From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B971C2745E; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704142; cv=none; b=Dq2zqzkc92xSL+W9uOeyjF80oPOOAjlglbWxvkbffwMoPv76ZZdd4blaDOruYk/+PbjxeFup9LNYwgHlO0vvwm+Zpn9AmTXJG0E7anZd1uIUNhKDMXPTtULXJFkRqwem30CeeuyXLhaUyJ79sUPW1Fzar+z0w46xdEKAKFYIIYg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704142; c=relaxed/simple; bh=poRenvYc2UJwmpUd+sGYuOxBqoO2KziJseV7+TelkSo=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=ltpJtw9GRME3ouIFFxN3q4CcA6YnuVI2cny0A5+ZbJmVaMomRb2o0eZJ42ON66ZlZ1myIpUhKXk+/KzpQvhDopPXlVkfCK9BfHnWtG/DSM2gvbIBMZGsj42EHessCNDju1yWJRy2qXUSfKxuu6kGJrzvq4PBinJfg/lGrvCQmmk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=BGnX24KV; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="BGnX24KV" Received: by smtp.kernel.org (Postfix) with ESMTPS id 57D18C2BCC6; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=poRenvYc2UJwmpUd+sGYuOxBqoO2KziJseV7+TelkSo=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=BGnX24KVv3TdjWNe2/0afNFiR+pnQwMZ8K1Ta92Afx9DdVrmUh2YkBxz+cVaOHsK0 bLg02Kv+OVxBvq0G4cXhD+WtyliXMOJ4s1rPVdcoAviXm3MIDnio3KU6JvX7hscH4U K6hPwLzUt86ZVD8/xhMgOvFxryXq49NdmgoDKhtpI8HVYPdXoutaIvHfDe6j9i/GJo zfzG52fJKlwYXKPYAp8ungVIjfNqj1P6DFquC5Aao/9U2bXSmv8AMdr0MUya2P+trh 5IBVXo88wQUD2uESXB+kbTwrubZaqLdVkxsTyP9TjyGvFGl4d2RH0wT8i/ZXftV0kx 3kgztN9xV7eNQ== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 4273CCD6E7E; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:04 -0500 Subject: [PATCH v3 01/23] PCI: Add SNIA SDXI accelerator sub-class 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: <20260605-sdxi-base-v3-1-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=1441; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=OwdioeWEQcxJLVaFYqBTlKzpo10yCo7NwekOCC/At7U=; b=9kwewPyVlVZHqx4QMSTGgh3csIXnMQl80YqCwZI/mMFGfRce66vPzr9fMKonYJTZ4LK5wOWLE v68SjNI/wN/CieUMRBpaR1/FmLqdFSFWRFU4a6449acS3/mpBWJ3V+A X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Make the class code for SNIA Smart Data Accelerator Interface (SDXI) functions available to both C and Rust code. See PCI Code and ID Assignment spec r1.14, sec 1.19. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- include/linux/pci_ids.h | 1 + rust/kernel/pci/id.rs | 1 + 2 files changed, 2 insertions(+) diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 24cb42f66e4b..83ab3f27eb5a 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -154,6 +154,7 @@ =20 #define PCI_BASE_CLASS_ACCELERATOR 0x12 #define PCI_CLASS_ACCELERATOR_PROCESSING 0x1200 +#define PCI_CLASS_ACCELERATOR_SDXI 0x120100 =20 #define PCI_CLASS_OTHERS 0xff =20 diff --git a/rust/kernel/pci/id.rs b/rust/kernel/pci/id.rs index 50005d176561..d5e006cd6641 100644 --- a/rust/kernel/pci/id.rs +++ b/rust/kernel/pci/id.rs @@ -292,6 +292,7 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Resul= t { SP_OTHER =3D bindings::PCI_CLASS_SP_OTHER, = // 0x118000 =20 ACCELERATOR_PROCESSING =3D bindings::PCI_CLASS_ACCELERATOR_PROCESS= ING, // 0x120000 + ACCELERATOR_SDXI =3D bindings::PCI_CLASS_ACCELERATOR_SDXI, = // 0x120100 =20 OTHERS =3D bindings::PCI_CLASS_OTHERS, = // 0xff0000 } --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B96F1CA4E; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704142; cv=none; b=MLzTJqK/8ql3I7zhS9bf/X7+VZHLQMlQ2I3tLite9O58DO5q17vI1MvivKqd7PZQQcroztIR89XtgRwDa3j9z+cbULrDbrGplFQXyUM4k0GndgwHu1+IyuYE8CVBGs1yd3bU3mJ7cjnwYKpIx8QfCCc9O+kFPA77HvbRhkFE53M= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704142; c=relaxed/simple; bh=qPK6UugunlFMoeP+8P0TP368mHmANW2O2gkSeilG6ro=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=Txj7ZirS32cf+x1R+yxFQM+Cey9j/gWcNrf5F6iXnwkXh3DFQpw/2UVIRpFpB8K0VmoVl6DrfMlTiLZl/eh/vyWM/FquVmh0TAYOvGFNOs3Jw3RhQwuZIpsKhebvfMIfD03JRcm5b7OIh9CpJbRwW1hRX6W8iE2MhZZjMby7hGw= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=TT9QC63R; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="TT9QC63R" Received: by smtp.kernel.org (Postfix) with ESMTPS id 67624C2BCB9; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=qPK6UugunlFMoeP+8P0TP368mHmANW2O2gkSeilG6ro=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=TT9QC63RcKXz1TtSzUFEyriyQkCtgaSFqRUYqofm1XH7qbUULRutigu+ZIcuVVwKM snu+ur5gEYEgrHZGp6LBcqlBvTW1CQanvnfSH0WPfB/VNPCsBXlCDT2cY/y385nS+7 nXB/YjhJ/PT8hwAmLwy8YZFIfWDEDRygP9XJQsLYaCT7JgOgpcrpMT+aKn0e/ko5UD IIYUJDgtzbFbT8Z25y7MD/5DuPxO9bv6CCMY4yjug1AjqioP0072CGttk8MgEo7SCX QtDOMnIXFhDhx1o58KLHFCKhLSiFzIGwoVsjQwiDQiMxsmzRFRNSXnpa0j9rjMXm5p 6BMokn8rGlJkg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5409BCD8C81; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:05 -0500 Subject: [PATCH v3 02/23] MAINTAINERS: Add entry for SDXI driver 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: <20260605-sdxi-base-v3-2-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=957; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=J7ULZm7Owlmcwbz490UgcmZhmtYpI8wOv94ro2VxLk4=; b=WY+9ghD8czK1AZnfW98i2DKmNdOXlXJaTHLTMGbV8TXdLxgVU2hnEjgwN18KwehyF1v0a6Rht 16DdXEBUB8lCRJytULgwXZfqJbXBhTjMipy+VA7o2S0htC4SPtE3ufK X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Add an entry for the SDXI driver to MAINTAINERS. Wei and I will maintain the driver. The SDXI specification and other materials may be found at: https://www.snia.org/sdxi Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 2fb1c75afd16..5c6d175a3f42 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -24036,6 +24036,13 @@ L: sdricohcs-devel@lists.sourceforge.net (subscrib= ers-only) S: Maintained F: drivers/mmc/host/sdricoh_cs.c =20 +SDXI (Smart Data Accelerator Interface) DRIVER +M: Nathan Lynch +M: Wei Huang +L: dmaengine@vger.kernel.org +S: Supported +F: drivers/dma/sdxi/ + SECO BOARDS CEC DRIVER M: Ettore Chimenti S: Maintained --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B96AF64; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704142; cv=none; b=mFFGAcl34l6vwEo7bKzzwcUxVSm17w2Xi1c7dm4h1t7+lp9M8ilfLYSkSBJU6QYQ5fUlmxQXMaJOzxXNcfCzeNmiNmUhYKVhXjf1esY3ka6zrYBNlqgKMX6MCo1Ji5COpHjZo7gw7lnRnbWEcf8SNbnGH74o2wRHHPXDLfJD/bM= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704142; c=relaxed/simple; bh=sOAB8FquBY7jrHJW7M3Or3hi1sUAHq+p1Pl4iW3yR4U=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=aWIXLAu2B3jvmc5Ei2exYaRtof/ySTz7QkD34fYLm83nwg1DvW2nAGZ6i4Cw5e3B/SL7m3uvYKHqkL0UORtsP84mCqxN2FzojHKOXbWjO05mTkS9hVuno6iKofWjrTG2stVYm7tKziM8Qj6q4tRCTHYfyRx28PhP/NFVWjX2doU= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=B8+rTFXA; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="B8+rTFXA" Received: by smtp.kernel.org (Postfix) with ESMTPS id 735E2C4AF09; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=sOAB8FquBY7jrHJW7M3Or3hi1sUAHq+p1Pl4iW3yR4U=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=B8+rTFXA8oPeHPbMT57VeUqp4/DFXqVL/XvEEHvT5449IOIPu/4Xgc6VERqbmo8Ku JeBX+ISW0hZRW0IoIGOBbSN3lzoohURUa3POADtSwIsfiJuesZ9Gqw0VjrXDJqhkhF TkVqnNCHXwDENuE74+uOv8qG/7hqhcTfU+oL7tmiDS2tzPZMKXIgMmUw8Y9moKQMeD Zr/Xzx0NPeH5c4CGM4OSPq2H3F97kNm46tOBeyAC6S3MFQ/Rez0UvNnfFImGa9GDrL LiYZS/JC+MZT86Qm7V6CWyV4pLAzvBISzM5/jNv5ewSfvBW7hGzADlghbMikqFAaXb 6O1Bt5jJ1kXWg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 64D52CD6E7B; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:06 -0500 Subject: [PATCH v3 03/23] dmaengine: sdxi: Add PCI initialization 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: <20260605-sdxi-base-v3-3-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=8020; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=BQZvxuDditz9IitbnDyUmKk8ltcT1WRXb6dWdWsUaGw=; b=9a5D3vEH+NkB7ShoIgfSvfFWXtouG9i5xbvR2GnjIbyDoNj3PQej2PGz/HEtgZUj9OQ6Ilkyi CfV+NkOQIpAABNbpciefnZsYnxeg9ALmsPisoz2BaU8ByyXkvBc14/b X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Add enough code to bind a SDXI device via the class code and map its control registers and doorbell region. All device resources are managed with devres at this point, so there is no explicit teardown path. While the SDXI specification includes a PCIe binding, the standard is intended to be independent of the underlying I/O interconnect. So the driver confines PCI-specific code to pci.c, and the rest (such as device.c, introduced here) is bus-agnostic. Hence there is some indirection: during probe, the bus code registers any matched device with the generic SDXI core, supplying the device and a sdxi_bus_ops vector. After the core associates a new sdxi_dev with the device, bus-specific initialization proceeds via the sdxi_bus_ops->init() callback. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/Kconfig | 2 ++ drivers/dma/Makefile | 1 + drivers/dma/sdxi/Kconfig | 28 ++++++++++++++++ drivers/dma/sdxi/Makefile | 6 ++++ drivers/dma/sdxi/device.c | 33 +++++++++++++++++++ drivers/dma/sdxi/pci.c | 84 +++++++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/sdxi.h | 38 +++++++++++++++++++++ 7 files changed, 192 insertions(+) diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index ae6a682c9f76..3d89284e7cf8 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -762,6 +762,8 @@ source "drivers/dma/lgm/Kconfig" =20 source "drivers/dma/loongson/Kconfig" =20 +source "drivers/dma/sdxi/Kconfig" + source "drivers/dma/stm32/Kconfig" =20 # clients diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 14aa086629d5..069bba1d26c7 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_XGENE_DMA) +=3D xgene-dma.o obj-$(CONFIG_ST_FDMA) +=3D st_fdma.o obj-$(CONFIG_FSL_DPAA2_QDMA) +=3D fsl-dpaa2-qdma/ obj-$(CONFIG_INTEL_LDMA) +=3D lgm/ +obj-$(CONFIG_SDXI_CORE) +=3D sdxi/ =20 obj-y +=3D amd/ obj-y +=3D loongson/ diff --git a/drivers/dma/sdxi/Kconfig b/drivers/dma/sdxi/Kconfig new file mode 100644 index 000000000000..b91b44231a04 --- /dev/null +++ b/drivers/dma/sdxi/Kconfig @@ -0,0 +1,28 @@ +config SDXI_CORE + tristate "SDXI (Smart Data Accelerator Interface) support" + # Doorbell updates require naturally-aligned 64-bit writes, per + # SDXI 1.0 9 MMIO Control Registers. + depends on 64BIT + select DMA_ENGINE + help + Enable support for Smart Data Accelerator Interface (SDXI) + Platform Data Mover devices. SDXI is a vendor-neutral + standard for a memory-to-memory data mover and acceleration + interface. + + This option is automatically selected by the SDXI PCI driver. + Enable it manually if you want to build the SDXI core for unit + testing without enabling the PCI driver. + + To compile this driver as a module, choose M here: the module + will be named "sdxi-core". + +config SDXI_PCI + tristate "SDXI (Smart Data Accelerator Interface) PCI driver" + depends on PCI_MSI && 64BIT + select SDXI_CORE + help + Enable support for PCI-hosted SDXI devices. + + To compile this driver as a module, choose M here: the module + will be named "sdxi-pci". diff --git a/drivers/dma/sdxi/Makefile b/drivers/dma/sdxi/Makefile new file mode 100644 index 000000000000..0006edf74d86 --- /dev/null +++ b/drivers/dma/sdxi/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_SDXI_CORE) +=3D sdxi-core.o +sdxi-core-y :=3D device.o + +obj-$(CONFIG_SDXI_PCI) +=3D sdxi-pci.o +sdxi-pci-y :=3D pci.o diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c new file mode 100644 index 000000000000..0974a83bb45c --- /dev/null +++ b/drivers/dma/sdxi/device.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI hardware device driver + * + * Copyright Advanced Micro Devices, Inc. + */ + +#include +#include +#include + +#include "sdxi.h" + +int sdxi_register(struct device *dev, const struct sdxi_bus_ops *ops) +{ + struct sdxi_dev *sdxi; + + sdxi =3D devm_kzalloc(dev, sizeof(*sdxi), GFP_KERNEL); + if (!sdxi) + return -ENOMEM; + + sdxi->dev =3D dev; + sdxi->bus_ops =3D ops; + dev_set_drvdata(dev, sdxi); + + return sdxi->bus_ops->init(sdxi); +} +EXPORT_SYMBOL_NS_GPL(sdxi_register, "SDXI"); + +MODULE_AUTHOR("Wei Huang"); +MODULE_AUTHOR("Nathan Lynch"); +MODULE_DESCRIPTION("SDXI core"); +MODULE_LICENSE("GPL"); diff --git a/drivers/dma/sdxi/pci.c b/drivers/dma/sdxi/pci.c new file mode 100644 index 000000000000..42e8af008b10 --- /dev/null +++ b/drivers/dma/sdxi/pci.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI PCI device code + * + * Copyright Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "sdxi.h" + +enum sdxi_mmio_bars { + SDXI_PCI_BAR_CTL_REGS =3D 0, + SDXI_PCI_BAR_DOORBELL =3D 2, +}; + +static struct pci_dev *sdxi_to_pci_dev(const struct sdxi_dev *sdxi) +{ + return to_pci_dev(sdxi->dev); +} + +static int sdxi_pci_init(struct sdxi_dev *sdxi) +{ + struct pci_dev *pdev =3D sdxi_to_pci_dev(sdxi); + struct device *dev =3D &pdev->dev; + int ret; + + ret =3D pcim_enable_device(pdev); + if (ret) + return dev_err_probe(dev, ret, "failed to enable device\n"); + + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + + sdxi->ctrl_regs =3D pcim_iomap_region(pdev, SDXI_PCI_BAR_CTL_REGS, + KBUILD_MODNAME); + if (IS_ERR(sdxi->ctrl_regs)) + return dev_err_probe(dev, PTR_ERR(sdxi->ctrl_regs), + "failed to map control registers\n"); + + sdxi->dbs =3D pcim_iomap_region(pdev, SDXI_PCI_BAR_DOORBELL, + KBUILD_MODNAME); + if (IS_ERR(sdxi->dbs)) + return dev_err_probe(dev, PTR_ERR(sdxi->dbs), + "failed to map doorbell region\n"); + + pci_set_master(pdev); + return 0; +} + +static const struct sdxi_bus_ops sdxi_pci_ops =3D { + .init =3D sdxi_pci_init, +}; + +static int sdxi_pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + return sdxi_register(&pdev->dev, &sdxi_pci_ops); +} + +static const struct pci_device_id sdxi_id_table[] =3D { + { PCI_DEVICE_CLASS(PCI_CLASS_ACCELERATOR_SDXI, 0xffffff) }, + { } +}; +MODULE_DEVICE_TABLE(pci, sdxi_id_table); + +static struct pci_driver sdxi_driver =3D { + .name =3D "sdxi", + .id_table =3D sdxi_id_table, + .probe =3D sdxi_pci_probe, + .sriov_configure =3D pci_sriov_configure_simple, +}; + +MODULE_IMPORT_NS("SDXI"); +MODULE_AUTHOR("Wei Huang"); +MODULE_AUTHOR("Nathan Lynch"); +MODULE_DESCRIPTION("SDXI PCIe interface driver"); +MODULE_LICENSE("GPL"); +module_pci_driver(sdxi_driver); diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h new file mode 100644 index 000000000000..d4c61ca2f875 --- /dev/null +++ b/drivers/dma/sdxi/sdxi.