed-off-by: Bobby Eshleman --- net/core/sock.c | 52 ++++++++++++++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 20 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index a1c8b47b0d56..f6526f43aa6e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1082,30 +1082,13 @@ static int sock_reserve_memory(struct sock *sk, int= bytes) #define MAX_DONTNEED_FRAGS 1024 =20 static noinline_for_stack int -sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optle= n) +sock_devmem_dontneed_autorelease(struct sock *sk, struct dmabuf_token *tok= ens, + unsigned int num_tokens) { - unsigned int num_tokens, i, j, k, netmem_num =3D 0; - struct dmabuf_token *tokens; + unsigned int i, j, k, netmem_num =3D 0; int ret =3D 0, num_frags =3D 0; netmem_ref netmems[16]; =20 - if (!sk_is_tcp(sk)) - return -EBADF; - - if (optlen % sizeof(*tokens) || - optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) - return -EINVAL; - - num_tokens =3D optlen / sizeof(*tokens); - tokens =3D kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL); - if (!tokens) - return -ENOMEM; - - if (copy_from_sockptr(tokens, optval, optlen)) { - kvfree(tokens); - return -EFAULT; - } - xa_lock_bh(&sk->sk_user_frags); for (i =3D 0; i < num_tokens; i++) { for (j =3D 0; j < tokens[i].token_count; j++) { @@ -1135,6 +1118,35 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optv= al, unsigned int optlen) for (k =3D 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); =20 + return ret; +} + +static noinline_for_stack int +sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optle= n) +{ + struct dmabuf_token *tokens; + unsigned int num_tokens; + int ret; + + if (!sk_is_tcp(sk)) + return -EBADF; + + if (optlen % sizeof(*tokens) || + optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) + return -EINVAL; + + num_tokens =3D optlen / sizeof(*tokens); + tokens =3D kvmalloc_array(num_tokens, sizeof(*tokens), GFP_KERNEL); + if (!tokens) + return -ENOMEM; + + if (copy_from_sockptr(tokens, optval, optlen)) { + kvfree(tokens); + return -EFAULT; + } + + ret =3D sock_devmem_dontneed_autorelease(sk, tokens, num_tokens); + kvfree(tokens); return ret; } --=20 2.47.3 From nobody Sun Feb 8 15:25:06 2026 Received: from mail-yx1-f43.google.com (mail-yx1-f43.google.com [74.125.224.43]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EFD75244692 for ; Sat, 10 Jan 2026 02:19:03 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.224.43 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011548; cv=none; b=XhojQtpHZt4rXfduEv7jQj0cSwKkRTRGBG8g6/NCJlqAGwsl5TnVY885902SBJuvZY+TDdXE/nsfbdZJacY2Zue0mn6we8a9h0QOeK944f6dzJRnr2THhM5cl1YgFk0nyYnpSL6YqsXGmnFiNgzUX5liVDzBXs5THaUtFvq112o= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011548; c=relaxed/simple; bh=P4d8UqC2nKeC0YQ+a7bgME0cFVqMsz/ydYLiYy8NQ78=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=cNSbzRK/tbaJcJ1pgR1wYdJ77l0BHbw815xSO0Y6b6MnCwxihcH3+P3P71vJj3TigjzO9dtCd/n+D63WObX58XwfeaQvxqZtXcgDVHFAzLsLg/+LknZUtjHLnSKpBy0+/SJpS5YKpKuqU9GhQeAq2DLYDl8JKsiY1yi6qUBWAzM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=IEcwGwAc; arc=none smtp.client-ip=74.125.224.43 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="IEcwGwAc" Received: by mail-yx1-f43.google.com with SMTP id 956f58d0204a3-6446fcddf2fso5080985d50.0 for ; Fri, 09 Jan 2026 18:19:03 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1768011543; x=1768616343; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=arzqbQXlNacdWL74Y2JXdnYTGjM1CMB+bcw7bQGNPJc=; b=IEcwGwAcy8SpujoBI6ZYumo5RItcS6LNZu5t0C6aTPGy5eaXbLkKV6RHUzCG2G2zYO E+lH83d4Tm58KORcQxVsibd+RgtAYzOMgqhu4763xmcbSMug6kXkqV7ogKaV+g4XD1Fl ugDmup+chut6/Q2SsY7QiZwVk/TRzryyDk3btP57Y/SAiOmRjZ/DmJ6XxiAElpDFvkuH DCZDliHbfti6NX+WZ2iAbZjj39hm/qheGQGMEOcS9dy4SjzQOBB9wYsOrjJQNY0NhNE2 60N73RSCbERvMRCR6UdMq8jD368cB9xqfLfEK/0wSma87Rh3kIPiRAnfuMMaZ6dArLoG 3XPg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1768011543; x=1768616343; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-gg:x-gm-message-state:from:to :cc:subject:date:message-id:reply-to; bh=arzqbQXlNacdWL74Y2JXdnYTGjM1CMB+bcw7bQGNPJc=; b=lEsSxC10dLFoeLd5FihZOPm7hsifTJ4hrvXchj5qJjc3iQJiZo5GI7uZBguuuPZhVX TYKcRWC7II1hVyKAprPI2hycFeh4ubbUD1FJ5rnOd2mqPQ6iXLuXUP2p2Q8puaDcotCe 9pNGFmHQVCsvLWYmkRTtFPgX88wtdhChIj4imFAY+VypBtrbZwFJXeNf79dKlDTW/WUI 5PMeH3B58fMVzxShuyCmZixkxB3g6rC4AsG4AkLhVtWyK2UuL/3oTdEJud+b+97fHPK+ v5og976YPjwa8Zzo64p9JTqX6UGu49NdupU9diAlHcGKnssW3qNIpx+ZY8LOa9/JRtt0 7Rnw== X-Forwarded-Encrypted: i=1; AJvYcCUYmt/S0oYrfoayKHBjsGo2a7PztemHUdMCU369DNp9CmLrbiMtew2l8ixfkQRrEwydGJCM02Vw1mpLYvE=@vger.kernel.org X-Gm-Message-State: AOJu0YxNYPW564kLuk7vEH/VlalXtcmSbIw0ldhE3jLyBWUJWrmamhSI AINwwNEz+2ZppIPhKXEHKugCTX4FaSvJi7AdEMm0wf7zsQKZXWiNtXH1 X-Gm-Gg: AY/fxX6eGBEXd1B1V56R9gRCnGcjQxdKWzplYe1edQ70MrGMXCUdc8Zkaa9rveOC486 BiV/CMQgnnDx2Q1HKx6rLdignmRk0hRswzTuOlSEJfKGq53h5DI98SadKv0u0X0Me4f2zjj2KPT qZ6JrwvU9OKrhUKg5uvWOPmrZZLz6rvPbNKidJTjFHG0bcnTT95LmMaEZq9pIMe/pu586xmdfYA AUvDQPSXrp7mx3CrSSmi8AlTzg2TTRV4L0UJJ5BnvUfjdgZcBkxCyGFDxZY8p0kX0kYzt3/2Vv0 tcZiMpfQweQnIlhqjXz0fBXlSuT3G4wnTxH4kKoCb3Bzqa5g/e+9nSDnTMwkJoaEyrb5ru2/QYj qgLZZaniHsOhRIPMRRHT8nL1+hucroe/TqdHrDBsvykRDcJuI5WiWJfRTjb2u4F23gsQWxdn1Do xFfe2QXrdC+g== X-Google-Smtp-Source: AGHT+IHLsLyVl2pa2JrSVd4sJ2IpcPmz1uN7KAItpcWVK3gHr7UzOLhB8xFQ0R4gUz+9ez73pmt2tA== X-Received: by 2002:a05:690e:11cb:b0:63f:b444:da92 with SMTP id 956f58d0204a3-64716b1f9e3mr10153697d50.31.1768011542884; Fri, 09 Jan 2026 18:19:02 -0800 (PST) Received: from localhost ([2a03:2880:25ff:41::]) by smtp.gmail.com with ESMTPSA id 956f58d0204a3-6470d89d4c9sm5232466d50.14.2026.01.09.18.19.02 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 09 Jan 2026 18:19:02 -0800 (PST) From: Bobby Eshleman Date: Fri, 09 Jan 2026 18:18:17 -0800 Subject: [PATCH net-next v9 3/5] net: devmem: implement autorelease token management Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-3-8042930d00d7@meta.com> References: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> In-Reply-To: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> To: "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Kuniyuki Iwashima , Willem de Bruijn , Neal Cardwell , David Ahern , Mina Almasry , Arnd Bergmann , Jonathan Corbet , Andrew Lunn , Shuah Khan , Donald Hunter Cc: Stanislav Fomichev , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, asml.silence@gmail.com, matttbe@kernel.org, skhawaja@google.com, Bobby Eshleman X-Mailer: b4 0.14.3 From: Bobby Eshleman Add support for autorelease toggling of tokens using a static branch to control system-wide behavior. This allows applications to choose between two memory management modes: 1. Autorelease on: Leaked tokens are automatically released when the socket closes. 2. Autorelease off: Leaked tokens are released during dmabuf unbind. The autorelease mode is requested via the NETDEV_A_DMABUF_AUTORELEASE attribute of the NETDEV_CMD_BIND_RX message. Having separate modes per binding is disallowed and is rejected by netlink. The system will be "locked" into the mode that the first binding is set to. It can only be changed again once there are zero bindings on the system. Disabling autorelease offers ~13% improvement in CPU utilization. Static branching is used to limit the system to one mode or the other. Signed-off-by: Bobby Eshleman --- Changes in v9: - Add missing stub for net_devmem_dmabuf_binding_get() when NET_DEVMEM=3Dn - Add wrapper around tcp_devmem_ar_key accesses so that it may be stubbed out when NET_DEVMEM=3Dn - only dec rx binding count for rx bindings in free (v8 did not exclude TX bindings) Changes in v8: - Only reset static key when bindings go to zero, defaulting back to disabled (Stan). - Fix bad usage of xarray spinlock for sleepy static branch switching, use mutex instead. - Access pp_ref_count via niov->desc instead of niov directly. - Move reset of static key to __net_devmem_dmabuf_binding_free() so that the static key can not be changed while there are outstanding tokens (free is only called when reference count reaches zero). - Add net_devmem_dmabuf_rx_bindings_count because tokens may be active even after xa_erase(), so static key changes must wait until all RX bindings are finally freed (not just when xarray is empty). A counter is a simple way to track this. - socket takes reference on the binding, to avoid use-after-free on sk_devmem_info.binding in the case that user releases all tokens, unbinds, then issues SO_DEVMEM_DONTNEED again (with bad token). - removed some comments that were unnecessary Changes in v7: - implement autorelease with static branch (Stan) - use netlink instead of sockopt (Stan) - merge uAPI and implementation patches into one patch (seemed less confusing) Changes in v6: - remove sk_devmem_info.autorelease, using binding->autorelease instead - move binding->autorelease check to outside of net_devmem_dmabuf_binding_put_urefs() (Mina) - remove overly defensive net_is_devmem_iov() (Mina) - add comment about multiple urefs mapping to a single netmem ref (Mina) - remove overly defense netmem NULL and netmem_is_net_iov checks (Mina) - use niov without casting back and forth with netmem (Mina) - move the autorelease flag from per-binding to per-socket (Mina) - remove the batching logic in sock_devmem_dontneed_manual_release() (Mina) - move autorelease check inside tcp_xa_pool_commit() (Mina) - remove single-binding restriction for autorelease mode (Mina) - unbind always checks for leaked urefs Changes in v5: - remove unused variables - introduce autorelease flag, preparing for future patch toggle new behavior Changes in v3: - make urefs per-binding instead of per-socket, reducing memory footprint - fallback to cleaning up references in dmabuf unbind if socket leaked tokens - drop ethtool patch Changes in v2: - always use GFP_ZERO for binding->vec (Mina) - remove WARN for changed binding (Mina) - remove extraneous binding ref get (Mina) - remove WARNs on invalid user input (Mina) - pre-assign niovs in binding->vec for RX case (Mina) - use atomic_set(, 0) to initialize sk_user_frags.urefs - fix length of alloc for urefs --- Documentation/netlink/specs/netdev.yaml | 12 ++++ include/net/netmem.h | 1 + include/net/sock.h | 7 ++- include/uapi/linux/netdev.h | 1 + net/core/devmem.c | 104 ++++++++++++++++++++++++++++= ---- net/core/devmem.h | 27 ++++++++- net/core/netdev-genl-gen.c | 5 +- net/core/netdev-genl.c | 10 ++- net/core/sock.c | 57 +++++++++++++++-- net/ipv4/tcp.c | 76 ++++++++++++++++++----- net/ipv4/tcp_ipv4.c | 11 +++- net/ipv4/tcp_minisocks.c | 3 +- tools/include/uapi/linux/netdev.h | 1 + 13 files changed, 269 insertions(+), 46 deletions(-) diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlin= k/specs/netdev.yaml index 596c306ce52b..7cbe9e7b9ee5 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -562,6 +562,17 @@ attribute-sets: type: u32 checks: min: 1 + - + name: autorelease + doc: | + Token autorelease mode. If true (1), leaked tokens are automatic= ally + released when the socket closes. If false (0), leaked tokens are= only + released when the dmabuf is unbound. Once a binding is created w= ith a + specific mode, all subsequent bindings system-wide must use the = same + mode. + + Optional. Defaults to false if not specified. + type: u8 =20 operations: list: @@ -769,6 +780,7 @@ operations: - ifindex - fd - queues + - autorelease reply: attributes: - id diff --git a/include/net/netmem.h b/include/net/netmem.h index 9e10f4ac50c3..80d2263ba4ed 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -112,6 +112,7 @@ struct net_iov { }; struct net_iov_area *owner; enum net_iov_type type; + atomic_t uref; }; =20 struct net_iov_area { diff --git a/include/net/sock.h b/include/net/sock.h index aafe8bdb2c0f..9d3d5bde15e9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -352,7 +352,7 @@ struct sk_filter; * @sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS * @sk_scm_unused: unused flags for scm_recv() * @ns_tracker: tracker for netns reference - * @sk_user_frags: xarray of pages the user is holding a reference on. + * @sk_devmem_info: the devmem binding information for the socket * @sk_owner: reference to the real owner of the socket that calls * sock_lock_init_class_and_name(). */ @@ -584,7 +584,10 @@ struct sock { struct numa_drop_counters *sk_drop_counters; struct rcu_head sk_rcu; netns_tracker ns_tracker; - struct xarray sk_user_frags; + struct { + struct xarray frags; + struct