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * SDXI device driver header + * + * Copyright Advanced Micro Devices, Inc. + */ + +#ifndef DMA_SDXI_H +#define DMA_SDXI_H + +#include +#include + +struct sdxi_dev; + +/** + * struct sdxi_bus_ops - Bus-specific methods for SDXI devices. + */ +struct sdxi_bus_ops { + /** + * @init: Map control registers and doorbell region, allocate + * IRQ ranges. Invoked before bus-agnostic SDXI + * function initialization. + */ + int (*init)(struct sdxi_dev *sdxi); +}; + +struct sdxi_dev { + struct device *dev; + void __iomem *ctrl_regs; /* virt addr of ctrl registers */ + void __iomem *dbs; /* virt addr of doorbells */ + + const struct sdxi_bus_ops *bus_ops; +}; + +int sdxi_register(struct device *dev, const struct sdxi_bus_ops *ops); + +#endif /* DMA_SDXI_H */ --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id BC46F3A1B5; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704142; cv=none; b=lXuiCK7kYIm0row9C7WOH54MoYjdHvWQIzG33NUh8sPfw4TFb5v5vQZOe4m2GUdzwXRfr+nURLLXzSR6G00JLnafTt2a5HHYehYc0/qdNRDvkfI+W4N8ojBVhlW7j+jXdXoeO7HHfleOQtE0xeQ8igjPcad4dUleJ94pxZGuOdE= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704142; c=relaxed/simple; bh=foTVdj1xR36i1v4eaSphs78f9nNYMPQaV23iQF8PWZc=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=i6rwyu/YOjGQHOqxyz+wx+QkyXUZu+aAol9R/yVm7PduTywKRIH6qF/m81EWp45GKovr0246JCnY6AY6tF6ZViaUJJVJ/xt/UrVLBXhUh5Gtc7AOPKux4oULkBk148GAzZSSFotryQ+nS7l0W6FAeSp0byOq9Wv4UrE9twix6Xs= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=eDJbyknj; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="eDJbyknj" Received: by smtp.kernel.org (Postfix) with ESMTPS id 7F6D7C2BCFD; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=foTVdj1xR36i1v4eaSphs78f9nNYMPQaV23iQF8PWZc=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=eDJbyknjwtvck0LgyJ9xnB8Xpg8t8oj+bdjDFK5kz+32nLyg+yWswu7bwRHzm6kHt X+WoDnokmaziZpinNHQQPsw6RlHTXP8jbS4hD2DZG1gyAhx4kIZpDdVffVQ6EsRgq3 v+h0C8ZMnmMQQZjnUcQOFGbnOgtSroWnsQMwwyxI2BkydaqaLRoZqqifaE4/QKslHK VJjY3XVqG1+Wk6nj9AeXWgAbGqXbEluKJ6wWdily4Frlq1bYQisOHsqB3bpIiu2znE hwtGrscTGg+dGwf3HFiwqZ7bPyaEocZwK8H82/FFYe/3kxtXoEgKECmJMGF+BlIjpo GHUBBZZJ5Igag== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 75188CD8C87; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:07 -0500 Subject: [PATCH v3 04/23] dmaengine: sdxi: Feature discovery and initial configuration 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: <20260605-sdxi-base-v3-4-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=10221; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=Y+e5uc6mpl40amHjM2bcjORW4MJ8LG/xiu061nroTCg=; b=79DYquEvcvKl0HuU0FpiwfRuASwzlqFkU+RtzH4TrFVc5qjA24st9Ns0yG0+XuXn5zmUFoeQk 8BZXM2Ub9O0DBMKriQnQvZUqg7RbmfoB0AlsxZTz21SHYR7wo0WV2vr X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Discover via the capability registers the doorbell region stride, the maximum supported context ID, the operation groups implemented, and limits on buffer and control structure sizes. The driver has the option of writing more conservative limits to the ctl2 register, but it uses those supplied by the implementation for now. Introduce device register definitions and associated masks via mmio.h. Add convenience wrappers which are first used here: - sdxi_read64() - sdxi_write64() Report the version of the standard to which the device conforms, e.g. sdxi 0000:00:03.0: SDXI 1.0 device found After bus-specific initialization, force the SDXI function to stopped state. This is the expected state from reset, but kexec or driver bugs can leave a function in other states from which the initialization code must be able to recover. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/device.c | 178 ++++++++++++++++++++++++++++++++++++++++++= +++- drivers/dma/sdxi/mmio.h | 54 ++++++++++++++ drivers/dma/sdxi/sdxi.h | 19 +++++ 3 files changed, 250 insertions(+), 1 deletion(-) diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index 0974a83bb45c..7c6652f9c3c0 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -5,15 +5,187 @@ * Copyright Advanced Micro Devices, Inc. */ =20 +#include +#include #include #include +#include +#include #include +#include =20 +#include "mmio.h" #include "sdxi.h" =20 +enum sdxi_fn_gsv { + SDXI_GSV_STOP =3D 0, + SDXI_GSV_INIT =3D 1, + SDXI_GSV_ACTIVE =3D 2, + SDXI_GSV_STOPG_SF =3D 3, + SDXI_GSV_STOPG_HD =3D 4, + SDXI_GSV_ERROR =3D 5, +}; + +static const char *const gsv_strings[] =3D { + [SDXI_GSV_STOP] =3D "stopped", + [SDXI_GSV_INIT] =3D "initializing", + [SDXI_GSV_ACTIVE] =3D "active", + [SDXI_GSV_STOPG_SF] =3D "soft stopping", + [SDXI_GSV_STOPG_HD] =3D "hard stopping", + [SDXI_GSV_ERROR] =3D "error", +}; + +static const char *gsv_str(enum sdxi_fn_gsv gsv) +{ + if ((size_t)gsv < ARRAY_SIZE(gsv_strings)) + return gsv_strings[(size_t)gsv]; + + WARN_ONCE(1, "unexpected gsv %u\n", gsv); + + return "unknown"; +} + +enum sdxi_fn_gsr { + SDXI_GSRV_RESET =3D 0, + SDXI_GSRV_STOP_SF =3D 1, + SDXI_GSRV_STOP_HD =3D 2, + SDXI_GSRV_ACTIVE =3D 3, +}; + +static enum sdxi_fn_gsv sdxi_dev_gsv(const struct sdxi_dev *sdxi) +{ + u64 sts0 =3D sdxi_read64(sdxi, SDXI_MMIO_STS0); + enum sdxi_fn_gsv gsv =3D FIELD_GET(SDXI_MMIO_STS0_FN_GSV, sts0); + + switch (gsv) { + case SDXI_GSV_STOP ... SDXI_GSV_ERROR: + break; + default: + dev_warn_ratelimited(sdxi->dev, "unknown gsv %u\n", gsv); + break; + } + + return gsv; +} + +static const unsigned long gsv_poll_interval_us =3D USEC_PER_MSEC; +static const unsigned long gsv_transition_timeout_us =3D USEC_PER_SEC; + +#define sdxi_dev_gsv_poll(sdxi, val, cond) \ + read_poll_timeout(sdxi_dev_gsv, val, cond, gsv_poll_interval_us, \ + gsv_transition_timeout_us, false, sdxi) + +static void sdxi_write_fn_gsr(struct sdxi_dev *sdxi, enum sdxi_fn_gsr cmd) +{ + u64 ctl0 =3D sdxi_read64(sdxi, SDXI_MMIO_CTL0); + + FIELD_MODIFY(SDXI_MMIO_CTL0_FN_GSR, &ctl0, cmd); + sdxi_write64(sdxi, SDXI_MMIO_CTL0, ctl0); +} + +/* Get the device to the GSV_STOP state. */ +static int sdxi_dev_stop(struct sdxi_dev *sdxi) +{ + enum sdxi_fn_gsv status =3D sdxi_dev_gsv(sdxi); + int ret; + + dev_dbg(sdxi->dev, "attempting stop, current state: %s\n", + gsv_str(status)); + + switch (status) { + case SDXI_GSV_INIT: + case SDXI_GSV_ACTIVE: + sdxi_write_fn_gsr(sdxi, SDXI_GSRV_STOP_SF); + break; + case SDXI_GSV_STOPG_SF: + sdxi_write_fn_gsr(sdxi, SDXI_GSRV_STOP_HD); + break; + case SDXI_GSV_STOPG_HD: + case SDXI_GSV_ERROR: + /* + * If hard-stopping, there's nothing to do but wait. + * If in error state, the reset is issued below. + */ + break; + default: + /* Unrecognized state; try a reset. */ + sdxi_write_fn_gsr(sdxi, SDXI_GSRV_RESET); + break; + } + + /* Wait for transition to either stop or error state. */ + ret =3D sdxi_dev_gsv_poll(sdxi, status, + status =3D=3D SDXI_GSV_STOP || + status =3D=3D SDXI_GSV_ERROR); + + if (ret =3D=3D 0 && status =3D=3D SDXI_GSV_ERROR) { + sdxi_write_fn_gsr(sdxi, SDXI_GSRV_RESET); + ret =3D sdxi_dev_gsv_poll(sdxi, status, status =3D=3D SDXI_GSV_STOP); + } + + if (ret) { + dev_err(sdxi->dev, "stop timed out, current state: %s\n", + gsv_str(status)); + return ret; + } + + return 0; +} + +/* + * See SDXI 1.0 4.1.8 Activation of the SDXI Function by Software. + */ +static int sdxi_fn_activate(struct sdxi_dev *sdxi) +{ + u64 version, cap0, cap1, ctl0, ctl2; + int err; + + /* + * Ensure the function is in GSV_STOP state, then clear ctl0's + * pasid and error interrupt configuration while preserving + * any assigned group ID (fn_grp_id). + */ + err =3D sdxi_dev_stop(sdxi); + if (err) + return err; + + ctl0 =3D sdxi_read64(sdxi, SDXI_MMIO_CTL0); + FIELD_MODIFY(SDXI_MMIO_CTL0_FN_ERR_INTR_EN, &ctl0, 0); + FIELD_MODIFY(SDXI_MMIO_CTL0_FN_PASID_VL, &ctl0, 0); + FIELD_MODIFY(SDXI_MMIO_CTL0_FN_PASID, &ctl0, 0); + sdxi_write64(sdxi, SDXI_MMIO_CTL0, ctl0); + + version =3D sdxi_read64(sdxi, SDXI_MMIO_VERSION); + dev_info(sdxi->dev, "SDXI %llu.%llu device found\n", + FIELD_GET(SDXI_MMIO_VERSION_MAJOR, version), + FIELD_GET(SDXI_MMIO_VERSION_MINOR, version)); + + /* Read capabilities and features. */ + cap0 =3D sdxi_read64(sdxi, SDXI_MMIO_CAP0); + sdxi->db_stride =3D SZ_4K; + sdxi->db_stride *=3D 1U << FIELD_GET(SDXI_MMIO_CAP0_DB_STRIDE, cap0); + + cap1 =3D sdxi_read64(sdxi, SDXI_MMIO_CAP1); + sdxi->op_grp_cap =3D FIELD_GET(SDXI_MMIO_CAP1_OPB_000_CAP, cap1); + sdxi->max_cxtid =3D FIELD_GET(SDXI_MMIO_CAP1_MAX_CXT, cap1); + + /* Apply our configuration. */ + ctl2 =3D FIELD_PREP(SDXI_MMIO_CTL2_MAX_CXT, sdxi->max_cxtid); + ctl2 |=3D FIELD_PREP(SDXI_MMIO_CTL2_MAX_BUFFER, + FIELD_GET(SDXI_MMIO_CAP1_MAX_BUFFER, cap1)); + ctl2 |=3D FIELD_PREP(SDXI_MMIO_CTL2_MAX_AKEY_SZ, + FIELD_GET(SDXI_MMIO_CAP1_MAX_AKEY_SZ, cap1)); + ctl2 |=3D FIELD_PREP(SDXI_MMIO_CTL2_OPB_000_AVL, + FIELD_GET(SDXI_MMIO_CAP1_OPB_000_CAP, cap1)); + sdxi_write64(sdxi, SDXI_MMIO_CTL2, ctl2); + + return 0; +} + int sdxi_register(struct device *dev, const struct sdxi_bus_ops *ops) { struct sdxi_dev *sdxi; + int err; =20 sdxi =3D devm_kzalloc(dev, sizeof(*sdxi), GFP_KERNEL); if (!sdxi) @@ -23,7 +195,11 @@ int sdxi_register(struct device *dev, const struct sdxi= _bus_ops *ops) sdxi->bus_ops =3D ops; dev_set_drvdata(dev, sdxi); =20 - return sdxi->bus_ops->init(sdxi); + err =3D sdxi->bus_ops->init(sdxi); + if (err) + return err; + + return sdxi_fn_activate(sdxi); } EXPORT_SYMBOL_NS_GPL(sdxi_register, "SDXI"); =20 diff --git a/drivers/dma/sdxi/mmio.h b/drivers/dma/sdxi/mmio.h new file mode 100644 index 000000000000..f07e857691b9 --- /dev/null +++ b/drivers/dma/sdxi/mmio.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * SDXI MMIO register offsets and layouts. + * + * Copyright Advanced Micro Devices, Inc. + */ + +#ifndef DMA_SDXI_MMIO_H +#define DMA_SDXI_MMIO_H + +#include + +enum sdxi_reg { + /* SDXI 1.0 9.1 General Control and Status Registers */ + SDXI_MMIO_CTL0 =3D 0x00000, + SDXI_MMIO_CTL2 =3D 0x00010, + SDXI_MMIO_STS0 =3D 0x00100, + SDXI_MMIO_CAP0 =3D 0x00200, + SDXI_MMIO_CAP1 =3D 0x00208, + SDXI_MMIO_VERSION =3D 0x00210, +}; + +/* SDXI 1.0 Table 9-2: MMIO_CTL0 */ +#define SDXI_MMIO_CTL0_FN_GSR GENMASK_ULL(1, 0) +#define SDXI_MMIO_CTL0_FN_PASID_VL BIT_ULL(2) +#define SDXI_MMIO_CTL0_FN_ERR_INTR_EN BIT_ULL(4) +#define SDXI_MMIO_CTL0_FN_PASID GENMASK_ULL(27, 8) + +/* SDXI 1.0 Table 9-4: MMIO_CTL2 */ +#define SDXI_MMIO_CTL2_MAX_BUFFER GENMASK_ULL(3, 0) +#define SDXI_MMIO_CTL2_MAX_AKEY_SZ GENMASK_ULL(15, 12) +#define SDXI_MMIO_CTL2_MAX_CXT GENMASK_ULL(31, 16) +#define SDXI_MMIO_CTL2_OPB_000_AVL GENMASK_ULL(63, 32) + +/* SDXI 1.0 Table 9-5: MMIO_STS0 */ +#define SDXI_MMIO_STS0_FN_GSV GENMASK_ULL(2, 0) + +/* SDXI 1.0 Table 9-6: MMIO_CAP0 */ +#define SDXI_MMIO_CAP0_SFUNC GENMASK_ULL(15, 0) +#define SDXI_MMIO_CAP0_DB_STRIDE GENMASK_ULL(22, 20) +#define SDXI_MMIO_CAP0_MAX_DS_RING_SZ GENMASK_ULL(28, 24) + +/* SDXI 1.0 Table 9-7: MMIO_CAP1 */ +#define SDXI_MMIO_CAP1_MAX_BUFFER GENMASK_ULL(3, 0) +#define SDXI_MMIO_CAP1_MAX_AKEY_SZ GENMASK_ULL(15, 12) +#define SDXI_MMIO_CAP1_MAX_CXT GENMASK_ULL(31, 16) +#define SDXI_MMIO_CAP1_OPB_000_CAP GENMASK_ULL(63, 32) + +/* SDXI 1.0 Table 9-8: MMIO_VERSION */ +#define SDXI_MMIO_VERSION_MINOR GENMASK_ULL(7, 0) +#define SDXI_MMIO_VERSION_MAJOR GENMASK_ULL(23, 16) + +#endif /* DMA_SDXI_MMIO_H */ diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h index d4c61ca2f875..721abf7556d1 100644 --- a/drivers/dma/sdxi/sdxi.h +++ b/drivers/dma/sdxi/sdxi.h @@ -9,8 +9,12 @@ #define DMA_SDXI_H =20 #include +#include +#include #include =20 +#include "mmio.h" + struct sdxi_dev; =20 /** @@ -30,9 +34,24 @@ struct sdxi_dev { void __iomem *ctrl_regs; /* virt addr of ctrl registers */ void __iomem *dbs; /* virt addr of doorbells */ =20 + /* hardware capabilities (from cap0 & cap1) */ + u32 db_stride; /* doorbell stride in bytes */ + u16 max_cxtid; /* Maximum context ID allowed. */ + u32 op_grp_cap; /* supported operation group cap */ + const struct sdxi_bus_ops *bus_ops; }; =20 int sdxi_register(struct device *dev, const struct sdxi_bus_ops *ops); =20 +static inline u64 sdxi_read64(const struct sdxi_dev *sdxi, enum sdxi_reg r= eg) +{ + return readq(sdxi->ctrl_regs + reg); +} + +static inline void sdxi_write64(struct sdxi_dev *sdxi, enum sdxi_reg reg, = u64 val) +{ + writeq(val, sdxi->ctrl_regs + reg); +} + #endif /* DMA_SDXI_H */ --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E04AD13B584; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=VtMddG0BwcLHBVjuInnBsuFTg94471olcB7X8QWvv/xKBAvbVaOA6h6Wwmv2LRcyoqDsjcT7e6xASFNkTCT3BPaMVJzAJXaQfWplZ+yi1tJkvFB/nHcvsTHa8TK6ltxZ2XnE5AKppDHRz5jtWcqg3envh0rRvF0x1Q+hFrGsD4Y= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=ZZu0V+rPqT/izsujMkzSmey3aT2Uzj0hjyU/K3uhP+M=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=kSxyUeo/mYbhjy4AWbkSt6WroBcoOfHx3RSLFN7/QAfu/5yNrx7LL3l8KOLrhFef1BOL/DsGUpdwJWJx7vXkiBk9RflAvR9h+8jVrsucMca/DdA6CBnxa0kgTjoTbuaJdpOEqoa+n4grCB8/br/YAR+vgHTPwZqh5yN+MG5V2Fk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=NkOoyPtz; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="NkOoyPtz" Received: by smtp.kernel.org (Postfix) with ESMTPS id 8C2CBC2BD00; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=ZZu0V+rPqT/izsujMkzSmey3aT2Uzj0hjyU/K3uhP+M=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=NkOoyPtz8QKXIxh92SlUlV3fgsbI6e5MLZZy20UEsNKqPUKfH05HMM6f84sb/ZiSi 0GqougSaawt3buCxor8U8SebakiZ7C5cNPfqkhfEVJPitOPieTXgjDXE1Ic4BrCFoQ bgn47GLGIfXjUQu9hcGuVCNNXLmndRHi1cTL578DDn0EfhxWkgtbvMQrVt8Od8l9pl nRLX3kchlsX611OVYWiQ1HNofdzxm2CumaKL+G4S6btEM16jPqlhYXPB82JBgAWgT2 3XYbtl2UQPo1Ocu1W2aBXx9IPaSzi4pTPS3Uyd8kibJhc5SNcUqXwXAqkpe+TcqY1q PzT9EOUfCgL7Q== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 856CFCD6E7C; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:08 -0500 Subject: [PATCH v3 05/23] dmaengine: sdxi: Configure context tables 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: <20260605-sdxi-base-v3-5-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=6949; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=5rNo0yGohn4V12ghAWHnkY5gG1afoq9X/n+k0EuQ2A4=; b=DIt55UdMe7H1pZIZj69yTIaSIDYB5rLbtl3XjeyXITY+QSnL9HbRQq1s6VMbezBHrCQTxG9uq rMJO7GdRoq7AXQa3Ddi1Pcm2DhL4eYYiPmoka7YGxdtHnGep7DQnPh6 X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch SDXI uses a two-level table hierarchy to track contexts. There is a single level 2 table per function which enumerates up to 512 level 1 tables. Each level 1 table enumerates up to 128 contexts. Allocate and install the L2 table and a single L1 table, enough for context IDs 0-127 (i.e. the admin context with reserved id 0, plus 127 client contexts). For now, to avoid dynamic management of additional L1 tables, cap ctl2.max_cxt to 127. Since the table allocations are devres-managed, there is no corresponding cleanup code required. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/device.c | 40 +++++++++++++++++++++++++++++-- drivers/dma/sdxi/hw.h | 61 +++++++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/mmio.h | 6 +++++ drivers/dma/sdxi/sdxi.h | 5 ++++ 4 files changed, 110 insertions(+), 2 deletions(-) diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index 7c6652f9c3c0..fa5e27a4190e 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -8,12 +8,15 @@ #include #include #include +#include #include #include #include +#include #include #include =20 +#include "hw.h" #include "mmio.h" #include "sdxi.h" =20 @@ -137,7 +140,8 @@ static int sdxi_dev_stop(struct sdxi_dev *sdxi) */ static int sdxi_fn_activate(struct sdxi_dev *sdxi) { - u64 version, cap0, cap1, ctl0, ctl2; + u64 version, cap0, cap1, ctl0, ctl2, cxt_l2, lv01_ptr; + struct sdxi_cxt_L2_ent *L2_ent; int err; =20 /* @@ -167,7 +171,13 @@ static int sdxi_fn_activate(struct sdxi_dev *sdxi) =20 cap1 =3D sdxi_read64(sdxi, SDXI_MMIO_CAP1); sdxi->op_grp_cap =3D FIELD_GET(SDXI_MMIO_CAP1_OPB_000_CAP, cap1); - sdxi->max_cxtid =3D FIELD_GET(SDXI_MMIO_CAP1_MAX_CXT, cap1); + + /* + * Constrain the number of client contexts supported by the + * driver to what fits in a single L1 table. + */ + sdxi->max_cxtid =3D min(SDXI_L1_TABLE_ENTRIES - 1, + FIELD_GET(SDXI_MMIO_CAP1_MAX_CXT, cap1)); =20 /* Apply our configuration. */ ctl2 =3D FIELD_PREP(SDXI_MMIO_CTL2_MAX_CXT, sdxi->max_cxtid); @@ -179,6 +189,32 @@ static int sdxi_fn_activate(struct sdxi_dev *sdxi) FIELD_GET(SDXI_MMIO_CAP1_OPB_000_CAP, cap1)); sdxi_write64(sdxi, SDXI_MMIO_CTL2, ctl2); =20 + /* SDXI 1.0 4.1.8.2 Context Level 2 Table Setup */ + sdxi->L2_table =3D dmam_alloc_coherent(sdxi->dev, + sizeof(*sdxi->L2_table), + &sdxi->L2_dma, GFP_KERNEL); + if (!sdxi->L2_table) + return -ENOMEM; + + cxt_l2 =3D FIELD_PREP(SDXI_MMIO_CXT_L2_PTR, sdxi->L2_dma >> ilog2(SZ_4K)); + sdxi_write64(sdxi, SDXI_MMIO_CXT_L2, cxt_l2); + + /* SDXI 1.0 4.1.8.3 Context Level 1 Table Setup */ + sdxi->L1_table =3D dmam_alloc_coherent(sdxi->dev, + sizeof(*sdxi->L1_table), + &sdxi->L1_dma, GFP_KERNEL); + if (!sdxi->L1_table) + return -ENOMEM; + /* + * SDXI 1.0 4.1.8.3.c: Initialize the Context level 2 table to + * point to the Context Level 1 [table]. + */ + L2_ent =3D &sdxi->L2_table->entry[0]; + lv01_ptr =3D FIELD_PREP(SDXI_CXT_L2_ENT_VL, 1) | + FIELD_PREP(SDXI_CXT_L2_ENT_LV01_PTR, + sdxi->L1_dma >> ilog2(SZ_4K)); + L2_ent->lv01_ptr =3D cpu_to_le64(lv01_ptr); + return 0; } =20 diff --git a/drivers/dma/sdxi/hw.h b/drivers/dma/sdxi/hw.h new file mode 100644 index 000000000000..00324f45b729 --- /dev/null +++ b/drivers/dma/sdxi/hw.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright Advanced Micro Devices, Inc. */ + +/* + * Control structures and constants defined in the SDXI specification, + * with low-level accessors. The ordering of the structures here + * follows the order of their definitions in the SDXI spec. + * + * Names of structures, members, and subfields (bit ranges within + * members) are written to match the spec, generally. E.g. struct + * sdxi_cxt_L2_ent corresponds to CXT_L2_ENT in the spec. + * + * Note: a member can have a subfield whose name is identical to the + * member's name. E.g. CXT_L2_ENT's lv01_ptr. + * + * All reserved fields and bits (usually named "rsvd" or some + * variation) must be set to zero by the driver unless otherwise + * specified. + */ + +#ifndef DMA_SDXI_HW_H +#define DMA_SDXI_HW_H + +#include +#include +#include +#include + +/* SDXI 1.0 Table 3-2: Context Level 2 Table Entry (CXT_L2_ENT) */ +struct sdxi_cxt_L2_ent { + __le64 lv01_ptr; +#define SDXI_CXT_L2_ENT_VL BIT_ULL(0) +#define SDXI_CXT_L2_ENT_LV01_PTR GENMASK_ULL(63, 12) +} __packed __aligned(8); +static_assert(sizeof(struct sdxi_cxt_L2_ent) =3D=3D 8); + +/* SDXI 1.0 3.2.1 Context Level 2 Table */ +#define SDXI_L2_TABLE_ENTRIES 512 +struct sdxi_cxt_L2_table { + struct sdxi_cxt_L2_ent entry[SDXI_L2_TABLE_ENTRIES]; +}; +static_assert(sizeof(struct sdxi_cxt_L2_table) =3D=3D 4096); + +/* SDXI 1.0 Table 3-3: Context Level 1 Table Entry (CXT_L1_ENT) */ +struct sdxi_cxt_L1_ent { + __le64 cxt_ctl_ptr; + __le64 akey_ptr; + __le32 misc0; + __le32 opb_000_enb; + __u8 rsvd_0[8]; +} __packed __aligned(32); +static_assert(sizeof(struct sdxi_cxt_L1_ent) =3D=3D 32); + +/* SDXI 1.0 3.2.2 Context Level 1 Table */ +#define SDXI_L1_TABLE_ENTRIES 128 +struct sdxi_cxt_L1_table { + struct sdxi_cxt_L1_ent entry[SDXI_L1_TABLE_ENTRIES]; +}; +static_assert(sizeof(struct sdxi_cxt_L1_table) =3D=3D 4096); + +#endif /* DMA_SDXI_HW_H */ diff --git a/drivers/dma/sdxi/mmio.h b/drivers/dma/sdxi/mmio.h index f07e857691b9..d1ea82b706ee 100644 --- a/drivers/dma/sdxi/mmio.h +++ b/drivers/dma/sdxi/mmio.h @@ -19,6 +19,9 @@ enum sdxi_reg { SDXI_MMIO_CAP0 =3D 0x00200, SDXI_MMIO_CAP1 =3D 0x00208, SDXI_MMIO_VERSION =3D 0x00210, + + /* SDXI 1.0 9.2 Context and RKey Table Registers */ + SDXI_MMIO_CXT_L2 =3D 0x10000, }; =20 /* SDXI 1.0 Table 9-2: MMIO_CTL0 */ @@ -51,4 +54,7 @@ enum sdxi_reg { #define SDXI_MMIO_VERSION_MINOR GENMASK_ULL(7, 0) #define SDXI_MMIO_VERSION_MAJOR GENMASK_ULL(23, 16) =20 +/* SDXI 1.0 Table 9-9: MMIO_CXT_L2 */ +#define SDXI_MMIO_CXT_L2_PTR GENMASK_ULL(63, 12) + #endif /* DMA_SDXI_MMIO_H */ diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h index 721abf7556d1..913292463eee 100644 --- a/drivers/dma/sdxi/sdxi.h +++ b/drivers/dma/sdxi/sdxi.h @@ -39,6 +39,11 @@ struct sdxi_dev { u16 max_cxtid; /* Maximum context ID allowed. */ u32 op_grp_cap; /* supported operation group cap */ =20 + struct sdxi_cxt_L2_table *L2_table; + dma_addr_t L2_dma; + struct sdxi_cxt_L1_table *L1_table; + dma_addr_t L1_dma; + const struct sdxi_bus_ops *bus_ops; }; =20 --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E08B9154425; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=W5T+tAVDBA5E4hcbRASs4kLh77KYQ2pXwoQa5wqGI6IPW5CE1ScZfFeyNqiUcLB0xM5cSWJ2EjKPet/BBHrvNVMgAuciHqSQctDImCc/MxAt86WH4HMHxxJgOBTtqZA4nxcelq1EV6sIwdrIP2qE9IP+KgNpbPCOsr05JXPvVk4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=4jf1UX/kSCkf0OQBB0DxszHloA/SowK1pgTk2RU4hwU=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=iAYQNc6X4JZYnjmRtWab4wTHx5Hg8Dm0SC8xf9C5sIS9BsDxiW/07tuNAXndz7J0r7pgyrlvUX5akryXQ6ARgogucRaPOdJaKeOG6n8bGAL5jg7AX4h1dHxiUmyCDXAq1uCpNRsRjguHFSpbpzitmBde2YeFT3lQtMks7gpsbTI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=IrOGVHy3; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="IrOGVHy3" Received: by smtp.kernel.org (Postfix) with ESMTPS id 9E63BC32781; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=4jf1UX/kSCkf0OQBB0DxszHloA/SowK1pgTk2RU4hwU=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=IrOGVHy3v5J2nlwtTS7oToqDXuXoNUMUMtnRKoX5cwGqrOZKqZU8NICJa1HzQtLVR o42JEM840izpVWRN7JIvdhqQCxHPL8F9HDQRQNCsFi16cuhrJzQ1WhZW/+FSGYM7DG Xw1tt/m6vr3TKegnB+3HcStK0iXGfgadijN8j1CgKlWYWu7ESS1uXT/HIaCFevTG3f OMoMw/cslV6sb0vHzFDUnB/jj+fahgISPNsYMdKdrrvhK1+7i83kzts2ZZARsZRBPq MW45n9LvqqiAy7nc9tKGi69CLJFLvRhNEBNri29CuuDWmiJliAqqzmrhFmoKP6BZ7U YiQ76cbo498hA== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9526ACD6E7E; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:09 -0500 Subject: [PATCH v3 06/23] dmaengine: sdxi: Allocate DMA pools 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: <20260605-sdxi-base-v3-6-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=4685; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=C3P80ebpeZVbhaM52K32rkyImUcW6/pnNndyzw2BApk=; b=eBgu/TlZHlz5S4js5ndxtiZ1V+vTaWnm2PtsPowTHIqBsZduHsS0V1fvrlis/Ke1p5UcMO4ug Rok/hobCIAlBpCyfzAxGttsldsPisJA63qMLJeWtUhVAsIYptIjNzag X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Each SDXI context consists of several control structures in system memory: * Descriptor ring * Access key (AKey) table * Context control block (CXT_CTL) * Context status block (CXT_STS) * Write index Of these, the write index, context control and context status blocks are small enough to justify DMA pools. SDXI descriptors also may have 32-byte completion status blocks (CST_BLK) associated with them that software can poll for completion. Introduce the C structures for context control, context status, and completion status blocks. Create a DMA pool for each of these objects as well as write indexes during SDXI function initialization, ensuring that potentially frequently-updated objects are aligned to avoid cacheline sharing. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/device.c | 42 +++++++++++++++++++++++++++++++++++++++++- drivers/dma/sdxi/hw.h | 28 ++++++++++++++++++++++++++++ drivers/dma/sdxi/sdxi.h | 5 +++++ 3 files changed, 74 insertions(+), 1 deletion(-) diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index fa5e27a4190e..7aa62a989bac 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -6,13 +6,16 @@ */ =20 #include +#include #include #include #include +#include #include #include #include #include +#include #include #include =20 @@ -218,6 +221,43 @@ static int sdxi_fn_activate(struct sdxi_dev *sdxi) return 0; } =20 +static int sdxi_device_init(struct sdxi_dev *sdxi) +{ + struct device *dev =3D sdxi->dev; + size_t size, align; + int err; + + size =3D sizeof(__le64); + align =3D max(size, SMP_CACHE_BYTES); + sdxi->write_index_pool =3D dmam_pool_create("Write_Index", dev, size, + align, 0); + if (!sdxi->write_index_pool) + return -ENOMEM; + + size =3D sizeof(struct sdxi_cxt_sts); + align =3D max(size, SMP_CACHE_BYTES); + sdxi->cxt_sts_pool =3D dmam_pool_create("CXT_STS", dev, size, align, 0); + if (!sdxi->cxt_sts_pool) + return -ENOMEM; + + size =3D align =3D sizeof(struct sdxi_cxt_ctl); + sdxi->cxt_ctl_pool =3D dmam_pool_create("CXT_CTL", dev, size, align, 0); + if (!sdxi->cxt_ctl_pool) + return -ENOMEM; + + size =3D sizeof(struct sdxi_cst_blk); + align =3D max(size, SMP_CACHE_BYTES); + sdxi->cst_blk_pool =3D dmam_pool_create("CST_BLK", dev, size, align, 0); + if (!sdxi->cst_blk_pool) + return -ENOMEM; + + err =3D sdxi_fn_activate(sdxi); + if (err) + return err; + + return 0; +} + int sdxi_register(struct device *dev, const struct sdxi_bus_ops *ops) { struct sdxi_dev *sdxi; @@ -235,7 +275,7 @@ int sdxi_register(struct device *dev, const struct sdxi= _bus_ops *ops) if (err) return err; =20 - return sdxi_fn_activate(sdxi); + return sdxi_device_init(sdxi); } EXPORT_SYMBOL_NS_GPL(sdxi_register, "SDXI"); =20 diff --git a/drivers/dma/sdxi/hw.h b/drivers/dma/sdxi/hw.h index 00324f45b729..b3fd3587ccf8 100644 --- a/drivers/dma/sdxi/hw.h +++ b/drivers/dma/sdxi/hw.h @@ -58,4 +58,32 @@ struct sdxi_cxt_L1_table { }; static_assert(sizeof(struct sdxi_cxt_L1_table) =3D=3D 4096); =20 +/* SDXI 1.0 Table 3-4: Context Control (CXT_CTL) */ +struct sdxi_cxt_ctl { + __le64 ds_ring_ptr; + __le32 ds_ring_sz; + __u8 rsvd_0[4]; + __le64 cxt_sts_ptr; + __le64 write_index_ptr; + __u8 rsvd_1[32]; +} __packed __aligned(64); +static_assert(sizeof(struct sdxi_cxt_ctl) =3D=3D 64); + +/* SDXI 1.0 Table 3-5: Context Status (CXT_STS) */ +struct sdxi_cxt_sts { + __u8 state; + __u8 misc0; + __u8 rsvd_0[6]; + __le64 read_index; +} __packed __aligned(16); +static_assert(sizeof(struct sdxi_cxt_sts) =3D=3D 16); + +/* SDXI 1.0 Table 6-4: CST_BLK (Completion Status Block) */ +struct sdxi_cst_blk { + __le64 signal; + __le32 flags; + __u8 rsvd_0[20]; +} __packed __aligned(32); +static_assert(sizeof(struct sdxi_cst_blk) =3D=3D 32); + #endif /* DMA_SDXI_HW_H */ diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h index 913292463eee..ade702b6bec5 100644 --- a/drivers/dma/sdxi/sdxi.h +++ b/drivers/dma/sdxi/sdxi.h @@ -44,6 +44,11 @@ struct sdxi_dev { struct sdxi_cxt_L1_table *L1_table; dma_addr_t L1_dma; =20 + struct dma_pool *write_index_pool; + struct dma_pool *cxt_sts_pool; + struct dma_pool *cxt_ctl_pool; + struct dma_pool *cst_blk_pool; + const struct sdxi_bus_ops *bus_ops; }; =20 --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E0D61155757; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=B4u4PmesMhI72Tytwshr8lpxsQVdD3tPMg8cIyA7Tx+wOUc0OUbbWx0wshgLq8K/xrznFTZeacRCK6KqjUx7ZLX4VQ1LcRdneQbsknVq+Hr6YeZXPDCupkmOSdBtfQ9KQRatA7fiBlzNMgYJ+p3bx1R5Z5GHm5PzRAth3IFZ2M8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=kraf85ZUwOLQ1KSQQioSLX8q4CoMjnXQdR9OB/u06BM=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=GCvk7oKSaxEujOLzRjrf1jy6nQMlLsYEXD+tN8jmvCDomAPwX1g66C4Fwu6jn6JBXJvdEDENZJPkPOIOjM0dEA5KJmC8vHeVAWR9PYRMSFdol8bplS+W2NayGikGbFdlGkzuwT6nymHXEaiEMMDP+gSJANHUXZy/uxAVIiQAZjk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=oTYXx4eD; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="oTYXx4eD" Received: by smtp.kernel.org (Postfix) with ESMTPS id AED54C2BCF6; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=kraf85ZUwOLQ1KSQQioSLX8q4CoMjnXQdR9OB/u06BM=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=oTYXx4eDfswVmXaby8o5ok27jk5qtOMRNJEjVRF8T+Wlb0T5ozfj6SwJ217VxZCp6 Ei/EDuNzc0JrjEWSU0wsGzUgB6SdmeDX1wxDEcBlr6pIupCz0s9KUtWbcM88YXPoNb MTyBFHMoQ7Zd+AmjLZRUsvVPkKERDNjjpCIV2mhL0P1lPEE9fxNGeYwcFEOZ/+1/4I 0529gShPFbRwOKj/HIVxexpzMuAzwvN9A6gxR2l6bIjEQbH7KAodneNw8HXr06ZvF8 ipZulTUY/8OHDzFB4RAdpF6uJKdeJmfxN9wRNRKWWMXMa14dmL+JDsPe4zkSZgPNLq FTgBfFKMZ6Lkg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id A5A75CD6E7B; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:10 -0500 Subject: [PATCH v3 07/23] dmaengine: sdxi: Allocate administrative context 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: <20260605-sdxi-base-v3-7-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Frank Li , Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=9183; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=pO1tBUN47TwpUNMIsAV28iMvmtfvg1vVtjUFD1Ue9T0=; b=wJKaeR8gJdi6k2e4kU+z+gHsTEPm8yTiEf3Kps8iux57D9d8Rd+urc8RFkBYb/ySYKwyRehj5 S9YaZORP8+TBfkhsL/i74IrhcaVnrwDblyYGZaEVsDrXGTKbGBa1j6i X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Create the control structure hierarchy in memory for the per-function administrative context. Use devres to queue the corresponding cleanup since the admin context is a device-scope resource. The context is inert for now; changes to follow will make it functional. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Frank Li Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/Makefile | 4 +- drivers/dma/sdxi/context.c | 128 +++++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/context.h | 54 +++++++++++++++++++ drivers/dma/sdxi/device.c | 11 ++++ drivers/dma/sdxi/hw.h | 43 +++++++++++++++ drivers/dma/sdxi/sdxi.h | 2 + 6 files changed, 241 insertions(+), 1 deletion(-) diff --git a/drivers/dma/sdxi/Makefile b/drivers/dma/sdxi/Makefile index 0006edf74d86..cdf8a455077b 100644 --- a/drivers/dma/sdxi/Makefile +++ b/drivers/dma/sdxi/Makefile @@ -1,6 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_SDXI_CORE) +=3D sdxi-core.o -sdxi-core-y :=3D device.o +sdxi-core-y :=3D \ + context.o \ + device.o =20 obj-$(CONFIG_SDXI_PCI) +=3D sdxi-pci.o sdxi-pci-y :=3D pci.o diff --git a/drivers/dma/sdxi/context.c b/drivers/dma/sdxi/context.c new file mode 100644 index 000000000000..443c231303af --- /dev/null +++ b/drivers/dma/sdxi/context.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI context management + * + * Copyright Advanced Micro Devices, Inc. + */ + +#define pr_fmt(fmt) "SDXI: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "context.h" +#include "sdxi.h" + +#define DEFAULT_DESC_RING_ENTRIES 1024 + +enum { + /* + * The admin context always has ID 0. See SDXI 1.0 3.5 + * Administrative Context (Context 0). + */ + SDXI_ADMIN_CXT_ID =3D 0, +}; + +/* + * Free context and its resources. @cxt may be partially allocated but + * must have ->sdxi set. + */ +static void sdxi_free_cxt(struct sdxi_cxt *cxt) +{ + struct sdxi_dev *sdxi =3D cxt->sdxi; + struct sdxi_sq *sq =3D cxt->sq; + + if (cxt->cxt_ctl) + dma_pool_free(sdxi->cxt_ctl_pool, cxt->cxt_ctl, + cxt->cxt_ctl_dma); + if (cxt->akey_table) + dma_free_coherent(sdxi->dev, sizeof(*cxt->akey_table), + cxt->akey_table, cxt->akey_table_dma); + if (sq && sq->write_index) + dma_pool_free(sdxi->write_index_pool, sq->write_index, + sq->write_index_dma); + if (sq && sq->cxt_sts) + dma_pool_free(sdxi->cxt_sts_pool, sq->cxt_sts, sq->cxt_sts_dma); + if (sq && sq->desc_ring) + dma_free_coherent(sdxi->dev, sq->ring_size, + sq->desc_ring, sq->ring_dma); + kfree(cxt->sq); + kfree(cxt); +} + +DEFINE_FREE(sdxi_cxt, struct sdxi_cxt *, if (_T) sdxi_free_cxt(_T)) + +/* Allocate a context and its control structure hierarchy in memory. */ +static struct sdxi_cxt *sdxi_alloc_cxt(struct sdxi_dev *sdxi) +{ + struct device *dev =3D sdxi->dev; + struct sdxi_sq *sq; + struct sdxi_cxt *cxt __free(sdxi_cxt) =3D kzalloc(sizeof(*cxt), GFP_KERNE= L); + + if (!cxt) + return NULL; + + cxt->sdxi =3D sdxi; + + cxt->sq =3D kzalloc_obj(*cxt->sq, GFP_KERNEL); + if (!cxt->sq) + return NULL; + + cxt->akey_table =3D dma_alloc_coherent(dev, sizeof(*cxt->akey_table), + &cxt->akey_table_dma, GFP_KERNEL); + if (!cxt->akey_table) + return NULL; + + cxt->cxt_ctl =3D dma_pool_zalloc(sdxi->cxt_ctl_pool, GFP_KERNEL, + &cxt->cxt_ctl_dma); + if (!cxt->cxt_ctl) + return NULL; + + sq =3D cxt->sq; + + sq->ring_entries =3D DEFAULT_DESC_RING_ENTRIES; + sq->ring_size =3D sq->ring_entries * sizeof(sq->desc_ring[0]); + sq->desc_ring =3D dma_alloc_coherent(dev, sq->ring_size, &sq->ring_dma, + GFP_KERNEL); + if (!sq->desc_ring) + return NULL; + + sq->cxt_sts =3D dma_pool_zalloc(sdxi->cxt_sts_pool, GFP_KERNEL, + &sq->cxt_sts_dma); + if (!sq->cxt_sts) + return NULL; + + sq->write_index =3D dma_pool_zalloc(sdxi->write_index_pool, GFP_KERNEL, + &sq->write_index_dma); + if (!sq->write_index) + return NULL; + + return_ptr(cxt); +} + +static void free_admin_cxt(void *ptr) +{ + struct sdxi_dev *sdxi =3D ptr; + + sdxi_free_cxt(sdxi->admin_cxt); +} + +int sdxi_admin_cxt_init(struct sdxi_dev *sdxi) +{ + struct sdxi_cxt *cxt __free(sdxi_cxt) =3D sdxi_alloc_cxt(sdxi); + if (!cxt) + return -ENOMEM; + + cxt->id =3D SDXI_ADMIN_CXT_ID; + cxt->db =3D sdxi->dbs + cxt->id * sdxi->db_stride; + + sdxi->admin_cxt =3D no_free_ptr(cxt); + + return devm_add_action_or_reset(sdxi->dev, free_admin_cxt, sdxi); +} diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h new file mode 100644 index 000000000000..a29387900df7 --- /dev/null +++ b/drivers/dma/sdxi/context.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright Advanced Micro Devices, Inc. + */ + +#ifndef DMA_SDXI_CONTEXT_H +#define DMA_SDXI_CONTEXT_H + +#include +#include + +#include "hw.h" +#include "sdxi.h" + +/* + * The size of the AKey table is flexible, from 4KB to 1MB. Always use + * the minimum size for now. + */ +struct sdxi_akey_table { + struct sdxi_akey_ent entry[SZ_4K / sizeof(struct sdxi_akey_ent)]; +}; + +/* Submission Queue */ +struct sdxi_sq { + u32 ring_entries; + u32 ring_size; + struct sdxi_desc *desc_ring; + dma_addr_t ring_dma; + + __le64 *write_index; + dma_addr_t write_index_dma; + + struct sdxi_cxt_sts *cxt_sts; + dma_addr_t cxt_sts_dma; +}; + +struct sdxi_cxt { + struct sdxi_dev *sdxi; + u16 id; + + __le64 __iomem *db; + + struct sdxi_cxt_ctl *cxt_ctl; + dma_addr_t cxt_ctl_dma; + + struct sdxi_akey_table *akey_table; + dma_addr_t akey_table_dma; + + struct sdxi_sq *sq; +}; + +int sdxi_admin_cxt_init(struct sdxi_dev *sdxi); + +#endif /* DMA_SDXI_CONTEXT_H */ diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index 7aa62a989bac..4d595e79b8ce 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -19,6 +19,7 @@ #include #include =20 +#include "context.h" #include "hw.h" #include "mmio.h" #include "sdxi.h" @@ -218,6 +219,16 @@ static int sdxi_fn_activate(struct sdxi_dev *sdxi) sdxi->L1_dma >> ilog2(SZ_4K)); L2_ent->lv01_ptr =3D cpu_to_le64(lv01_ptr); =20 + /* + * SDXI 1.0 4.1.8.4 Administrative Context + * + * The admin context will not consume descriptors until we + * write its doorbell later. + */ + err =3D sdxi_admin_cxt_init(sdxi); + if (err) + return err; + return 0; } =20 diff --git a/drivers/dma/sdxi/hw.h b/drivers/dma/sdxi/hw.h index b3fd3587ccf8..55d63d50a01b 100644 --- a/drivers/dma/sdxi/hw.h +++ b/drivers/dma/sdxi/hw.h @@ -23,6 +23,7 @@ =20 #include #include +#include #include #include =20 @@ -72,12 +73,39 @@ static_assert(sizeof(struct sdxi_cxt_ctl) =3D=3D 64); /* SDXI 1.0 Table 3-5: Context Status (CXT_STS) */ struct sdxi_cxt_sts { __u8 state; +#define SDXI_CXT_STS_STATE GENMASK(3, 0) __u8 misc0; __u8 rsvd_0[6]; __le64 read_index; } __packed __aligned(16); static_assert(sizeof(struct sdxi_cxt_sts) =3D=3D 16); =20 +/* SDXI 1.0 Table 3-6: CXT_STS.state Encoding */ +/* Valid values for FIELD_GET(SDXI_CXT_STS_STATE, sdxi_cxt_sts.state). */ +enum cxt_sts_state { + CXTV_STOP_SW =3D 0x0, + CXTV_RUN =3D 0x1, + CXTV_STOPG_SW =3D 0x2, + CXTV_STOP_FN =3D 0x4, + CXTV_STOPG_FN =3D 0x6, + CXTV_ERR_FN =3D 0xf, +}; + +/* SDXI 1.0 Table 3-7: AKey Table Entry (AKEY_ENT) */ +struct sdxi_akey_ent { + __le16 intr_num; +#define SDXI_AKEY_ENT_VL BIT(0) +#define SDXI_AKEY_ENT_IV BIT(1) +#define SDXI_AKEY_ENT_INTR_NUM GENMASK(14, 4) + __le16 tgt_sfunc; + __le32 pasid; + __le16 stag; + __u8 rsvd_0[2]; + __le16 rkey; + __u8 rsvd_1[2]; +} __packed __aligned(16); +static_assert(sizeof(struct sdxi_akey_ent) =3D=3D 16); + /* SDXI 1.0 Table 6-4: CST_BLK (Completion Status Block) */ struct sdxi_cst_blk { __le64 signal; @@ -86,4 +114,19 @@ struct sdxi_cst_blk { } __packed __aligned(32); static_assert(sizeof(struct sdxi_cst_blk) =3D=3D 32); =20 +struct sdxi_desc { + union { + /* + * SDXI 1.0 Table 6-3: DSC_GENERIC SDXI Descriptor + * Common Header and Footer Format + */ + struct_group_tagged(sdxi_dsc_generic, generic, + __le32 opcode; + __u8 operation[52]; + __le64 csb_ptr; + ); + }; +} __packed __aligned(64); +static_assert(sizeof(struct sdxi_desc) =3D=3D 64); + #endif /* DMA_SDXI_HW_H */ diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h index ade702b6bec5..f5e0cd986b9e 100644 --- a/drivers/dma/sdxi/sdxi.h +++ b/drivers/dma/sdxi/sdxi.h @@ -49,6 +49,8 @@ struct sdxi_dev { struct dma_pool *cxt_ctl_pool; struct dma_pool *cst_blk_pool; =20 + struct sdxi_cxt *admin_cxt; + const struct sdxi_bus_ops *bus_ops; }; =20 --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E053F13DDA4; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=Tw8rrdET1x+VZuQBYkvcsqvFvEyLN+aEzeOqo6VRtBfaiyct4vbmFPhtFhYYbi4P18Y52KhHsdp379fKHHayO337VlNGb/fK4qcME1EYHdcRH6iHq3b948+/tcPKzyRY4CAXqncpnYLAqPMJyUyNC5Db5AYQQcgBwFRH2YitfZY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=Tp2DRlO6SqKW2OmnnN6MqpnTkP5tD4sN8tnLoKhufPg=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=qm7VlpzvCv1F1PwRt9vdtnX05Xu45o4/xMGgFAsa+NXuEuaIzzZ6Gl+HCDL2Ndg2S8HFBLsocVS2P/hrsupwUMUN48yK7el0+ux2xP7xMty3rjSkZUqKJtOPDwX90qNl2Q+dDueQxU0qoUelUqwPLjdFlxmBSlYcrUCYzTBur1I= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=RMlYRuwp; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="RMlYRuwp" Received: by smtp.kernel.org (Postfix) with ESMTPS id C045CC2BD05; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=Tp2DRlO6SqKW2OmnnN6MqpnTkP5tD4sN8tnLoKhufPg=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=RMlYRuwpBUvhCH6vvDx/LEHsjFtkhpVa0+FRsCgOV0N3IDu1IEa84+d63gYqbU9gM OYv6klxAEmqfAd1hx6puw4+O79DT0o4XVMgrr+vGiBuU3ECUdp9kZCHEg66zo4vhmU I76lMxOntzkV0DOUJm6z8CzyK5uSyd9QFEUlolztE/FB67GsTeqpGK0AjQhuYRPcHP YLmLYdrHCivVsVeZr7GU9QA5Y9/8ydiWmMdiWIuafOCnwhlkZac6+RqfOx5nAT9mo5 uwrdeiOzfh13illIcy6pF6A8d9X6AbgSzlDzI77zvLMHW7XSFiKxycihddT9RFCSKh fBO/9eAsj+tGg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id B841CCD8C81; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:11 -0500 Subject: [PATCH v3 08/23] dmaengine: sdxi: Install administrative context 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: <20260605-sdxi-base-v3-8-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=9174; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=zW988Sovngm2snUuwqnu55nb+6mHuS+MKCdhjdyAMsI=; b=7XxWXdYXlti/8gV4wmltQKSYR89kye/zJuHomV2vjs0l/aygalZGlJChaMcFQMj/uOV9nmIzi VnyHdc9IzvCCctQKH2ib1iGZCzzjRCwpzzFMdIqaWYvFzyhnbNg3Lpc X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Serialize the context control block, akey table, and L1 entry for the admin context, making its descriptor ring, write index, and context status block visible to the SDXI implementation once it is activated. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/context.c | 162 +++++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/context.h | 7 ++ drivers/dma/sdxi/hw.h | 15 +++++ drivers/dma/sdxi/sdxi.h | 9 +++ 4 files changed, 193 insertions(+) diff --git a/drivers/dma/sdxi/context.c b/drivers/dma/sdxi/context.c index 443c231303af..cc99fe9ecf92 100644 --- a/drivers/dma/sdxi/context.c +++ b/drivers/dma/sdxi/context.c @@ -7,16 +7,22 @@ =20 #define pr_fmt(fmt) "SDXI: " fmt =20 +#include +#include #include #include #include #include #include #include +#include #include #include +#include +#include =20 #include "context.h" +#include "hw.h" #include "sdxi.h" =20 #define DEFAULT_DESC_RING_ENTRIES 1024 @@ -106,6 +112,152 @@ static struct sdxi_cxt *sdxi_alloc_cxt(struct sdxi_de= v *sdxi) return_ptr(cxt); } =20 +struct sdxi_cxt_ctl_cfg { + dma_addr_t ds_ring_ptr; + dma_addr_t cxt_sts_ptr; + dma_addr_t write_index_ptr; + u32 ds_ring_sz; + u8 qos; + u8 csa; + bool se; +}; + +static int configure_cxt_ctl(struct sdxi_cxt_ctl *ctl, const struct sdxi_c= xt_ctl_cfg *cfg) +{ + u64 ds_ring_ptr, cxt_sts_ptr, write_index_ptr; + + write_index_ptr =3D FIELD_PREP(SDXI_CXT_CTL_WRITE_INDEX_PTR, + cfg->write_index_ptr >> WRT_INDEX_PTR_SHIFT); + cxt_sts_ptr =3D FIELD_PREP(SDXI_CXT_CTL_CXT_STS_PTR, + cfg->cxt_sts_ptr >> CXT_STATUS_PTR_SHIFT); + + *ctl =3D (typeof(*ctl)) { + /* + * ds_ring_ptr contains the validity bit and is updated + * after a barrier is issued. + */ + .ds_ring_sz =3D cpu_to_le32(cfg->ds_ring_sz), + .cxt_sts_ptr =3D cpu_to_le64(cxt_sts_ptr), + .write_index_ptr =3D cpu_to_le64(write_index_ptr), + }; + + ds_ring_ptr =3D FIELD_PREP(SDXI_CXT_CTL_VL, 1) | + FIELD_PREP(SDXI_CXT_CTL_QOS, cfg->qos) | + FIELD_PREP(SDXI_CXT_CTL_SE, cfg->se) | + FIELD_PREP(SDXI_CXT_CTL_CSA, cfg->csa) | + FIELD_PREP(SDXI_CXT_CTL_DS_RING_PTR, + cfg->ds_ring_ptr >> DESC_RING_BASE_PTR_SHIFT); + /* Ensure other fields are visible before hw sees vl=3D1. */ + dma_wmb(); + WRITE_ONCE(ctl->ds_ring_ptr, cpu_to_le64(ds_ring_ptr)); + + return 0; +} + +/* + * Logical representation of CXT_L1_ENT subfields. + */ +struct sdxi_cxt_L1_cfg { + dma_addr_t cxt_ctl_ptr; + dma_addr_t akey_ptr; + u32 cxt_pasid; + u32 opb_000_enb; + u16 max_buffer; + u8 akey_sz; + bool ka; + bool pv; +}; + +static int configure_L1_entry(struct sdxi_cxt_L1_ent *ent, + const struct sdxi_cxt_L1_cfg *cfg) +{ + u64 cxt_ctl_ptr, akey_ptr; + u32 misc0; + + if (WARN_ON_ONCE(!IS_ALIGNED(cfg->cxt_ctl_ptr, SZ_64))) + return -EFAULT; + if (WARN_ON_ONCE(!IS_ALIGNED(cfg->akey_ptr, SZ_4K))) + return -EFAULT; + + akey_ptr =3D FIELD_PREP(SDXI_CXT_L1_ENT_AKEY_SZ, cfg->akey_sz) | + FIELD_PREP(SDXI_CXT_L1_ENT_AKEY_PTR, + cfg->akey_ptr >> L1_CXT_AKEY_PTR_SHIFT); + + misc0 =3D FIELD_PREP(SDXI_CXT_L1_ENT_PASID, cfg->cxt_pasid) | + FIELD_PREP(SDXI_CXT_L1_ENT_MAX_BUFFER, cfg->max_buffer); + + *ent =3D (typeof(*ent)) { + /* + * cxt_ctl_ptr contains the validity bit and is + * updated after a barrier is issued. + */ + .akey_ptr =3D cpu_to_le64(akey_ptr), + .misc0 =3D cpu_to_le32(misc0), + .opb_000_enb =3D cpu_to_le32(cfg->opb_000_enb), + }; + + cxt_ctl_ptr =3D FIELD_PREP(SDXI_CXT_L1_ENT_VL, 1) | + FIELD_PREP(SDXI_CXT_L1_ENT_KA, cfg->ka) | + FIELD_PREP(SDXI_CXT_L1_ENT_PV, cfg->pv) | + FIELD_PREP(SDXI_CXT_L1_ENT_CXT_CTL_PTR, + cfg->cxt_ctl_ptr >> L1_CXT_CTRL_PTR_SHIFT); + /* Ensure other fields are visible before hw sees vl=3D1. */ + dma_wmb(); + WRITE_ONCE(ent->cxt_ctl_ptr, cpu_to_le64(cxt_ctl_ptr)); + + return 0; +} + +/* + * Make the context control structure hierarchy valid from the POV of + * the SDXI implementation. This may eventually involve allocation of + * a L1 table page, so it needs to be fallible. + */ +static int sdxi_publish_cxt(const struct sdxi_cxt *cxt) +{ + struct sdxi_cxt_ctl_cfg ctl_cfg; + struct sdxi_cxt_L1_cfg L1_cfg; + struct sdxi_cxt_L1_ent *ent; + u8 l1_idx; + int err; + + if (WARN_ONCE(cxt->id > cxt->sdxi->max_cxtid, + "can't install cxt with id %u (limit %u)", + cxt->id, cxt->sdxi->max_cxtid)) + return -EINVAL; + + ctl_cfg =3D (typeof(ctl_cfg)) { + .se =3D 1, + .csa =3D 1, + .ds_ring_ptr =3D cxt->sq->ring_dma, + .ds_ring_sz =3D cxt->sq->ring_size >> 6, + .cxt_sts_ptr =3D cxt->sq->cxt_sts_dma, + .write_index_ptr =3D cxt->sq->write_index_dma, + }; + + err =3D configure_cxt_ctl(cxt->cxt_ctl, &ctl_cfg); + if (err) + return err; + + l1_idx =3D ID_TO_L1_INDEX(cxt->id); + + ent =3D &cxt->sdxi->L1_table->entry[l1_idx]; + + L1_cfg =3D (typeof(L1_cfg)) { + .ka =3D 1, + .pv =3D 0, + .cxt_ctl_ptr =3D cxt->cxt_ctl_dma, + .akey_sz =3D akey_table_order(cxt->akey_table), + .akey_ptr =3D cxt->akey_table_dma, + .cxt_pasid =3D IOMMU_NO_PASID, + .max_buffer =3D 11, /* 4GB */ + .opb_000_enb =3D cxt->sdxi->op_grp_cap, + }; + + return configure_L1_entry(ent, &L1_cfg); + /* todo: need to send DSC_CXT_UPD to admin */ +} + static void free_admin_cxt(void *ptr) { struct sdxi_dev *sdxi =3D ptr; @@ -115,13 +267,23 @@ static void free_admin_cxt(void *ptr) =20 int sdxi_admin_cxt_init(struct sdxi_dev *sdxi) { + int err; + struct sdxi_sq *sq; + struct sdxi_cxt *cxt __free(sdxi_cxt) =3D sdxi_alloc_cxt(sdxi); if (!cxt) return -ENOMEM; =20 + sq =3D cxt->sq; + /* SDXI 1.0 4.1.8.4.b: Set CXT_STS.state to CXTV_RUN. */ + sq->cxt_sts->state =3D FIELD_PREP(SDXI_CXT_STS_STATE, CXTV_RUN); cxt->id =3D SDXI_ADMIN_CXT_ID; cxt->db =3D sdxi->dbs + cxt->id * sdxi->db_stride; =20 + err =3D sdxi_publish_cxt(cxt); + if (err) + return err; + sdxi->admin_cxt =3D no_free_ptr(cxt); =20 return devm_add_action_or_reset(sdxi->dev, free_admin_cxt, sdxi); diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h index a29387900df7..65b773446ba3 100644 --- a/drivers/dma/sdxi/context.h +++ b/drivers/dma/sdxi/context.h @@ -20,6 +20,13 @@ struct sdxi_akey_table { struct sdxi_akey_ent entry[SZ_4K / sizeof(struct sdxi_akey_ent)]; }; =20 +/* For encoding the akey table size in CXT_L1_ENT's akey_sz. */ +static inline u8 akey_table_order(const struct sdxi_akey_table *tbl) +{ + static_assert(sizeof(*tbl) =3D=3D SZ_4K); + return 0; +} + /* Submission Queue */ struct sdxi_sq { u32 ring_entries; diff --git a/drivers/dma/sdxi/hw.h b/drivers/dma/sdxi/hw.h index 55d63d50a01b..4b65337a5975 100644 --- a/drivers/dma/sdxi/hw.h +++ b/drivers/dma/sdxi/hw.h @@ -45,8 +45,16 @@ static_assert(sizeof(struct sdxi_cxt_L2_table) =3D=3D 40= 96); /* SDXI 1.0 Table 3-3: Context Level 1 Table Entry (CXT_L1_ENT) */ struct sdxi_cxt_L1_ent { __le64 cxt_ctl_ptr; +#define SDXI_CXT_L1_ENT_VL BIT_ULL(0) +#define SDXI_CXT_L1_ENT_KA BIT_ULL(1) +#define SDXI_CXT_L1_ENT_PV BIT_ULL(2) +#define SDXI_CXT_L1_ENT_CXT_CTL_PTR GENMASK_ULL(63, 6) __le64 akey_ptr; +#define SDXI_CXT_L1_ENT_AKEY_SZ GENMASK_ULL(3, 0) +#define SDXI_CXT_L1_ENT_AKEY_PTR GENMASK_ULL(63, 12) __le32 misc0; +#define SDXI_CXT_L1_ENT_PASID GENMASK(19, 0) +#define SDXI_CXT_L1_ENT_MAX_BUFFER GENMASK(23, 20) __le32 opb_000_enb; __u8 rsvd_0[8]; } __packed __aligned(32); @@ -62,10 +70,17 @@ static_assert(sizeof(struct sdxi_cxt_L1_table) =3D=3D 4= 096); /* SDXI 1.0 Table 3-4: Context Control (CXT_CTL) */ struct sdxi_cxt_ctl { __le64 ds_ring_ptr; +#define SDXI_CXT_CTL_VL BIT_ULL(0) +#define SDXI_CXT_CTL_QOS GENMASK_ULL(3, 2) +#define SDXI_CXT_CTL_SE BIT_ULL(4) +#define SDXI_CXT_CTL_CSA BIT_ULL(5) +#define SDXI_CXT_CTL_DS_RING_PTR GENMASK_ULL(63, 6) __le32 ds_ring_sz; __u8 rsvd_0[4]; __le64 cxt_sts_ptr; +#define SDXI_CXT_CTL_CXT_STS_PTR GENMASK_ULL(63, 4) __le64 write_index_ptr; +#define SDXI_CXT_CTL_WRITE_INDEX_PTR GENMASK_ULL(63, 3) __u8 rsvd_1[32]; } __packed __aligned(64); static_assert(sizeof(struct sdxi_cxt_ctl) =3D=3D 64); diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h index f5e0cd986b9e..903bf18bd3cc 100644 --- a/drivers/dma/sdxi/sdxi.h +++ b/drivers/dma/sdxi/sdxi.h @@ -15,6 +15,15 @@ =20 #include "mmio.h" =20 +#define ID_TO_L1_INDEX(id) ((id) & 0x7F) + +#define DESC_RING_BASE_PTR_SHIFT 6 +#define CXT_STATUS_PTR_SHIFT 4 +#define WRT_INDEX_PTR_SHIFT 3 + +#define L1_CXT_CTRL_PTR_SHIFT 6 +#define L1_CXT_AKEY_PTR_SHIFT 12 + struct sdxi_dev; =20 /** --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3669421ADB7; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=aXeaZbS1q2nIybVM4aSUt/MuBBl2wSny3QgpIJj2QrlwFO4FSuZ0sRFnANChYnHOHJejOblQvxTO9ETqDbAYNb5UtacXzN8cwr15+QHusNRnnY/qfOv0rX1vUxoj2+Hmal5NAP+u7k/JREZpNlrCHjfyxdQ5MxmxyLuvnD4CiMY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=WPoSfU5dZwZT2IZNdbcuv/ZH4xLJrv+uNXMErQMKsyg=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=lAmXXpBN0EeL6ZdC7y46eoLusoWgzbZJpgI9snw7BYc35BeQ/w29p2hB7sWFuVZeAHYKlcwleDlOptR7Y5qDfYtOxp0yNNW5exjgM9cysLbQoOAjVChTL5iIfngfjnS6yZ6uMMNI6vFTVthKu4uKRBXJwKsBDtbyWwH8SZs8x9Q= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=G9a8V13A; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="G9a8V13A" Received: by smtp.kernel.org (Postfix) with ESMTPS id D3724C2BCC9; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=WPoSfU5dZwZT2IZNdbcuv/ZH4xLJrv+uNXMErQMKsyg=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=G9a8V13Az+EIAjhhN6gG3sXni4GAxtYj7ZzAbyWIfc5g5G0HMN7LKoXzwkt5xQmgQ Q0ReJRkjDpXWo90TMR7lx9AWLkLqSGLW2mkZHC6trN/NlB/DDspvab6tyQvt8IaZFQ O+JF+yz5afJP/NB2wO254lfZWPr0UDz6VPSQ95LTbl9PeorXhLwSxDKlTyegfAq5xx pERINBYeyJRm4QCPYLcEHL/m66MfNTW+9eN+OMwzSQmUKIq6jrDhX6powQKIf87/MA vbbVa+3ck/QfFBkxoUV8c/ySOqej5S6YNZ+kELDNf7ZjPjzi6qmRkK7X4SazMtMigr eEZJBu3b64N8w== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id C8F67CD6E7B; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:12 -0500 Subject: [PATCH v3 09/23] dmaengine: sdxi: Start functions on probe, stop on remove 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: <20260605-sdxi-base-v3-9-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=4059; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=HJWXcsWA72TD+d9YgNYbMCtKgp6O0CoGRH3DT157Mcc=; b=ddgeXegAogUDZM8IolRQiz+WKYeZAUBSCUKkcdu0+1TJv9JpV+aCBwu8qucLlgssXggCygqMa AxX9226ioh5CZQ1dxGAaTyqo+miqWrk7KsHQYUzrrWQsMTKrKldUeUK X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Following admin context setup in the previous patch, drive each SDXI function to active state during probe. This is done by writing GSRV_ACTIVE to MMIO_CTL0.fn_gsr and polling MMIO_STS0.fn_gsv until the function reaches GSV_ACTIVE or an error state. A 1-second timeout has been sufficient in practice so far. Introduce sdxi_unregister() to stop the function during remove and wire it up via the pci_driver .remove callback. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/device.c | 50 +++++++++++++++++++++++++++++++++++++++++++= +++- drivers/dma/sdxi/pci.c | 7 +++++++ drivers/dma/sdxi/sdxi.h | 1 + 3 files changed, 57 insertions(+), 1 deletion(-) diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index 4d595e79b8ce..e8f087f758fd 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -90,6 +90,42 @@ static void sdxi_write_fn_gsr(struct sdxi_dev *sdxi, enu= m sdxi_fn_gsr cmd) sdxi_write64(sdxi, SDXI_MMIO_CTL0, ctl0); } =20 +/* + * Transition the function from stopped state to active. + * See SDXI 1.0 4.1 SDXI Function State. + */ +static int sdxi_dev_start(struct sdxi_dev *sdxi) +{ + enum sdxi_fn_gsv status =3D sdxi_dev_gsv(sdxi); + int ret; + + if (status !=3D SDXI_GSV_STOP) { + dev_err(sdxi->dev, + "can't activate busy device (unexpected gsv: %s)\n", + gsv_str(status)); + return -EBUSY; + } + + sdxi_write_fn_gsr(sdxi, SDXI_GSRV_ACTIVE); + + ret =3D sdxi_dev_gsv_poll(sdxi, status, + status =3D=3D SDXI_GSV_ACTIVE || + status =3D=3D SDXI_GSV_ERROR); + if (ret) { + dev_err(sdxi->dev, "activation timed out, current state: %s\n", + gsv_str(status)); + return ret; + } + + if (status =3D=3D SDXI_GSV_ERROR) { + dev_err(sdxi->dev, "went to error state during activation\n"); + return -EIO; + } + + dev_dbg(sdxi->dev, "activated\n"); + return 0; +} + /* Get the device to the GSV_STOP state. */ static int sdxi_dev_stop(struct sdxi_dev *sdxi) { @@ -229,7 +265,11 @@ static int sdxi_fn_activate(struct sdxi_dev *sdxi) if (err) return err; =20 - return 0; + /* + * SDXI 1.0 4.1.8.9: Set MMIO_CTL0.fn_gsr to GSRV_ACTIVE and + * wait for MMIO_STS0.fn_gsv to reach GSV_ACTIVE or GSV_ERROR. + */ + return sdxi_dev_start(sdxi); } =20 static int sdxi_device_init(struct sdxi_dev *sdxi) @@ -290,6 +330,14 @@ int sdxi_register(struct device *dev, const struct sdx= i_bus_ops *ops) } EXPORT_SYMBOL_NS_GPL(sdxi_register, "SDXI"); =20 +void sdxi_unregister(struct device *dev) +{ + struct sdxi_dev *sdxi =3D dev_get_drvdata(dev); + + sdxi_dev_stop(sdxi); +} +EXPORT_SYMBOL_NS_GPL(sdxi_unregister, "SDXI"); + MODULE_AUTHOR("Wei Huang"); MODULE_AUTHOR("Nathan Lynch"); MODULE_DESCRIPTION("SDXI core"); diff --git a/drivers/dma/sdxi/pci.c b/drivers/dma/sdxi/pci.c index 42e8af008b10..4d7d6812da6d 100644 --- a/drivers/dma/sdxi/pci.c +++ b/drivers/dma/sdxi/pci.c @@ -63,6 +63,12 @@ static int sdxi_pci_probe(struct pci_dev *pdev, return sdxi_register(&pdev->dev, &sdxi_pci_ops); } =20 +static void sdxi_pci_remove(struct pci_dev *pdev) +{ + pci_disable_sriov(pdev); + sdxi_unregister(&pdev->dev); +} + static const struct pci_device_id sdxi_id_table[] =3D { { PCI_DEVICE_CLASS(PCI_CLASS_ACCELERATOR_SDXI, 0xffffff) }, { } @@ -73,6 +79,7 @@ static struct pci_driver sdxi_driver =3D { .name =3D "sdxi", .id_table =3D sdxi_id_table, .probe =3D sdxi_pci_probe, + .remove =3D sdxi_pci_remove, .sriov_configure =3D pci_sriov_configure_simple, }; =20 diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h index 903bf18bd3cc..a15b97135308 100644 --- a/drivers/dma/sdxi/sdxi.h +++ b/drivers/dma/sdxi/sdxi.h @@ -64,6 +64,7 @@ struct sdxi_dev { }; =20 int sdxi_register(struct device *dev, const struct sdxi_bus_ops *ops); +void