net_devmem_dmabuf_binding *binding; + } sk_devmem_info; =20 #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) struct module *sk_owner; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index e0b579a1df4f..1e5c209cb998 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -207,6 +207,7 @@ enum { NETDEV_A_DMABUF_QUEUES, NETDEV_A_DMABUF_FD, NETDEV_A_DMABUF_ID, + NETDEV_A_DMABUF_AUTORELEASE, =20 __NETDEV_A_DMABUF_MAX, NETDEV_A_DMABUF_MAX =3D (__NETDEV_A_DMABUF_MAX - 1) diff --git a/net/core/devmem.c b/net/core/devmem.c index 05a9a9e7abb9..05c16df657c7 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -28,6 +29,19 @@ =20 static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1); =20 +/* If the user unbinds before releasing all tokens, the static key must not + * change until all tokens have been released (to avoid calling the wrong + * SO_DEVMEM_DONTNEED handler). We prevent this by making static key chang= es + * and binding alloc/free atomic with regards to each other, using the + * devmem_ar_lock. This works because binding free does not occur until al= l of + * the outstanding token's references on the binding are dropped. + */ +static DEFINE_MUTEX(devmem_ar_lock); + +DEFINE_STATIC_KEY_FALSE(tcp_devmem_ar_key); +EXPORT_SYMBOL(tcp_devmem_ar_key); +static int net_devmem_dmabuf_rx_bindings_count; + static const struct memory_provider_ops dmabuf_devmem_ops; =20 bool net_is_devmem_iov(struct net_iov *niov) @@ -60,6 +74,14 @@ void __net_devmem_dmabuf_binding_free(struct work_struct= *wq) =20 size_t size, avail; =20 + if (binding->direction =3D=3D DMA_FROM_DEVICE) { + mutex_lock(&devmem_ar_lock); + net_devmem_dmabuf_rx_bindings_count--; + if (net_devmem_dmabuf_rx_bindings_count =3D=3D 0) + static_branch_disable(&tcp_devmem_ar_key); + mutex_unlock(&devmem_ar_lock); + } + gen_pool_for_each_chunk(binding->chunk_pool, net_devmem_dmabuf_free_chunk_owner, NULL); =20 @@ -116,6 +138,24 @@ void net_devmem_free_dmabuf(struct net_iov *niov) gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE); } =20 +static void +net_devmem_dmabuf_binding_put_urefs(struct net_devmem_dmabuf_binding *bind= ing) +{ + int i; + + for (i =3D 0; i < binding->dmabuf->size / PAGE_SIZE; i++) { + struct net_iov *niov; + netmem_ref netmem; + + niov =3D binding->vec[i]; + netmem =3D net_iov_to_netmem(niov); + + /* Multiple urefs map to only a single netmem ref. */ + if (atomic_xchg(&niov->uref, 0) > 0) + WARN_ON_ONCE(!napi_pp_put_page(netmem)); + } +} + void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) { struct netdev_rx_queue *rxq; @@ -143,6 +183,7 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_= binding *binding) __net_mp_close_rxq(binding->dev, rxq_idx, &mp_params); } =20 + net_devmem_dmabuf_binding_put_urefs(binding); net_devmem_dmabuf_binding_put(binding); } =20 @@ -179,8 +220,10 @@ struct net_devmem_dmabuf_binding * net_devmem_bind_dmabuf(struct net_device *dev, struct device *dma_dev, enum dma_data_direction direction, - unsigned int dmabuf_fd, struct netdev_nl_sock *priv, - struct netlink_ext_ack *extack) + unsigned int dmabuf_fd, + struct netdev_nl_sock *priv, + struct netlink_ext_ack *extack, + bool autorelease) { struct net_devmem_dmabuf_binding *binding; static u32 id_alloc_next; @@ -231,14 +274,12 @@ net_devmem_bind_dmabuf(struct net_device *dev, goto err_detach; } =20 - if (direction =3D=3D DMA_TO_DEVICE) { - binding->vec =3D kvmalloc_array(dmabuf->size / PAGE_SIZE, - sizeof(struct net_iov *), - GFP_KERNEL); - if (!binding->vec) { - err =3D -ENOMEM; - goto err_unmap; - } + binding->vec =3D kvmalloc_array(dmabuf->size / PAGE_SIZE, + sizeof(struct net_iov *), + GFP_KERNEL | __GFP_ZERO); + if (!binding->vec) { + err =3D -ENOMEM; + goto err_unmap; } =20 /* For simplicity we expect to make PAGE_SIZE allocations, but the @@ -292,25 +333,62 @@ net_devmem_bind_dmabuf(struct net_device *dev, niov =3D &owner->area.niovs[i]; niov->type =3D NET_IOV_DMABUF; niov->owner =3D &owner->area; + atomic_set(&niov->uref, 0); page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), net_devmem_get_dma_addr(niov)); - if (direction =3D=3D DMA_TO_DEVICE) - binding->vec[owner->area.base_virtual / PAGE_SIZE + i] =3D niov; + binding->vec[owner->area.base_virtual / PAGE_SIZE + i] =3D niov; } =20 virtual +=3D len; } =20 + mutex_lock(&devmem_ar_lock); + + if (direction =3D=3D DMA_FROM_DEVICE) { + if (net_devmem_dmabuf_rx_bindings_count > 0) { + bool mode; + + mode =3D static_key_enabled(&tcp_devmem_ar_key); + + /* When bindings exist, enforce that the mode does not + * change. + */ + if (mode !=3D autorelease) { + NL_SET_ERR_MSG_FMT(extack, + "System already configured with autorelease=3D%d", + mode); + err =3D -EINVAL; + goto err_unlock_mutex; + } + } else if (autorelease) { + /* First binding with autorelease enabled sets the + * mode. If autorelease is false, the key is already + * disabled by default so no action is needed. + */ + static_branch_enable(&tcp_devmem_ar_key); + } + + net_devmem_dmabuf_rx_bindings_count++; + } + err =3D xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id, binding, xa_limit_32b, &id_alloc_next, GFP_KERNEL); if (err < 0) - goto err_free_chunks; + goto err_dec_binding_count; + + mutex_unlock(&devmem_ar_lock); =20 list_add(&binding->list, &priv->bindings); =20 return binding; =20 +err_dec_binding_count: + if (direction =3D=3D DMA_FROM_DEVICE) + net_devmem_dmabuf_rx_bindings_count--; + +err_unlock_mutex: + mutex_unlock(&devmem_ar_lock); err_free_chunks: gen_pool_for_each_chunk(binding->chunk_pool, net_devmem_dmabuf_free_chunk_owner, NULL); diff --git a/net/core/devmem.h b/net/core/devmem.h index 1ea6228e4f40..8c586f30e371 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -12,9 +12,13 @@ =20 #include #include +#include =20 struct netlink_ext_ack; =20 +/* static key for TCP devmem autorelease */ +extern struct static_key_false tcp_devmem_ar_key; + struct net_devmem_dmabuf_binding { struct dma_buf *dmabuf; struct dma_buf_attachment *attachment; @@ -61,7 +65,7 @@ struct net_devmem_dmabuf_binding { =20 /* Array of net_iov pointers for this binding, sorted by virtual * address. This array is convenient to map the virtual addresses to - * net_iovs in the TX