sdxi_unregister(struct device *dev); =20 static inline u64 sdxi_read64(const struct sdxi_dev *sdxi, enum sdxi_reg r= eg) { --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1052B1A6834; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=cCKIMOAo+dZ3HFoH/jvj6tEVvl5P5G/9XcyRaD9Xpr3HarX/8ecVNjlYI7MnfK7lTELzZwOVDZj5lbE+TbiFtNuFY0GMl9uKxoMBZMHJpyDn3HjsuqMlMAnbcLNzhXBk140+bAF0hanmD+UBGoFKNC6VcCysBF/u4YXtu3TYK6s= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=WVxHfEur6o3vH7LAeyswUujG5b0/scfR0gbsdP/aH7k=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=jbafhpNk8dxv38atLFg5jAH+NipOieA89uRAqhApZDZbygu5EPYyqfAgpwMVo3qfCED5I8Yo6XC0KXh6e7sWjOb0ghSvem3QVSVv9vYrDK/Witdt9J9Ry3k1RVq7hmgQnAsOQ1bkqVkJW/Ci0Lg5EKK1nx44Y5HFyFSK9GFZDSo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=bICP3Kqw; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="bICP3Kqw" Received: by smtp.kernel.org (Postfix) with ESMTPS id E22A9C2BCC6; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704142; bh=WVxHfEur6o3vH7LAeyswUujG5b0/scfR0gbsdP/aH7k=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=bICP3KqwGb+Rcr9+VjQmoUUeAD+RWUNy+LQHEdfX1g711PdLkO43QMwCRgDF6xbCl 8NvOfr1b+FAngpUesshyVUxAvD7knLra8fAXD5Otb40IxXL20Ag2WuF8eIyHj2e/Gx 0KHeECaFq46x+cYauQWipXs1v4LcZXOtkN2rUF9Q86+0gATHUnz7Prq0PQCZsZaJZM /PmJxZsJWuAQT3e5y63xc+hF+O7tFw632DlVkLpCf3QH2U0mdkUsh6Rcw5xz6y6bhU TNQ+i98EW6kUh5I55+Z389OfQfGF0itEcNyPK12Nl1Wu5b741EtG6HEqZH5VGduCTN 9TEVODDYJewqA== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id D94A0CD8C87; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:13 -0500 Subject: [PATCH v3 10/23] dmaengine: sdxi: Complete administrative context jump start 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: <20260605-sdxi-base-v3-10-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=2039; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=Xz7O1bmLJ7W3hisyPklvsix3wrpdn8nowta4bg4ztKU=; b=bBfy3bckto5YkTDFV48vvpTAsuE3lLh6h4IVtlPaE2wYbyYBuxemg+UbGB3UxB2untV4Sgd1L fdFf5AdtBQ4DF7SVjqKz/EQTEII7Yo38JBMUDxDtd0235zYQVuVOQYb X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Now that the SDXI function has been placed in active state, the admin context can finally be started by writing its doorbell. Introduce a sdxi_cxt_push_doorbell() helper to simplify this for callers; it will be used in all descriptor submission paths. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/context.h | 6 ++++++ drivers/dma/sdxi/device.c | 15 ++++++++++++++- 2 files changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h index 65b773446ba3..d89e026a7736 100644 --- a/drivers/dma/sdxi/context.h +++ b/drivers/dma/sdxi/context.h @@ -7,6 +7,7 @@ #define DMA_SDXI_CONTEXT_H =20 #include +#include #include =20 #include "hw.h" @@ -58,4 +59,9 @@ struct sdxi_cxt { =20 int sdxi_admin_cxt_init(struct sdxi_dev *sdxi); =20 +static inline void sdxi_cxt_push_doorbell(struct sdxi_cxt *cxt, u64 index) +{ + writeq(index, cxt->db); +} + #endif /* DMA_SDXI_CONTEXT_H */ diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index e8f087f758fd..b875d8cdb58a 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -269,7 +269,20 @@ static int sdxi_fn_activate(struct sdxi_dev *sdxi) * SDXI 1.0 4.1.8.9: Set MMIO_CTL0.fn_gsr to GSRV_ACTIVE and * wait for MMIO_STS0.fn_gsv to reach GSV_ACTIVE or GSV_ERROR. */ - return sdxi_dev_start(sdxi); + err =3D sdxi_dev_start(sdxi); + if (err) + return err; + + /* + * SDXI 1.0 4.1.8.10.b: Start the admin context using method + * #3 ("Jump Start 1") from 4.3.4 Starting A Context and + * Context Signaling. We haven't queued any descriptors to the + * admin context at this point, so the appropriate value for + * the doorbell is 0. + */ + sdxi_cxt_push_doorbell(sdxi->admin_cxt, 0); + + return 0; } =20 static int sdxi_device_init(struct sdxi_dev *sdxi) --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1DF4E1D89EF; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=YUXsrsWXvFPeNvh7LHShjJZMbH/xbt34RueAsgBQZ5myj+ABM8reHJVc1bXKToTtkK9/eZfTaW744Vj6qmtB6eBQZS0JBoPvimZWDflUBkXfeF3YnhCaLigyCrcCHoi3uxKNw0hgA6cmEqHTDlwkPo5XeaOqVCHVbhZhxqKr0Ns= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=M8N4adi5bqCBOERwaGDpd/naV5mIBnYqVcOdJPhlkis=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=UAujI8Vbwc16cgfJa9DgTw40cwh5lPPxvSQiKLlyHBzmM5DUVoD4GdOOS6VtorltzbVmxEPFqj1tuIx9wQjMDb5U9fKKuRXslpUBVN6bCi5KZS4OxVZCBUmRAuGRw6dhpxqp7+F/KxKwSLf8xAwHEz9+B9WKUl3jh5J7sgKUrgY= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=GG7IF7cD; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="GG7IF7cD" Received: by smtp.kernel.org (Postfix) with ESMTPS id F1BD2C2BCF5; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=M8N4adi5bqCBOERwaGDpd/naV5mIBnYqVcOdJPhlkis=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=GG7IF7cDHmYVzECLAWSBelftYDACHIdNHPlN1nnFf8lMNghG5W7A0jBWvCnw2vWKN 8RG93Bwg8XnlRj3LhiTvODbq2c4wxlqbfnZ7mP77udInkujBfzFv4+Sdt/eqlu9+W0 S9kv/JlcgyGtnrYLFDreRcxr89uznNv8Z7vqrFbw11CCTIl5qam2u+cSRk5gyMT5sp dcyvv24sT3mmlj7fNuQi7+eLs+IlLKHaPpk8P25ankphgDTPr2roOZFfPlnUWekPjh jIABcsoPB/h64Jabd2x8Rt1ApcMhR5hIcRzzwQDXOfyW7hpwwXVoWY72NWeN++qBJY 6ijMSXmFN+fYA== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id E93BACD8C88; Sat, 6 Jun 2026 00:02:22 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:14 -0500 Subject: [PATCH v3 11/23] dmaengine: sdxi: Add client context alloc and release APIs 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: <20260605-sdxi-base-v3-11-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=7890; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=bg5O6c12/89MBViyHySgKBGfrFpvaHJA7C+k35wt+Xk=; b=b2eWWMlJFn47HBaF90EaILUcVFrLeyTss8WVO8xbtXgltu/vm0TPi+mZ/j7kzMQsepeKzHGmU BkH4MZ3BkSNAf8eV7BjpUML8Jp3sCJxawCa/wh4y4+lxKNFsM/98KcF X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Expose sdxi_cxt_new() and sdxi_cxt_exit(), which are the rest of the driver's entry points to creating and releasing SDXI contexts. Track client contexts in a device-wide allocating xarray, mapping context ID to the context object. The admin context always has ID 0, so begin allocations at 1. Define a local sdxi_cxt_id class to facilitate early allocation (before committing more resources) and automatic release of context IDs. Introduce new code to invalidate a context's entry in the L1 table on deallocation. Support for starting and stopping contexts will be added in changes to follow. The only expected user of sdxi_cxt_new() and sdxi_cxt_exit() at this point is the DMA engine provider code where a client context per channel will be created. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/context.c | 122 +++++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/context.h | 13 +++++ drivers/dma/sdxi/device.c | 8 +++ drivers/dma/sdxi/sdxi.h | 2 + 4 files changed, 145 insertions(+) diff --git a/drivers/dma/sdxi/context.c b/drivers/dma/sdxi/context.c index cc99fe9ecf92..2f9a29df5d9c 100644 --- a/drivers/dma/sdxi/context.c +++ b/drivers/dma/sdxi/context.c @@ -44,6 +44,10 @@ static void sdxi_free_cxt(struct sdxi_cxt *cxt) struct sdxi_dev *sdxi =3D cxt->sdxi; struct sdxi_sq *sq =3D cxt->sq; =20 + /* Release the id if this is a client context. */ + if (cxt->id) + WARN_ON(xa_erase(&sdxi->client_cxts, cxt->id) !=3D cxt); + if (cxt->cxt_ctl) dma_pool_free(sdxi->cxt_ctl_pool, cxt->cxt_ctl, cxt->cxt_ctl_dma); @@ -154,6 +158,16 @@ static int configure_cxt_ctl(struct sdxi_cxt_ctl *ctl,= const struct sdxi_cxt_ctl return 0; } =20 +static void invalidate_cxtl_ctl(struct sdxi_cxt_ctl *ctl) +{ + u64 ds_ring_ptr =3D le64_to_cpu(ctl->ds_ring_ptr); + + FIELD_MODIFY(SDXI_CXT_CTL_VL, &ds_ring_ptr, 0); + WRITE_ONCE(ctl->ds_ring_ptr, cpu_to_le64(ds_ring_ptr)); + dma_wmb(); + *ctl =3D (typeof(*ctl)) { 0 }; +} + /* * Logical representation of CXT_L1_ENT subfields. */ @@ -208,6 +222,16 @@ static int configure_L1_entry(struct sdxi_cxt_L1_ent *= ent, return 0; } =20 +static void invalidate_L1_entry(struct sdxi_cxt_L1_ent *ent) +{ + u64 cxt_ctl_ptr =3D le64_to_cpu(ent->cxt_ctl_ptr); + + FIELD_MODIFY(SDXI_CXT_L1_ENT_VL, &cxt_ctl_ptr, 0); + WRITE_ONCE(ent->cxt_ctl_ptr, cpu_to_le64(cxt_ctl_ptr)); + dma_wmb(); + *ent =3D (typeof(*ent)) { 0 }; +} + /* * Make the context control structure hierarchy valid from the POV of * the SDXI implementation. This may eventually involve allocation of @@ -258,6 +282,17 @@ static int sdxi_publish_cxt(const struct sdxi_cxt *cxt) /* todo: need to send DSC_CXT_UPD to admin */ } =20 +/* Invalidate a context. */ +static void sdxi_rescind_cxt(struct sdxi_cxt *cxt) +{ + u8 l1_idx =3D ID_TO_L1_INDEX(cxt->id); + struct sdxi_cxt_L1_ent *ent =3D &cxt->sdxi->L1_table->entry[l1_idx]; + + invalidate_L1_entry(ent); + invalidate_cxtl_ctl(cxt->cxt_ctl); + /* todo: need to send DSC_CXT_UPD to admin */ +} + static void free_admin_cxt(void *ptr) { struct sdxi_dev *sdxi =3D ptr; @@ -288,3 +323,90 @@ int sdxi_admin_cxt_init(struct sdxi_dev *sdxi) =20 return devm_add_action_or_reset(sdxi->dev, free_admin_cxt, sdxi); } + +/* + * Temporary owner for context id until it can be assigned to a + * context object; enables scope-based cleanup. + */ +struct sdxi_cxt_id { + struct sdxi_dev *sdxi; + u16 index; +}; + +static void sdxi_cxt_id_dtor(const struct sdxi_cxt_id *cxt_id) +{ + if (cxt_id->index =3D=3D 0) + return; + WARN_ON(xa_erase(&cxt_id->sdxi->client_cxts, cxt_id->index) !=3D NULL); +} + +static struct sdxi_cxt_id sdxi_cxt_id_ctor(struct sdxi_dev *sdxi) +{ + struct xa_limit limit =3D XA_LIMIT(1, sdxi->max_cxtid); + u32 index; + + return (struct sdxi_cxt_id) { + .sdxi =3D sdxi, + .index =3D xa_alloc(&sdxi->client_cxts, &index, NULL, + limit, GFP_KERNEL) ? 0 : (u16)index, + }; +} + +DEFINE_CLASS(sdxi_cxt_id, struct sdxi_cxt_id, sdxi_cxt_id_dtor(&_T), + sdxi_cxt_id_ctor(sdxi), struct sdxi_dev *sdxi) + +static bool sdxi_cxt_id_valid(const struct sdxi_cxt_id *cxt_id) +{ + return cxt_id->index > 0; +} + +/* + * Transfer ownership of the id to the context object, recording the + * context pointer in the device's client_cxt xarray. sdxi_cxt_free() + * is responsible for releasing the id from now on. + */ +static void sdxi_cxt_id_assign(struct sdxi_cxt *cxt, struct sdxi_cxt_id *c= xt_id) +{ + /* We reserved the space in the constructor so this should not fail. */ + WARN_ON(xa_store(&cxt_id->sdxi->client_cxts, + cxt_id->index, cxt, GFP_KERNEL)); + cxt->id =3D cxt_id->index; + cxt_id->index =3D 0; +} + +/* + * Allocate a context for in-kernel use. Starting the context is the + * caller's responsibility. + */ +struct sdxi_cxt *sdxi_cxt_new(struct sdxi_dev *sdxi) +{ + /* + * Ensure an ID is available before allocating memory for the + * context and its control structures. + */ + CLASS(sdxi_cxt_id, id)(sdxi); + if (!sdxi_cxt_id_valid(&id)) + return NULL; + + struct sdxi_cxt *cxt __free(sdxi_cxt) =3D sdxi_alloc_cxt(sdxi); + if (!cxt) + return NULL; + + sdxi_cxt_id_assign(cxt, &id); + + cxt->db =3D sdxi->dbs + cxt->id * sdxi->db_stride; + + if (sdxi_publish_cxt(cxt)) + return NULL; + + return_ptr(cxt); +} + +void sdxi_cxt_exit(struct sdxi_cxt *cxt) +{ + if (WARN_ON(sdxi_cxt_is_admin(cxt))) + return; + + sdxi_rescind_cxt(cxt); + sdxi_free_cxt(cxt); +} diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h index d89e026a7736..42e377bb2446 100644 --- a/drivers/dma/sdxi/context.h +++ b/drivers/dma/sdxi/context.h @@ -59,6 +59,19 @@ struct sdxi_cxt { =20 int sdxi_admin_cxt_init(struct sdxi_dev *sdxi); =20 +struct sdxi_cxt *sdxi_cxt_new(struct sdxi_dev *sdxi); +void sdxi_cxt_exit(struct sdxi_cxt *cxt); + +static inline struct sdxi_cxt *to_admin_cxt(const struct sdxi_cxt *cxt) +{ + return cxt->sdxi->admin_cxt; +} + +static inline bool sdxi_cxt_is_admin(const struct sdxi_cxt *cxt) +{ + return cxt =3D=3D to_admin_cxt(cxt); +} + static inline void sdxi_cxt_push_doorbell(struct sdxi_cxt *cxt, u64 index) { writeq(index, cxt->db); diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index b875d8cdb58a..d3d1ad2f2eff 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -18,6 +18,7 @@ #include #include #include +#include =20 #include "context.h" #include "hw.h" @@ -333,6 +334,7 @@ int sdxi_register(struct device *dev, const struct sdxi= _bus_ops *ops) =20 sdxi->dev =3D dev; sdxi->bus_ops =3D ops; + xa_init_flags(&sdxi->client_cxts, XA_FLAGS_ALLOC1); dev_set_drvdata(dev, sdxi); =20 err =3D sdxi->bus_ops->init(sdxi); @@ -346,6 +348,12 @@ EXPORT_SYMBOL_NS_GPL(sdxi_register, "SDXI"); void sdxi_unregister(struct device *dev) { struct sdxi_dev *sdxi =3D dev_get_drvdata(dev); + struct sdxi_cxt *cxt; + unsigned long index; + + xa_for_each(&sdxi->client_cxts, index, cxt) + sdxi_cxt_exit(cxt); + xa_destroy(&sdxi->client_cxts); =20 sdxi_dev_stop(sdxi); } diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h index a15b97135308..4e29d1f90dae 100644 --- a/drivers/dma/sdxi/sdxi.h +++ b/drivers/dma/sdxi/sdxi.h @@ -12,6 +12,7 @@ #include #include #include +#include =20 #include "mmio.h" =20 @@ -59,6 +60,7 @@ struct sdxi_dev { struct dma_pool *cst_blk_pool; =20 struct sdxi_cxt *admin_cxt; + struct xarray client_cxts; /* context id -> (struct sdxi_cxt *) */ =20 const struct sdxi_bus_ops *bus_ops; }; --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2B9981E376C; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=eQISRIG1Sx7K77UyBoDi57+9O9SEsujjKc9bo/QxrPJkM3E9poLe672GHeMtj2lbvTkQcAFZv57WSJgDNaT7V0ZsXHq9u+T20V3P8glMKRiVMRzKpzOG02XlmhWMdxQ9Oy8fNA1idnml46rCsrVFMXcI8LybgcoQzuFarcZ42GI= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=3r8qAeadjqF7U6wgSq1wgMd5o+VrpDZ0Osek0TCOqQA=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=bzmageyuIQDKyLRdeIKmPhboobJ2DJC4mgZmgpQNO0FM4rcYNjB6lxPt8ID80PvZSPvGtzLv5OO5X5HnMNRMtfTV9rfbimIVk3ha2op0HKzlvn55dZy7oIMtt5pMSRF9tLRqC0ooKN+BFH0nsj///oGdiytr7qX2EzjdRgRG5qo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=ceHoYd7V; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="ceHoYd7V" Received: by smtp.kernel.org (Postfix) with ESMTPS id 0BD4FC2BCFB; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=3r8qAeadjqF7U6wgSq1wgMd5o+VrpDZ0Osek0TCOqQA=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=ceHoYd7VNVDv/3Kpi9ukx8+QJ9Q0wv5m/T3XS//wugDkCnMCPhvGRWbFTvM2B6hS0 unxH8u+SAGNbk3/VsDQ5ijsce1jjSvuII7iZttW0hdfoTvMBSHaXJuERiQXgfYi270 Wa+sCUc2fxtUMHyOxJpPUsD9APpJBsJ1n+0+GOqQO3RpF6bD0qNunA+88TXM7kKvh3 Zz0jQn6yQdyFF5SPVkHCz2WG3HGMO6QdBF8NXRZaumuJ0NuvqvrsRX9WMRvYeuTerW SoZvy2HIZQWDdCywlDVQiRhvnXJGEk4OCVu7Cz/8jiBSESGlBYqAvDnmk+pIeqiCbl vFs+Ap9AlOPSA== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 05224CD6E7C; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:15 -0500 Subject: [PATCH v3 12/23] dmaengine: sdxi: Add descriptor ring 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: <20260605-sdxi-base-v3-12-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=9311; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=dJ2kLZpgYp+5rraz3GSkb+EuvGuJnIu5vJ8Fkw1RpTc=; b=uYXRsuaJsLgpTfCQzCpN60PLsGx021Ah9Z17RB7p+PmgeT9VvYEztIcuJ6KxHy3kBDUKxmiSy c06dU1wXds9C7osbsx+TVN84obv55Isq3zaRkz66fGY2zzfeAz0tCQl X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Introduce a library for managing SDXI descriptor ring state. It encapsulates determining the next free space in the ring to deposit descriptors and performing the update of the write index correctly, as well as iterating over slices (reservations) of the ring without dealing directly with ring offsets/indexes. The central abstraction is sdxi_ring_state, which maintains the write index and a wait queue. An internal spin lock serializes checks for space in the ring and updates to the write index. Reservations (sdxi_ring_resv) are intended to be short-lived on-stack objects representing slices of the ring for callers to populate with descriptors. Both blocking and non-blocking reservation APIs are provided. Descriptor access within a reservation is provided via sdxi_ring_resv_next() and sdxi_ring_resv_foreach(). Completion handlers must call sdxi_ring_wake_up() when descriptors have been consumed so that blocked reservations can proceed. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/Makefile | 3 +- drivers/dma/sdxi/ring.c | 159 ++++++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/ring.h | 84 ++++++++++++++++++++++++ 3 files changed, 245 insertions(+), 1 deletion(-) diff --git a/drivers/dma/sdxi/Makefile b/drivers/dma/sdxi/Makefile index cdf8a455077b..bfcb443f1e64 100644 --- a/drivers/dma/sdxi/Makefile +++ b/drivers/dma/sdxi/Makefile @@ -2,7 +2,8 @@ obj-$(CONFIG_SDXI_CORE) +=3D sdxi-core.o sdxi-core-y :=3D \ context.o \ - device.o + device.o \ + ring.o =20 obj-$(CONFIG_SDXI_PCI) +=3D sdxi-pci.o sdxi-pci-y :=3D pci.o diff --git a/drivers/dma/sdxi/ring.c b/drivers/dma/sdxi/ring.c new file mode 100644 index 000000000000..91b28c7afbbf --- /dev/null +++ b/drivers/dma/sdxi/ring.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI descriptor ring state management. Handles advancing the write + * index correctly and supplies "reservations" i.e. slices of the ring + * to be filled with descriptors. + * + * Copyright Advanced Micro Devices, Inc. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ring.h" +#include "hw.h" + +/* + * Initialize ring management state. Caller is responsible for + * allocating, mapping, and initializing the actual control structures + * shared with hardware: the indexes and ring array. + */ +void sdxi_ring_state_init(struct sdxi_ring_state *rs, const __le64 *read_i= ndex, + __le64 *write_index, u32 entries, + struct sdxi_desc descs[static SZ_1K]) +{ + WARN_ON_ONCE(!read_index); + WARN_ON_ONCE(!write_index); + /* + * See SDXI 1.0 Table 3-1 Memory Structure Summary. Minimum + * descriptor ring size in bytes is 64KB; thus 1024 64-byte + * entries. + */ + WARN_ON_ONCE(entries < SZ_1K); + + *rs =3D (typeof(*rs)) { + .write_index =3D le64_to_cpu(*write_index), + .write_index_ptr =3D write_index, + .read_index_ptr =3D read_index, + .entries =3D entries, + .entry =3D descs, + }; + spin_lock_init(&rs->lock); + init_waitqueue_head(&rs->wqh); +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_ring_state_init); + +static u64 sdxi_ring_state_load_ridx(struct sdxi_ring_state *rs) +{ + lockdep_assert_held(&rs->lock); + return le64_to_cpu(READ_ONCE(*rs->read_index_ptr)); +} + +static void sdxi_ring_state_store_widx(struct sdxi_ring_state *rs, u64 new= _widx) +{ + lockdep_assert_held(&rs->lock); + rs->write_index =3D new_widx; + WRITE_ONCE(*rs->write_index_ptr, cpu_to_le64(new_widx)); +} + +/* Non-blocking ring reservation. Callers must handle ring full (-EBUSY). = */ +int sdxi_ring_try_reserve(struct sdxi_ring_state *rs, size_t nr, + struct sdxi_ring_resv *resv) +{ + u64 new_widx; + + /* + * Caller bug, warn and reject. + */ + if (WARN_ONCE(nr < 1 || nr > rs->entries, + "Reservation of size %zu requested from ring of size %u\n", + nr, rs->entries)) + return -EINVAL; + + scoped_guard(spinlock_irqsave, &rs->lock) { + u64 ridx =3D sdxi_ring_state_load_ridx(rs); + + /* + * Bug: the read index should never exceed the write index. + * TODO: sdxi_err() or similar; need a reference to + * the device. + */ + if (ridx > rs->write_index) + return -EIO; + + new_widx =3D rs->write_index + nr; + + /* + * Not enough space available right now. + * TODO: sdxi_dbg() or tracepoint here. + */ + if (new_widx - ridx > rs->entries) + return -EBUSY; + + sdxi_ring_state_store_widx(rs, new_widx); + } + + *resv =3D (typeof(*resv)) { + .rs =3D rs, + .range =3D { + .start =3D new_widx - nr, + .end =3D new_widx - 1, + }, + .iter =3D new_widx - nr, + }; + + return 0; +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_ring_try_reserve); + +/* Blocking ring reservation. Retries until success or non-transient error= . */ +int sdxi_ring_reserve(struct sdxi_ring_state *rs, size_t nr, + struct sdxi_ring_resv *resv) +{ + int ret; + + wait_event(rs->wqh, + (ret =3D sdxi_ring_try_reserve(rs, nr, resv)) !=3D -EBUSY); + + return ret; +} + +/* Completion code should call this whenever descriptors have been consume= d. */ +void sdxi_ring_wake_up(struct sdxi_ring_state *rs) +{ + wake_up_all(&rs->wqh); +} + +static struct sdxi_desc * +sdxi_desc_ring_entry(const struct sdxi_ring_state *rs, u64 index) +{ + return &rs->entry[do_div(index, rs->entries)]; +} + +struct sdxi_desc *sdxi_ring_resv_next(struct sdxi_ring_resv *resv) +{ + if (resv->range.start <=3D resv->iter && resv->iter <=3D resv->range.end) + return sdxi_desc_ring_entry(resv->rs, resv->iter++); + /* + * Caller has iterated to the end of the reservation. + */ + if (resv->iter =3D=3D resv->range.end + 1) + return NULL; + /* + * Should happen only if caller messed with internal + * reservation state. + */ + WARN_ONCE(1, "reservation[%llu,%llu] with iter %llu", + resv->range.start, resv->range.end, resv->iter); + return NULL; +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_ring_resv_next); diff --git a/drivers/dma/sdxi/ring.h b/drivers/dma/sdxi/ring.h new file mode 100644 index 000000000000..d5682687c05c --- /dev/null +++ b/drivers/dma/sdxi/ring.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright Advanced Micro Devices, Inc. */ +#ifndef DMA_SDXI_RING_H +#define DMA_SDXI_RING_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "hw.h" + +/* + * struct sdxi_ring_state - Descriptor ring management. + * + * @lock: Guards *read_index_ptr (RO), *write_index_ptr (RW), + * write_index (RW). *read_index is incremented by hw. + * @write_index: Cached write index value, minimizes dereferences in + * critical sections. + * @write_index_ptr: Location of the architected write index shared with + * the SDXI implementation. + * @read_index_ptr: Location of the architected read index shared with + * the SDXI implementation. + * @entries: Number of entries in the ring. + * @entry: The descriptor ring itself, shared with the SDXI implementation. + * @wqh: Pending reservations. + */ +struct sdxi_ring_state { + spinlock_t lock; + u64 write_index; /* Cache current value of write index. */ + __le64 *write_index_ptr; + const __le64 *read_index_ptr; + u32 entries; + struct sdxi_desc *entry; + wait_queue_head_t wqh; +}; + +/* + * Ring reservation and iteration state. + */ +struct sdxi_ring_resv { + const struct sdxi_ring_state *rs; + struct range range; + u64 iter; +}; + +void sdxi_ring_state_init(struct sdxi_ring_state *ring, const __le64 *read= _index, + __le64 *write_index, u32 entries, + struct sdxi_desc descs[static SZ_1K]); +void sdxi_ring_wake_up(struct sdxi_ring_state *rs); +int sdxi_ring_reserve(struct sdxi_ring_state *ring, size_t nr, + struct sdxi_ring_resv *resv); +int sdxi_ring_try_reserve(struct sdxi_ring_state *ring, size_t nr, + struct sdxi_ring_resv *resv); +struct sdxi_desc *sdxi_ring_resv_next(struct sdxi_ring_resv *resv); + +/* Reset reservation's internal iterator. */ +static inline void sdxi_ring_resv_reset(struct sdxi_ring_resv *resv) +{ + resv->iter =3D resv->range.start; +} + +/* + * Return the value that should be written to the doorbell after + * serializing descriptors for this reservation, i.e. the value of the + * write index after obtaining the reservation. + */ +static inline u64 sdxi_ring_resv_dbval(const struct sdxi_ring_resv *resv) +{ + return resv->range.end + 1; +} + +#define sdxi_ring_resv_foreach(resv_, desc_) \ + for (sdxi_ring_resv_reset(resv_), \ + desc_ =3D sdxi_ring_resv_next(resv_); \ + desc_; \ + desc_ =3D sdxi_ring_resv_next(resv_)) + +#endif /* DMA_SDXI_RING_H */ --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 4155722068D; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=WOJHgl1Huk5aT0pXj+ctDvlUJNCq+Ge+kv5w1KNdoe2HsYxs8jjTD4YtIXPQdS3LcYyxU3mXiLAfHT7tTQ0uXoG7he5UOK3nbtozYTvjNC7Lj+SeEQ/hDiwZeaYrPzxwCL9PP5bkJ0/5AA2YQ+ypB17FTeKog7qzb7oJJyKZ3E4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=Flk3OzgFJwdu7qVBc8FGZ7a1yxRFBhW7x/D8pU+MqB0=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=lHu3WFENB5iTMrlw2qL72EpDiodoYVdWp6cB+wMIGPgtRVFl8x9r71wdcfC9o8L67Tpa1peoZOPdb7vp6Vk9ZwdFm/ZDJ86VNY6iY9It2sJNoU6SS7uyu7Xiiu7/xkA9ka2xXcMRMT5oFvTaNtdqGatgvYENwocOJEDOY4bs8w8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=hx/eyYE9; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="hx/eyYE9" Received: by smtp.kernel.org (Postfix) with ESMTPS id 1FAC8C4AF0F; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=Flk3OzgFJwdu7qVBc8FGZ7a1yxRFBhW7x/D8pU+MqB0=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=hx/eyYE9DYjsY8Buz7C/ZhgC2646nMWG1767LVHdi+/QdPv8neyhZu/YpX0KHvu6J PMMxaivuMjQe6VP9MAc4MU5idE5WjFZKpKtqUfOl8lYUJF5l3xO6+KKDmFzwcLJ2QS +XNcaW2EwhQa7xiKu33dU3Ybzf8GDIPUyXAGY6KpbW7bmoH3960vH6UmDMsGMdyG7Y Z9S5tiOlL04jjMWiRtMWaFsquGJHNYTSN6GnMrM5EiKdoXbmYGJAw02cZcFQdfOsZy uYKcT91jvhQ37jKohGWRhz7GqyhnoOmTa3lNc9UZ6sn8H7AHL5q0PB5nFN49DLFOox t9mRmy8givqPg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 14FF2CD6E7B; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:16 -0500 Subject: [PATCH v3 13/23] dmaengine: sdxi: Add unit tests for descriptor ring reservations 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: <20260605-sdxi-base-v3-13-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=5291; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=AjqlcR1J/MdjgT8HA14M/iwSkOjphEY9WGqJW4+YCzE=; b=D0VFz6DmNWL9JA+2QGNBo5wg4j3HDEu7MZMwXhngMRfX1Tsd46uFat+ytjhWOuWlk3/NxUDjb UtfW0FaBUrhBLYJphGbugTqK1aY978WWZ00cwFNUKAAINj3m9HFmrHH X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Add KUnit tests for the descriptor ring reservation API, covering: - Valid reservations: full-ring and single-slot after advancing the read pointer. - Error paths: zero or over-capacity count (-EINVAL), inconsistent index state (-EIO), and insufficient space (-EBUSY). A .kunitconfig is included ease of use: $ tools/testing/kunit/kunit.py run \ --kunitconfig=3Ddrivers/dma/sdxi/.kunitconfig No SDXI hardware is required to run these tests. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/.kunitconfig | 4 ++ drivers/dma/sdxi/Kconfig | 10 ++++ drivers/dma/sdxi/Makefile | 3 ++ drivers/dma/sdxi/ring_kunit.c | 105 ++++++++++++++++++++++++++++++++++++++= ++++ 4 files changed, 122 insertions(+) diff --git a/drivers/dma/sdxi/.kunitconfig b/drivers/dma/sdxi/.kunitconfig new file mode 100644 index 000000000000..16a1ae04b156 --- /dev/null +++ b/drivers/dma/sdxi/.kunitconfig @@ -0,0 +1,4 @@ +CONFIG_KUNIT=3Dy +CONFIG_DMADEVICES=3Dy +CONFIG_SDXI_CORE=3Dy +CONFIG_SDXI_KUNIT_TEST=3Dy diff --git a/drivers/dma/sdxi/Kconfig b/drivers/dma/sdxi/Kconfig index b91b44231a04..7217375c9216 100644 --- a/drivers/dma/sdxi/Kconfig +++ b/drivers/dma/sdxi/Kconfig @@ -26,3 +26,13 @@ config SDXI_PCI =20 To compile this driver as a module, choose M here: the module will be named "sdxi-pci". + +config SDXI_KUNIT_TEST + tristate "SDXI unit tests" if !KUNIT_ALL_TESTS + depends on SDXI_CORE && KUNIT + default KUNIT_ALL_TESTS + help + KUnit tests for parts of the SDXI driver. Does not require + SDXI hardware. + + If unsure, say N. diff --git a/drivers/dma/sdxi/Makefile b/drivers/dma/sdxi/Makefile index bfcb443f1e64..00e3f1cb0808 100644 --- a/drivers/dma/sdxi/Makefile +++ b/drivers/dma/sdxi/Makefile @@ -7,3 +7,6 @@ sdxi-core-y :=3D \ =20 obj-$(CONFIG_SDXI_PCI) +=3D sdxi-pci.o sdxi-pci-y :=3D pci.o + +obj-$(CONFIG_SDXI_KUNIT_TEST) +=3D \ + ring_kunit.o diff --git a/drivers/dma/sdxi/ring_kunit.c b/drivers/dma/sdxi/ring_kunit.c new file mode 100644 index 000000000000..3bc7073e0c39 --- /dev/null +++ b/drivers/dma/sdxi/ring_kunit.