path. + * net_iovs. */ struct net_iov **vec; =20 @@ -88,7 +92,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, struct device *dma_dev, enum dma_data_direction direction, unsigned int dmabuf_fd, struct netdev_nl_sock *priv, - struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack, bool autorelease); struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id); void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, @@ -138,6 +142,11 @@ net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf= _binding *binding) schedule_work(&binding->unbind_w); } =20 +static inline bool net_devmem_autorelease_enabled(void) +{ + return static_branch_unlikely(&tcp_devmem_ar_key); +} + void net_devmem_get_net_iov(struct net_iov *niov); void net_devmem_put_net_iov(struct net_iov *niov); =20 @@ -155,6 +164,12 @@ net_devmem_get_niov_at(struct net_devmem_dmabuf_bindin= g *binding, size_t addr, #else struct net_devmem_dmabuf_binding; =20 +static inline bool +net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) +{ + return false; +} + static inline void net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) { @@ -174,7 +189,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, enum dma_data_direction direction, unsigned int dmabuf_fd, struct netdev_nl_sock *priv, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + bool autorelease) { return ERR_PTR(-EOPNOTSUPP); } @@ -241,6 +257,11 @@ net_devmem_iov_binding(const struct net_iov *niov) { return NULL; } + +static inline bool net_devmem_autorelease_enabled(void) +{ + return false; +} #endif =20 #endif /* _NET_DEVMEM_H */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index ba673e81716f..01b7765e11ec 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -86,10 +86,11 @@ static const struct nla_policy netdev_qstats_get_nl_pol= icy[NETDEV_A_QSTATS_SCOPE }; =20 /* NETDEV_CMD_BIND_RX - do */ -static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD= + 1] =3D { +static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_AU= TORELEASE + 1] =3D { [NETDEV_A_DMABUF_IFINDEX] =3D NLA_POLICY_MIN(NLA_U32, 1), [NETDEV_A_DMABUF_FD] =3D { .type =3D NLA_U32, }, [NETDEV_A_DMABUF_QUEUES] =3D NLA_POLICY_NESTED(netdev_queue_id_nl_policy), + [NETDEV_A_DMABUF_AUTORELEASE] =3D { .type =3D NLA_U8, }, }; =20 /* NETDEV_CMD_NAPI_SET - do */ @@ -188,7 +189,7 @@ static const struct genl_split_ops netdev_nl_ops[] =3D { .cmd =3D NETDEV_CMD_BIND_RX, .doit =3D netdev_nl_bind_rx_doit, .policy =3D netdev_bind_rx_nl_policy, - .maxattr =3D NETDEV_A_DMABUF_FD, + .maxattr =3D NETDEV_A_DMABUF_AUTORELEASE, .flags =3D GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 470fabbeacd9..c742bb34865e 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -939,6 +939,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct = genl_info *info) struct netdev_nl_sock *priv; struct net_device *netdev; unsigned long *rxq_bitmap; + bool autorelease =3D false; struct device *dma_dev; struct sk_buff *rsp; int err =3D 0; @@ -952,6 +953,10 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct= genl_info *info) ifindex =3D nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); dmabuf_fd =3D nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); =20 + if (info->attrs[NETDEV_A_DMABUF_AUTORELEASE]) + autorelease =3D + !!nla_get_u8(info->attrs[NETDEV_A_DMABUF_AUTORELEASE]); + priv =3D genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk); if (IS_ERR(priv)) return PTR_ERR(priv); @@ -1002,7 +1007,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struc= t genl_info *info) } =20 binding =3D net_devmem_bind_dmabuf(netdev, dma_dev, DMA_FROM_DEVICE, - dmabuf_fd, priv, info->extack); + dmabuf_fd, priv, info->extack, + autorelease); if (IS_ERR(binding)) { err =3D PTR_ERR(binding); goto err_rxq_bitmap; @@ -1097,7 +1103,7 @@ int netdev_nl_bind_tx_doit(struct sk_buff *skb, struc= t genl_info *info) =20 dma_dev =3D netdev_queue_get_dma_dev(netdev, 0); binding =3D net_devmem_bind_dmabuf(netdev, dma_dev, DMA_TO_DEVICE, - dmabuf_fd, priv, info->extack); + dmabuf_fd, priv, info->extack, false); if (IS_ERR(binding)) { err =3D PTR_ERR(binding); goto err_unlock_netdev; diff --git a/net/core/sock.c b/net/core/sock.c index f6526f43aa6e..6355c2ccfb8a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -87,6 +87,7 @@ =20 #include #include +#include #include #include #include @@ -151,6 +152,7 @@ #include =20 #include "dev.h" +#include "devmem.h" =20 static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); @@ -1081,6 +1083,44 @@ static int sock_reserve_memory(struct sock *sk, int = bytes) #define MAX_DONTNEED_TOKENS 128 #define MAX_DONTNEED_FRAGS 1024 =20 +static noinline_for_stack int +sock_devmem_dontneed_manual_release(struct sock *sk, + struct dmabuf_token *tokens, + unsigned int num_tokens) +{ + struct net_iov *niov; + unsigned int i, j; + netmem_ref netmem; + unsigned int token; + int num_frags =3D 0; + int ret =3D 0; + + if (!sk->sk_devmem_info.binding) + return -EINVAL; + + for (i =3D 0; i < num_tokens; i++) { + for (j =3D 0; j < tokens[i].token_count; j++) { + size_t size =3D sk->sk_devmem_info.binding->dmabuf->size; + + token =3D tokens[i].token_start + j; + if (token >=3D size / PAGE_SIZE) + break; + + if (++num_frags > MAX_DONTNEED_FRAGS) + return ret; + + niov =3D sk->sk_devmem_info.binding->vec[token]; + if (atomic_dec_and_test(&niov->uref)) { + netmem =3D net_iov_to_netmem(niov); + WARN_ON_ONCE(!napi_pp_put_page(netmem)); + } + ret++; + } + } + + return ret; +} + static noinline_for_stack int sock_devmem_dontneed_autorelease(struct sock *sk, struct dmabuf_token *tok= ens, unsigned int num_tokens) @@ -1089,32 +1129,33 @@ sock_devmem_dontneed_autorelease(struct sock *sk, s= truct dmabuf_token *tokens, int ret =3D 0, num_frags =3D 0; netmem_ref netmems[16]; =20 - xa_lock_bh(&sk->sk_user_frags); + xa_lock_bh(&sk->sk_devmem_info.frags); for (i =3D 0; i < num_tokens; i++) { for (j =3D 0; j < tokens[i].token_count; j++) { if (++num_frags > MAX_DONTNEED_FRAGS) goto frag_limit_reached; =20 netmem_ref netmem =3D (__force netmem_ref)__xa_erase( - &sk->sk_user_frags, tokens[i].token_start + j); + &sk->sk_devmem_info.frags, + tokens[i].token_start + j); =20 if (!netmem || WARN_ON_ONCE(!netmem_is_net_iov(netmem))) continue; =20 netmems[netmem_num++] =3D netmem; if (netmem_num =3D=3D ARRAY_SIZE(netmems)) { - xa_unlock_bh(&sk->sk_user_frags); + xa_unlock_bh(&sk->sk_devmem_info.frags); for (k =3D 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); netmem_num =3D 0; - xa_lock_bh(&sk->sk_user_frags); + xa_lock_bh(&sk->sk_devmem_info.frags); } ret++; } } =20 frag_limit_reached: - xa_unlock_bh(&sk->sk_user_frags); + xa_unlock_bh(&sk->sk_devmem_info.frags); for (k =3D 0; k < netmem_num; k++) WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); =20 @@ -1145,7 +1186,11 @@ sock_devmem_dontneed(struct sock *sk, sockptr_t optv= al, unsigned int optlen) return -EFAULT; } =20 - ret =3D sock_devmem_dontneed_autorelease(sk, tokens, num_tokens); + if (net_devmem_autorelease_enabled()) + ret =3D sock_devmem_dontneed_autorelease(sk, tokens, num_tokens); + else + ret =3D sock_devmem_dontneed_manual_release(sk, tokens, + num_tokens); =20 kvfree(tokens); return ret; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d5319ebe2452..a8a4af552909 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -260,6 +260,7 @@ #include #include #include +#include #include #include #include @@ -492,7 +493,8 @@ void tcp_init_sock(struct sock *sk) =20 set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); - xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); + xa_init_flags(&sk->sk_devmem_info.frags, XA_FLAGS_ALLOC1); + sk->sk_devmem_info.binding =3D NULL; } EXPORT_IPV6_MOD(tcp_init_sock); =20 @@ -2424,11 +2426,12 @@ static void tcp_xa_pool_commit_locked(struct sock *= sk, struct tcp_xa_pool *p) =20 /* Commit part that has been copied to user space. */ for (i =3D 0; i < p->idx; i++) - __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, - (__force void *)p->netmems[i], GFP_KERNEL); + __xa_cmpxchg(&sk->sk_devmem_info.frags, p->tokens[i], + XA_ZERO_ENTRY, (__force void *)p->netmems[i], + GFP_KERNEL); /* Rollback what has been pre-allocated and is no longer needed. */ for (; i < p->max; i++) - __xa_erase(&sk->sk_user_frags, p->tokens[i]); + __xa_erase(&sk->sk_devmem_info.frags, p->tokens[i]); =20 p->max =3D 0; p->idx =3D 0; @@ -2436,14 +2439,18 @@ static void tcp_xa_pool_commit_locked(struct sock *= sk, struct tcp_xa_pool *p) =20 static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) { + /* Skip xarray operations if autorelease is disabled (manual mode) */ + if (!net_devmem_autorelease_enabled()) + return; + if (!p->max) return; =20 - xa_lock_bh(&sk->sk_user_frags); + xa_lock_bh(&sk->sk_devmem_info.frags); =20 tcp_xa_pool_commit_locked(sk, p); =20 - xa_unlock_bh(&sk->sk_user_frags); + xa_unlock_bh(&sk->sk_devmem_info.frags); } =20 static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, @@ -2454,24 +2461,41 @@ static int tcp_xa_pool_refill(struct sock *sk, stru= ct tcp_xa_pool *p, if (p->idx < p->max) return 0; =20 - xa_lock_bh(&sk->sk_user_frags); + xa_lock_bh(&sk->sk_devmem_info.frags); =20 tcp_xa_pool_commit_locked(sk, p); =20 for (k =3D 0; k < max_frags; k++) { - err =3D __xa_alloc(&sk->sk_user_frags, &p->tokens[k], + err =3D __xa_alloc(&sk->sk_devmem_info.frags, &p->tokens[k], XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); if (err) break; } =20 - xa_unlock_bh(&sk->sk_user_frags); + xa_unlock_bh(&sk->sk_devmem_info.frags); =20 p->max =3D k; p->idx =3D 0; return k ? 0 : err; } =20 +static void tcp_xa_pool_inc_pp_ref_count(struct tcp_xa_pool *tcp_xa_pool, + skb_frag_t *frag) +{ + struct net_iov *niov; + + niov =3D skb_frag_net_iov(frag); + + if (net_devmem_autorelease_enabled()) { + atomic_long_inc(&niov->desc.pp_ref_count); + tcp_xa_pool->netmems[tcp_xa_pool->idx++] =3D + skb_frag_netmem(frag); + } else { + if (atomic_inc_return(&niov->uref) =3D=3D 1) + atomic_long_inc(&niov->desc.pp_ref_count); + } +} + /* On error, returns the -errno. On success, returns number of bytes sent = to the * user. May not consume all of @remaining_len. */ @@ -2533,6 +2557,7 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const = struct sk_buff *skb, * sequence of cmsg */ for (i =3D 0; i < skb_shinfo(skb)->nr_frags; i++) { + struct net_devmem_dmabuf_binding *binding =3D NULL; skb_frag_t *frag =3D &skb_shinfo(skb)->frags[i]; struct net_iov *niov; u64 frag_offset; @@ -2568,13 +2593,35 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, cons= t struct sk_buff *skb, start; dmabuf_cmsg.frag_offset =3D frag_offset; dmabuf_cmsg.frag_size =3D copy; - err =3D tcp_xa_pool_refill(sk, &tcp_xa_pool, - skb_shinfo(skb)->nr_frags - i); - if (err) + + binding =3D net_devmem_iov_binding(niov); + + if (!sk->sk_devmem_info.binding) { + net_devmem_dmabuf_binding_get(binding); + sk->sk_devmem_info.binding =3D binding; + } + + if (sk->sk_devmem_info.binding !=3D binding) { + err =3D -EFAULT; goto out; + } + + if (net_devmem_autorelease_enabled()) { + err =3D tcp_xa_pool_refill(sk, + &tcp_xa_pool, + skb_shinfo(skb)->nr_frags - i); + if (err) + goto out; + + dmabuf_cmsg.frag_token =3D + tcp_xa_pool.tokens[tcp_xa_pool.idx]; + } else { + dmabuf_cmsg.frag_token =3D + net_iov_virtual_addr(niov) >> PAGE_SHIFT; + } + =20 /* Will perform the exchange later */ - dmabuf_cmsg.frag_token =3D tcp_xa_pool.tokens[tcp_xa_pool.idx]; dmabuf_cmsg.dmabuf_id =3D net_devmem_iov_binding_id(niov); =20 offset +=3D copy; @@ -2587,8 +2634,7 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const = struct sk_buff *skb, if (err) goto out; =20 - atomic_long_inc(&niov->desc.pp_ref_count); - tcp_xa_pool.netmems[tcp_xa_pool.idx++] =3D skb_frag_netmem(frag); + tcp_xa_pool_inc_pp_ref_count(&tcp_xa_pool, frag); =20 sent +=3D copy; =20 diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f8a9596e8f4d..7b1b5a17002f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -89,6 +89,9 @@ =20 #include =20 +#include +#include "../core/devmem.h" + #include =20 #ifdef CONFIG_TCP_MD5SIG @@ -2492,7 +2495,7 @@ static void tcp_release_user_frags(struct sock *sk) unsigned long index; void *netmem; =20 - xa_for_each(&sk->sk_user_frags, index, netmem) + xa_for_each(&sk->sk_devmem_info.frags, index, netmem) WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); #endif } @@ -2503,7 +2506,11 @@ void tcp_v4_destroy_sock(struct sock *sk) =20 tcp_release_user_frags(sk); =20 - xa_destroy(&sk->sk_user_frags); + xa_destroy(&sk->sk_devmem_info.frags); + if (sk->sk_devmem_info.binding) { + net_devmem_dmabuf_binding_put(sk->sk_devmem_info.binding); + sk->sk_devmem_info.binding =3D NULL; + } =20 trace_tcp_destroy_sock(sk); =20 diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index bd5462154f97..2aec977f5c12 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -662,7 +662,8 @@ struct sock *tcp_create_openreq_child(const struct sock= *sk, =20 __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); =20 - xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1); + xa_init_flags(&newsk->sk_devmem_info.frags, XA_FLAGS_ALLOC1); + newsk->sk_devmem_info.binding =3D NULL; =20 return newsk; } diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/n= etdev.h index e0b579a1df4f..1e5c209cb998 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -207,6 +207,7 @@ enum { NETDEV_A_DMABUF_QUEUES, NETDEV_A_DMABUF_FD, NETDEV_A_DMABUF_ID, + NETDEV_A_DMABUF_AUTORELEASE, =20 __NETDEV_A_DMABUF_MAX, NETDEV_A_DMABUF_MAX =3D (__NETDEV_A_DMABUF_MAX - 1) --=20 2.47.3 From nobody Sun Feb 8 15:25:06 2026 Received: from mail-yx1-f66.google.com (mail-yx1-f66.google.com [74.125.224.66]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 098CD25F78F for ; Sat, 10 Jan 2026 02:19:04 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.224.66 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011550; cv=none; b=U15hcOt0BQeT5Y/C0ejnv6zLZ5Rd0QLXLMZccu4JtfxSAgsU5J1OKhK6ikoalsQPmyDhET3Mli8/jSmFtWOOEeaa6zUhjwUq3b8jMQ/KcMWKbIY+Unfow9dSqbtVu3L3cf7l70QX7GDz1iz4RmyKGFpxeCtVVnjcAIWMz2z1AGo= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011550; c=relaxed/simple; bh=6tucM9ZQ59G0xrDfMuItsfF1GTt7N8xzYil/t1gA1PQ=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=TBUwFMh7WQ1uyVChDUc44PCGaEThDtahTH4oqpVm8k94aW0NSx3XTwdwmk7tw3f9VQirs6/R9QUoxNyRHweC8KVs1u3TbPn/2BssxKq+1t4TgoIrLv6Q0A8jGQvn53vOhnZG5Yj4TNWQVofT4CBwliHAXf0rbF7i7e16LfrjLeg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=RRZ//9XF; arc=none smtp.client-ip=74.125.224.66 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="RRZ//9XF" Received: by mail-yx1-f66.google.com with SMTP id 956f58d0204a3-646d9eb45afso4577671d50.2 for ; Fri, 09 Jan 2026 18:19:04 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1768011544; x=1768616344; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=DXRdbOnUYiudn9GxHVVfvuR3By+3aRth8g9ruHEmquY=; b=RRZ//9XFWutooYFdB4GTmpzjV5zZXDbguHHvTNrat3+JjePN7DsXSBz2YEoc1sBUNr CWu19+T0PsjbWWn41lO6qbwbaQCFgEKUdQZRxI6vEVYheN8zDQV/QhDWt1gK53qaLMxV wBg6p4gCF9VZK3tj0a7cQ2ddG+jgbuShYTP4Ijfwm9A1A7+pU9pml2geDMy4xT0YWuZG BqjWeoJXTdjafCZrbOD/GX980Rkv6SR8HuaMHHTTdDLCdIlDx+KBx2QN4XIEAeFvTfW7 5usfQLENdof2Bu2Z7IWiVc121bGmVIZb6qnKORdhNx18h83RXKnRXKU7JJn4RmFRM0vI zrVQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1768011544; x=1768616344; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-gg:x-gm-message-state:from:to :cc:subject:date:message-id:reply-to; bh=DXRdbOnUYiudn9GxHVVfvuR3By+3aRth8g9ruHEmquY=; b=vaNF2qLKkOTdBGM1x7YBENEcziG2W43Hjv7q0YuOvhAUjhzJK++0gEWshQ+FM8UB4Q 0UY1JWijSEq+WenYXeaqYjcDY9rO12bFugVs3DOYmd5xK5+AzbVZOIuaVJ0WUVzPDAto +jJbBgxvcDUnqYlzKKMl5UK7FHCh3KZbF2Zxe4E2OYKQZmzaW2TJR+HZnYM/t+Lkbnp0 hWG55pcfg1Ep1od8XjIwYRv+va9gyHBtyj6n/9RFlH36a7pmw1b2ms6/VaqgPpAWxWis CEnbWrvvnTTReoEjmNZCdrqrUWjWc+EHarecXhoWPL2TsLlytxvL2vWLL25ucRZfi5vU Oo9A== X-Forwarded-Encrypted: i=1; AJvYcCWBkscg8XMFmDuRKutVyGRg1YPwehyss646v2kJP5hQvMNBgufboyBdwC9pAuD1yPE/usLXFGAhaQp5eds=@vger.kernel.org X-Gm-Message-State: AOJu0YwM74LlMQWJT9qfkjG9sImTycO+r7nD217iCk7brjQKvOKsP3tq bAowdPiFcwuRYf3cQKQy49kB7uYsXB6u2PAeU7cvICI40UEtHgp/U97T X-Gm-Gg: AY/fxX6AR+G5puLIYpgUs+YT4JdNzgOUxGGGtf7PdKaflIuxCLBffJqQVBuQA5Nrqrv 4ndiel44ACoV1WfFKC8NntZE52ihjCJgDOL2OsTr7oNAfoaELic3mx4k3AdjfeZ8O9hXFEm68Ec nnVZjxV+zt1RRAGiT11FsiGRqHb6ipsOSVbYupYmVe2XQ0nc7Hoc+CNXW8aC2hQNBX5m5AyGq9T BNU6QxZ8yZEYtKsGmXvblTUe5mMbIucAQhcN5M6XGpMG8/YzrT1d0URJ8p33P/OsOoAUrqdJ7g/ OAHBfWOe25ucEAxa9/uRrni6SU+1dNkurnEIYkqWlhHyxUUDse9ymdGVMqMsv+PybUICcWo5VT8 zRl+anl+CX1/bY7i1c9nwf88/bp/sLxL8HABY1wfuF9Rh9tcHQcCfPga7gUVm+RqfS7a75Paypc eqhLqE4chDvg== X-Google-Smtp-Source: AGHT+IGzRizbGlIsAZwDp+VnMT+8idkBjcUWkmHJRYK1pkT2bOkNYQhUeyud4a1V268OgPfep68gmw== X-Received: by 2002:a05:690e:400a:b0:646:a3cf:a2e8 with SMTP id 956f58d0204a3-64716ba374amr9762926d50.40.1768011543796; Fri, 09 Jan 2026 18:19:03 -0800 (PST) Received: from localhost ([2a03:2880:25ff:53::]) by smtp.gmail.com with ESMTPSA id 00721157ae682-790aa672725sm47421447b3.34.2026.01.09.18.19.03 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 09 Jan 2026 18:19:03 -0800 (PST) From: Bobby Eshleman Date: Fri, 09 Jan 2026 18:18:18 -0800 Subject: [PATCH net-next v9 4/5] net: devmem: document NETDEV_A_DMABUF_AUTORELEASE netlink attribute Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-4-8042930d00d7@meta.com> References: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> In-Reply-To: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> To: "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Kuniyuki Iwashima , Willem de Bruijn , Neal Cardwell , David Ahern , Mina Almasry , Arnd Bergmann , Jonathan Corbet , Andrew Lunn , Shuah Khan , Donald Hunter Cc: Stanislav Fomichev , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, asml.silence@gmail.com, matttbe@kernel.org, skhawaja@google.com, Bobby Eshleman X-Mailer: b4 0.14.3 From: Bobby Eshleman Update devmem.rst documentation to describe the autorelease netlink attribute used during RX dmabuf binding. The autorelease attribute is specified at bind-time via the netlink API (NETDEV_CMD_BIND_RX) and controls what happens to outstanding tokens when the socket closes. Document the two token release modes (automatic vs manual), how to configure the binding for autorelease, the perf benefits, new caveats and restrictions, and the way the mode is enforced system-wide. Signed-off-by: Bobby Eshleman Reviewed-by: Mina Almasry --- Changes in v7: - Document netlink instead of sockopt - Mention system-wide locked to one mode --- Documentation/networking/devmem.rst | 70 +++++++++++++++++++++++++++++++++= ++++ 1 file changed, 70 insertions(+) diff --git a/Documentation/networking/devmem.rst b/Documentation/networking= /devmem.rst index a6cd7236bfbd..67c63bc5a7ae 100644 --- a/Documentation/networking/devmem.rst +++ b/Documentation/networking/devmem.rst @@ -235,6 +235,76 @@ can be less than the tokens provided by the user in ca= se of: (a) an internal kernel leak bug. (b) the user passed more than 1024 frags. =20 + +Autorelease Control +~~~~~~~~~~~~~~~~~~~ + +The autorelease mode controls what happens to outstanding tokens (tokens n= ot +released via SO_DEVMEM_DONTNEED) when the socket closes. Autorelease is +configured per-binding at binding creation time via the netlink API:: + + struct netdev_bind_rx_req *req; + struct netdev_bind_rx_rsp *rsp; + struct ynl_sock *ys; + struct ynl_error yerr; + + ys =3D ynl_sock_create(&ynl_netdev_family, &yerr); + + req =3D netdev_bind_rx_req_alloc(); + netdev_bind_rx_req_set_ifindex(req, ifindex); + netdev_bind_rx_req_set_fd(req, dmabuf_fd); + netdev_bind_rx_req_set_autorelease(req, 0); /* 0 =3D manual, 1 =3D auto */ + __netdev_bind_rx_req_set_queues(req, queues, n_queues); + + rsp =3D netdev_bind_rx(ys, req); + + dmabuf_id =3D rsp->id; + +When autorelease is disabled (0): + +- Outstanding tokens are NOT released when the socket closes +- Outstanding tokens are only released when the dmabuf is unbound +- Provides better performance by eliminating xarray overhead (~13% CPU red= uction) +- Kernel tracks tokens via atomic reference counters in net_iov structures + +When autorelease is enabled (1): + +- Outstanding tokens are automatically released when the socket closes +- Backwards compatible behavior +- Kernel tracks tokens in an xarray per socket + +The default is autorelease disabled. + +Important: In both modes, applications should call SO_DEVMEM_DONTNEED to +return tokens as soon as they are done processing. The autorelease setting= only +affects what happens to tokens that are still outstanding when close() is = called. + +The mode is enforced system-wide. Once a binding is created with a specific +autorelease mode, all subsequent bindings system-wide must use the same mo= de. + + +Performance Considerations +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Disabling autorelease provides approximately ~13% CPU utilization improvem= ent +in RX workloads. That said, applications must ensure all tokens are releas= ed +via SO_DEVMEM_DONTNEED before closing the socket, otherwise the backing pa= ges +will remain pinned until the dmabuf is unbound. + + +Caveats +~~~~~~~ + +- Once a system-wide autorelease mode is selected (via the first binding), + all subsequent bindings must use the same mode. Attempts to create bindi= ngs + with a different mode will be rejected with -EINVAL. + +- Applications using manual release mode (autorelease=3D0) must ensure all= tokens + are returned via SO_DEVMEM_DONTNEED before socket close to avoid resource + leaks during the lifetime of the dmabuf binding. Tokens not released bef= ore + close() will only be freed when the dmabuf is unbound. + + TX Interface =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =20 --=20 2.47.3 From nobody Sun Feb 8 15:25:06 2026 Received: from mail-yw1-f172.google.com (mail-yw1-f172.google.com [209.85.128.172]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5652C24DCEB for ; Sat, 10 Jan 2026 02:19:06 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011562; cv=none; b=ecd3rxlkTqNbIxhfqm23N5og591AAh7wALSbp01gtI+ruJv4Em4E9MeRc3beA8zpffFKFxFYl7T+UhO73RfznewHLukd9q4J8brNeLwj9wvITdO1tlAjBo3W5qk3jnBcMzKh/wIakUlRMbgLsZyAtnUdTP0Z05UA61TBBUFO/zw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768011562; c=relaxed/simple; bh=dy8VSMAomXo21WIjaY0wYi9sSGnjr0Ji79ClfNkKMS0=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=SdhIjTXUY/6rHM+NH5BOTnnDomhDvvtJgObrGAdKiOvs5eZnhrAKoZnI3YwkWdTDKv9Q0zk670SXdcTFN37cSoapb7Gmf0x9OjWBZ2/Mh5dvjqtLw5YjQMVjCcbKV8f8JiLctnmm94jmyBxopjVAOJfvCre6DavWf9CFWzTw5bw= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=dbSdeyIe; arc=none smtp.client-ip=209.85.128.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="dbSdeyIe" Received: by mail-yw1-f172.google.com with SMTP id 00721157ae682-78fba1a1b1eso57253327b3.1 for ; Fri, 09 Jan 2026 18:19:06 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1768011545; x=1768616345; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=rU6cZCgpG9GOAbb+tnZ37tmEGId4jQzirW7dllLFVzU=; b=dbSdeyIeAwAgxNNYNEDkqR8EXlFXsTZ9CREiQJKB5PWtVkDsYqfNVmR7Wb7r0mggPt 0+25HsBymcm0EslWSBUCUm0a3syuNkPm19jvll/ptLCtYwDrAMabAg1hZuspSaDBY6WE TuDZ6o/VO+MjX5oFJg38+IqCnsYrzmPc31Mwvf5UpiLGzkr4fDNq5TYXRITjR6PRaV6J FRnhqUQ7zK4e0aqQpF/Vc7rqfsSvl12OqYwxdAsiDsr2igDtBGTPDi0Zhja7Zug61Xep //mg63YrPzT/sLp81eG7aRzq4eiOOqkfXqGfDHNY1loZWvcgX+lOMslJE5Mpl8dEWCc1 4gKg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1768011545; x=1768616345; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-gg:x-gm-message-state:from:to :cc:subject:date:message-id:reply-to; bh=rU6cZCgpG9GOAbb+tnZ37tmEGId4jQzirW7dllLFVzU=; b=hR3acl/OXqbbMtQ+9u7X1VPkVlLYasqIctUqf+V7TB3Sx32lcyafcDFI+xBalolP8g mTQzQNDdnkyPcOMELQHIVhD5ehxBhGhDdSyp6ofgoGCIKTh1m/BgqBOvOJNPp5aItb7R 9tH9v/0TGWexP5VnMgdWcy8AjxrTz1tjKu6YwSu2bvLEYc24c6eis22Df5NLg1DI657y /D1isbGPKqTrz7Bm4NdQYKxy/k+qKCUe9bhv3OXP8t1I1G6CrB/Zb8OTBJ43Pf4NPyvY 9hy0GVTKCnWtwf2rbIqyuoMzA5GAdcPx/tsIkA4h0QHxD+Vv5Rcs1P4QUIDEOB37SowX vh7w== X-Forwarded-Encrypted: i=1; AJvYcCWfi2VqVhecd9X7SK4Woc77jpamQSELS7fE+yVqA8PXkf6CtbWItJyRaJpmIjjnNV/3HliU1yE6W7tgG6w=@vger.kernel.org X-Gm-Message-State: AOJu0YzHlvlWGCLIxbTku0Iz8KuHGtlyrB7KrX/C2FCG9Kf8+6V2Sa3l KYd8yCHSqiMXRkYlSB901Orb2I54at7PYQ9yrrbs4MM8tMDPUdScnRmT X-Gm-Gg: AY/fxX4ZYVwxEIjxayWDSt+1Up+W+H+X81hBFbnh91W9QjkXJvx/KV9w0Vv9zQJLM4X 6dsjHRQOkC9YdqlHpkUi/yyJfMlR8HepjPOEvYWH9YRPZu5A9Wtz/gelyFY8aU+hzTdA4B6erZf m+auBXCW6RPZ5LcX9T8uJ6/Q8O2SInbrI+HKwFzwAUTM4AbzwA9KVZNZLLtNC227AAKpUzPQ7yt xvs/7y/+TelpVMhY+Xf/asY/zFX4AF/DWc6hMUkaM0e6SdyQ97YJ1bJ14lUA06y4W5jxHcO0+Vq b/NJJ3RdeNe7R/Q5BrFvWXNPkttntXScMtP0uiYU1sNpla1+9Jte+4U83r89cf4h8g2Yf+d7L8v jFnciPipcA16xQ5h7mwhC29kB4TAhoSi7dS199ma3nHrpTKdvDgOzk0mTnKtuOKC6qjfAmhI6QD XM+b/srEia X-Google-Smtp-Source: AGHT+IFqAUeGS3fSoQYRClaCLLvuhBszFYipmE9EIxwk8GX5j0l3xuZmsLsWYJV8IBz3HNxIn50cwg== X-Received: by 2002:a05:690e:b85:b0:641:f5bc:692e with SMTP id 956f58d0204a3-6470d2f4d8emr10686850d50.39.1768011544827; Fri, 09 Jan 2026 18:19:04 -0800 (PST) Received: from localhost ([2a03:2880:25ff:c::]) by smtp.gmail.com with ESMTPSA id 00721157ae682-790aa67999fsm47779197b3.37.2026.01.09.18.19.04 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 09 Jan 2026 18:19:04 -0800 (PST) From: Bobby Eshleman Date: Fri, 09 Jan 2026 18:18:19 -0800 Subject: [PATCH net-next v9 5/5] selftests: drv-net: devmem: add autorelease test Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-5-8042930d00d7@meta.com> References: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> In-Reply-To: <20260109-scratch-bobbyeshleman-devmem-tcp-token-upstream-v9-0-8042930d00d7@meta.com> To: "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Simon Horman , Kuniyuki Iwashima , Willem de Bruijn , Neal Cardwell , David Ahern , Mina Almasry , Arnd Bergmann , Jonathan Corbet , Andrew Lunn , Shuah Khan , Donald Hunter Cc: Stanislav Fomichev , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, asml.silence@gmail.com, matttbe@kernel.org, skhawaja@google.com, Bobby Eshleman X-Mailer: b4 0.14.3 From: Bobby Eshleman Add test case for autorelease. The test case is the same as the RX test, but enables autorelease. The original RX test is changed to use the -a 0 flag to disable autorelease. TAP version 13 1..4 ok 1 devmem.check_rx ok 2 devmem.check_rx_autorelease ok 3 devmem.check_tx ok 4 devmem.check_tx_chunks Signed-off-by: Bobby Eshleman --- Changes in v8: - removed stale/missing tests Changes in v7: - use autorelease netlink - remove sockopt tests --- tools/testing/selftests/drivers/net/hw/devmem.py | 21 +++++++++++++++++++= -- tools/testing/selftests/drivers/net/hw/ncdevmem.c | 19 +++++++++++++------ 2 files changed, 32 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testi= ng/selftests/drivers/net/hw/devmem.py index 45c2d49d55b6..dbe696a445bd 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -25,7 +25,24 @@ def check_rx(cfg) -> None: =20 port =3D rand_port() socat =3D f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind=3D{= cfg.remote_baddr}:{port}" - listen_cmd =3D f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {= port} -c {cfg.remote_addr} -v 7" + listen_cmd =3D f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {= port} -c {cfg.remote_addr} -v 7 -a 0" + + with bkg(listen_cmd, exit_wait=3DTrue) as ncdevmem: + wait_port_listen(port) + cmd(f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | \ + head -c 1K | {socat}", host=3Dcfg.remote, shell=3DTrue) + + ksft_eq(ncdevmem.ret, 0) + + +@ksft_disruptive +def check_rx_autorelease(cfg) -> None: + require_devmem(cfg) + + port =3D rand_port() + socat =3D f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind=3D{= cfg.remote_baddr}:{port}" + listen_cmd =3D f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {= port} \ + -c {cfg.remote_addr} -v 7 -a 1" =20 with bkg(listen_cmd, exit_wait=3DTrue) as ncdevmem: wait_port_listen(port) @@ -68,7 +85,7 @@ def main() -> None: cfg.bin_local =3D path.abspath(path.dirname(__file__) + "/ncdevmem= ") cfg.bin_remote =3D cfg.remote.deploy(cfg.bin_local) =20 - ksft_run([check_rx, check_tx, check_tx_chunks], + ksft_run([check_rx, check_rx_autorelease, check_tx, check_tx_chunk= s], args=3D(cfg, )) ksft_exit() =20 diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/test= ing/selftests/drivers/net/hw/ncdevmem.c index 3288ed04ce08..406f1771d9ec 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -92,6 +92,7 @@ static char *port; static size_t do_validation; static int start_queue =3D -1; static int num_queues =3D -1; +static int devmem_autorelease; static char *ifname; static unsigned int ifindex; static unsigned int dmabuf_id; @@ -679,7 +680,8 @@ static int configure_flow_steering(struct sockaddr_in6 = *server_sin) =20 static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, struct netdev_queue_id *queues, - unsigned int n_queue_index, struct ynl_sock **ys) + unsigned int n_queue_index, struct ynl_sock **ys, + int autorelease) { struct netdev_bind_rx_req *req =3D NULL; struct netdev_bind_rx_rsp *rsp =3D NULL; @@ -695,6 +697,7 @@ static int bind_rx_queue(unsigned int ifindex, unsigned= int dmabuf_fd, req =3D netdev_bind_rx_req_alloc(); netdev_bind_rx_req_set_ifindex(req, ifindex); netdev_bind_rx_req_set_fd(req, dmabuf_fd); + netdev_bind_rx_req_set_autorelease(req, autorelease); __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); =20 rsp =3D netdev_bind_rx(*ys, req); @@ -872,7 +875,8 @@ static int do_server(struct memory_buffer *mem) goto err_reset_rss; } =20 - if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) { + if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys, + devmem_autorelease)) { pr_err("Failed to bind"); goto err_reset_flow_steering; } @@ -1092,7 +1096,7 @@ int run_devmem_tests(void) goto err_reset_headersplit; } =20 - if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) { + if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys, 0)) { pr_err("Binding empty queues array should have failed"); goto err_unbind; } @@ -1108,7 +1112,7 @@ int run_devmem_tests(void) goto err_reset_headersplit; } =20 - if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) { + if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys, 0)) { pr_err("Configure dmabuf with header split off should have failed"); goto err_unbind; } @@ -1124,7 +1128,7 @@ int run_devmem_tests(void) goto err_reset_headersplit; } =20 - if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) { + if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys, 0)) { pr_err("Failed to bind"); goto err_reset_headersplit; } @@ -1397,7 +1401,7 @@ int main(int argc, char *argv[]) int is_server =3D 0, opt; int ret, err =3D 1; =20 - while ((opt =3D getopt(argc, argv, "ls:c:p:v:q:t:f:z:")) !=3D -1) { + while ((opt =3D getopt(argc, argv, "ls:c:p:v:q:t:f:z:a:")) !=3D -1) { switch (opt) { case 'l': is_server =3D 1; @@ -1426,6 +1430,9 @@ int main(int argc, char *argv[]) case 'z': max_chunk =3D atoi(optarg); break; + case 'a': + devmem_autorelease =3D atoi(optarg); + break; case '?': fprintf(stderr, "unknown option: %c\n", optopt); break; --=20 2.47.3