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI descriptor ring management tests. + * + * Copyright Advanced Micro Devices, Inc. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ring.h" + +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); + +static void valid(struct kunit *t) +{ + __le64 wi, ri; + struct sdxi_ring_state r; + struct sdxi_ring_resv resv; + struct sdxi_desc *descs, *desc; + + + descs =3D kunit_kmalloc_array(t, SZ_1K, sizeof(descs[0]), + GFP_KERNEL | __GFP_ZERO); + KUNIT_ASSERT_NOT_NULL(t, descs); + + ri =3D wi =3D 0; + sdxi_ring_state_init(&r, &ri, &wi, SZ_1K, descs); + + KUNIT_EXPECT_EQ(t, sdxi_ring_try_reserve(&r, r.entries, &resv), 0); + KUNIT_EXPECT_EQ(t, resv.range.start, 0); + KUNIT_EXPECT_EQ(t, resv.range.end, r.entries - 1); + KUNIT_EXPECT_EQ(t, le64_to_cpu(wi), r.entries); + sdxi_ring_resv_foreach(&resv, desc) { + KUNIT_EXPECT_NOT_NULL_MSG(t, sdxi_ring_resv_next(&resv), + "unexpected null descriptor for index %llu", resv.iter); + } + + ri =3D cpu_to_le64(1); + KUNIT_EXPECT_EQ(t, sdxi_ring_try_reserve(&r, 1, &resv), 0); + KUNIT_EXPECT_EQ(t, le64_to_cpu(wi), r.entries + 1); + KUNIT_EXPECT_NOT_NULL(t, sdxi_ring_resv_next(&resv)); +} + +static void invalid(struct kunit *t) +{ + __le64 wi, ri; + struct sdxi_ring_state rs; + struct sdxi_ring_resv resv; + struct sdxi_desc *descs; + + descs =3D kunit_kmalloc_array(t, SZ_1K, sizeof(descs[0]), + GFP_KERNEL | __GFP_ZERO); + KUNIT_ASSERT_NOT_NULL(t, descs); + + ri =3D wi =3D 0; + sdxi_ring_state_init(&rs, &ri, &wi, SZ_1K, descs); + + KUNIT_EXPECT_EQ(t, sdxi_ring_try_reserve(&rs, 0, &resv), -EINVAL); + KUNIT_EXPECT_EQ(t, sdxi_ring_try_reserve(&rs, rs.entries + 1, &resv), -EI= NVAL); + + ri =3D cpu_to_le64(1); + KUNIT_EXPECT_EQ(t, sdxi_ring_try_reserve(&rs, 1, &resv), -EIO); + + ri =3D 0; + wi =3D cpu_to_le64(rs.entries); + sdxi_ring_state_init(&rs, &ri, &wi, SZ_1K, descs); + KUNIT_EXPECT_EQ(t, sdxi_ring_try_reserve(&rs, 1, &resv), -EBUSY); + + ri =3D cpu_to_le64(rs.entries); + wi =3D cpu_to_le64(rs.entries + 1); + sdxi_ring_state_init(&rs, &ri, &wi, SZ_1K, descs); + KUNIT_EXPECT_EQ(t, sdxi_ring_try_reserve(&rs, rs.entries, &resv), -EBUSY); +} + +static struct kunit_case testcases[] =3D { + KUNIT_CASE(valid), + KUNIT_CASE(invalid), + {} +}; + +static int setup_device(struct kunit *t) +{ + struct device *dev =3D kunit_device_register(t, "sdxi-mock-device"); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(t, dev); + t->priv =3D dev; + return 0; +} + +static struct kunit_suite generic_desc_ts =3D { + .name =3D "SDXI descriptor ring management", + .test_cases =3D testcases, + .init =3D setup_device, +}; +kunit_test_suite(generic_desc_ts); + +MODULE_DESCRIPTION("SDXI descriptor ring tests"); +MODULE_AUTHOR("Nathan Lynch"); +MODULE_LICENSE("GPL"); --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 57F4323A564; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=Uy7EvSLupLOnTU5SL5ZaCG3PHXpiFOPAvVT+c/DeRVA2MlOX31IDOz/robiU+1O+sRcLQL2nMHEOI6N8OrYkRYwXLAQvff0CEP8qjdRklUzGoqSSXaCacI/FC5JC7nDXZQaod+6exBwqx/dPrymM3nwgg+ucfPTufejYdjkDGDM= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=ztZGiysJV/gPfTV1Ym4VhCsPMKgV5j+h5TarXurHmQI=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=fhkM2WkI1DWf5B00OhVqca+BA/TlgyhoeBpLyHnePPE05tS7KsbTNFUWZ3wewrMuUM3VNqRHDyA3BY490hBRNr3wHrx3usexPBqmEtIJQKV/hcAlph9b1fN43PK9MqcvBLk+7J6dSPG5bIDVPngTDh9N6qJgBXn9q4FkdOMtuDk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=DCvjReyY; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="DCvjReyY" Received: by smtp.kernel.org (Postfix) with ESMTPS id 36B66C2BCC6; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=ztZGiysJV/gPfTV1Ym4VhCsPMKgV5j+h5TarXurHmQI=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=DCvjReyYaJpZTWPpHaDhyira77BdrJfFE7Ly5P0qlXJKS+1eaG5tAxwn8QGPlCT9W hOD5ajDS7++gXj9BKUWKMQG6qc5ZcQNSNQVf3a2i0XcivwllHV7jjsXjwvvSiUOIHM GrI8VR5IZnn1QzPaqvujol6h17rMsCUG2Fw3VOaZLjxyUKOUHQhGcyMvAA8YvHkdDv LjUlA99mNG8Vz8EGg/LGu6ABwkEozW4Q82dMj6LHge84wb962ektOk/VptXqMFuAjU F5i4NvzytVdDchcpFqR/U52sg8h4eYj69aaT9SiklraJWpeJoM/fxeKwyeiXm2fMOB 1qgQVYQjpMqkQ== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2BC9BCD8C89; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:17 -0500 Subject: [PATCH v3 14/23] dmaengine: sdxi: Attach descriptor ring state to contexts 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: <20260605-sdxi-base-v3-14-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Frank Li , Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=2755; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=mVoy7jpXsiISK+5ennlQ+W8GV1ph1JWCYcEBJFYCu4k=; b=q6WmAOAvMFzetozaGdduNSq0LeWlJtfWi7PPGqLypSju4M00aSmm1VhwARCvDfjrKa7Jy4jg8 aUPFS1HhBe0B+XE0m+sSF3jWavwdQibCDNrledoQbc0Mj0SMbc8MmCN X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Attach an instance of struct sdxi_ring_state to each context upon allocation. Each ring state has the same lifetime has its context and is freed upon context release. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Frank Li Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/context.c | 14 ++++++++++++++ drivers/dma/sdxi/context.h | 2 ++ 2 files changed, 16 insertions(+) diff --git a/drivers/dma/sdxi/context.c b/drivers/dma/sdxi/context.c index 2f9a29df5d9c..907547ac450f 100644 --- a/drivers/dma/sdxi/context.c +++ b/drivers/dma/sdxi/context.c @@ -23,6 +23,7 @@ =20 #include "context.h" #include "hw.h" +#include "ring.h" #include "sdxi.h" =20 #define DEFAULT_DESC_RING_ENTRIES 1024 @@ -63,6 +64,7 @@ static void sdxi_free_cxt(struct sdxi_cxt *cxt) dma_free_coherent(sdxi->dev, sq->ring_size, sq->desc_ring, sq->ring_dma); kfree(cxt->sq); + kfree(cxt->ring_state); kfree(cxt); } =20 @@ -80,6 +82,10 @@ static struct sdxi_cxt *sdxi_alloc_cxt(struct sdxi_dev *= sdxi) =20 cxt->sdxi =3D sdxi; =20 + cxt->ring_state =3D kzalloc_obj(*cxt->ring_state, GFP_KERNEL); + if (!cxt->ring_state) + return NULL; + cxt->sq =3D kzalloc_obj(*cxt->sq, GFP_KERNEL); if (!cxt->sq) return NULL; @@ -314,6 +320,8 @@ int sdxi_admin_cxt_init(struct sdxi_dev *sdxi) sq->cxt_sts->state =3D FIELD_PREP(SDXI_CXT_STS_STATE, CXTV_RUN); cxt->id =3D SDXI_ADMIN_CXT_ID; cxt->db =3D sdxi->dbs + cxt->id * sdxi->db_stride; + sdxi_ring_state_init(cxt->ring_state, &sq->cxt_sts->read_index, + sq->write_index, sq->ring_entries, sq->desc_ring); =20 err =3D sdxi_publish_cxt(cxt); if (err) @@ -380,6 +388,8 @@ static void sdxi_cxt_id_assign(struct sdxi_cxt *cxt, st= ruct sdxi_cxt_id *cxt_id) */ struct sdxi_cxt *sdxi_cxt_new(struct sdxi_dev *sdxi) { + struct sdxi_sq *sq; + /* * Ensure an ID is available before allocating memory for the * context and its control structures. @@ -396,6 +406,10 @@ struct sdxi_cxt *sdxi_cxt_new(struct sdxi_dev *sdxi) =20 cxt->db =3D sdxi->dbs + cxt->id * sdxi->db_stride; =20 + sq =3D cxt->sq; + sdxi_ring_state_init(cxt->ring_state, &sq->cxt_sts->read_index, + sq->write_index, sq->ring_entries, sq->desc_ring); + if (sdxi_publish_cxt(cxt)) return NULL; =20 diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h index 42e377bb2446..0aebcba3dc1e 100644 --- a/drivers/dma/sdxi/context.h +++ b/drivers/dma/sdxi/context.h @@ -55,6 +55,8 @@ struct sdxi_cxt { dma_addr_t akey_table_dma; =20 struct sdxi_sq *sq; + + struct sdxi_ring_state *ring_state; }; =20 int sdxi_admin_cxt_init(struct sdxi_dev *sdxi); --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 6775B246762; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=mkBcexjolThmVD8VVtw4+YW8MKLT8Od1zSutdMO5L9BlY4hA3UaLd0qC+6RGV27k4JDnF9omq0jIsKk+zFNbH9nSEpBbSQ44v0ZnG/qExZte3RjtpG4+AJQx+Fi4DkrQR4Dukv6Xv+GnGrmJzS18q5eBZ7rqHSGdaTbzg00DiWc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=F+X2RmAvatT2COhP39e2IEdDB8GIFHIzFbu71qpGHtc=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=LRB/HXHzTJQhEjmngg0KJHj4gAXewTAZHNyeiMWrSoHCFcuzN8+rZXplXuhaqA8Hfox5BD/kHuz9z59chGJ7DIxFuQqvAfwiiwvQ3ugX/JlbfjbE0bFnxsBjqPlvzoDKhp+i3Q4gOjhA4VhcZjhVtF54F5zUjTkdrWz5W+dR9Q0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=rdYjOnq8; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="rdYjOnq8" Received: by smtp.kernel.org (Postfix) with ESMTPS id 49D9DC2BCF6; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=F+X2RmAvatT2COhP39e2IEdDB8GIFHIzFbu71qpGHtc=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=rdYjOnq8nKUVOWx3G8+voPAOiVHCBjs3MZ5JWu44oN8BigCH8FExGwK+qzUwwUnbm yEFX63fbVBSobkxw/FziVdF9JmhyCFlnWVOqGg1ZK9aCmm53tHskWK4x4LSitrousx xZvDXLlLHsiUkYuDnSrKkwDZteBV4bXS142g9kRJbAif6hywXU7itUTvN+QW+cb017 dX1F5CIDFLBSd5hWcUGQ+Sj56FYNiJc3vp4d4lGy+U38RxYGBRaCkDOWwkco50/6L4 GqqJFwGCXcuB08olDtAqqlhv6XBuhYUWvL+t+UG3vFTPACRvdXHvtSE/HPdFj+wvj0 iko9phDjCjKzw== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3D37BCD6E7B; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:18 -0500 Subject: [PATCH v3 15/23] dmaengine: sdxi: Per-context access key (AKey) table entry allocator 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: <20260605-sdxi-base-v3-15-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Frank Li , Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=4006; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=qM+QbqXnjHZY2gASGdo8Ro4hhIgKFSsWu/7lBT9zABQ=; b=8/YlrydD/Gu/C20AVCj74NOQeu2fSrtavM8mt/Ro4i0+KkIUGmUjRLeqTcNtglJZl4hY8LtTs tG/x/vFRpywAPbhPWqLmvqsQXLvCvdWZpL3XdR0gT5ehnLQgpHjgTz6 X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Each SDXI context has a table of access keys (AKeys). SDXI descriptors submitted to a context may refer to an AKey associated with that context by its index in the table. AKeys describe properties of the access that the descriptor is to perform, such as PASID or a target SDXI function, or an interrupt to trigger. Use a per-context IDA to keep track of used entries in the table. Provide sdxi_alloc_akey(), which claims an AKey table entry for the caller to program directly; sdxi_akey_index(), which returns the entry's index for programming into descriptors the caller intends to submit; and sdxi_free_akey(), which clears the entry and makes it available again. The DMA engine provider is currently the only user and allocates a single entry that encodes the access properties for copy operations and a completion interrupt. More complex use patterns are possible when user space gains access to SDXI contexts (not in this series). Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Frank Li Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/context.c | 4 ++++ drivers/dma/sdxi/context.h | 24 ++++++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/drivers/dma/sdxi/context.c b/drivers/dma/sdxi/context.c index 907547ac450f..9b0984842d9a 100644 --- a/drivers/dma/sdxi/context.c +++ b/drivers/dma/sdxi/context.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -64,6 +65,7 @@ static void sdxi_free_cxt(struct sdxi_cxt *cxt) dma_free_coherent(sdxi->dev, sq->ring_size, sq->desc_ring, sq->ring_dma); kfree(cxt->sq); + ida_destroy(&cxt->akey_ida); kfree(cxt->ring_state); kfree(cxt); } @@ -322,6 +324,7 @@ int sdxi_admin_cxt_init(struct sdxi_dev *sdxi) cxt->db =3D sdxi->dbs + cxt->id * sdxi->db_stride; sdxi_ring_state_init(cxt->ring_state, &sq->cxt_sts->read_index, sq->write_index, sq->ring_entries, sq->desc_ring); + ida_init(&cxt->akey_ida); =20 err =3D sdxi_publish_cxt(cxt); if (err) @@ -409,6 +412,7 @@ struct sdxi_cxt *sdxi_cxt_new(struct sdxi_dev *sdxi) sq =3D cxt->sq; sdxi_ring_state_init(cxt->ring_state, &sq->cxt_sts->read_index, sq->write_index, sq->ring_entries, sq->desc_ring); + ida_init(&cxt->akey_ida); =20 if (sdxi_publish_cxt(cxt)) return NULL; diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h index 0aebcba3dc1e..a8511f18db5d 100644 --- a/drivers/dma/sdxi/context.h +++ b/drivers/dma/sdxi/context.h @@ -6,8 +6,11 @@ #ifndef DMA_SDXI_CONTEXT_H #define DMA_SDXI_CONTEXT_H =20 +#include #include +#include #include +#include #include =20 #include "hw.h" @@ -51,6 +54,7 @@ struct sdxi_cxt { struct sdxi_cxt_ctl *cxt_ctl; dma_addr_t cxt_ctl_dma; =20 + struct ida akey_ida; struct sdxi_akey_table *akey_table; dma_addr_t akey_table_dma; =20 @@ -79,4 +83,24 @@ static inline void sdxi_cxt_push_doorbell(struct sdxi_cx= t *cxt, u64 index) writeq(index, cxt->db); } =20 +static inline struct sdxi_akey_ent *sdxi_alloc_akey(struct sdxi_cxt *cxt) +{ + unsigned int max =3D ARRAY_SIZE(cxt->akey_table->entry) - 1; + int idx =3D ida_alloc_max(&cxt->akey_ida, max, GFP_KERNEL); + + return idx < 0 ? NULL : &cxt->akey_table->entry[idx]; +} + +static inline unsigned int sdxi_akey_index(const struct sdxi_cxt *cxt, + const struct sdxi_akey_ent *akey) +{ + return akey - &cxt->akey_table->entry[0]; +} + +static inline void sdxi_free_akey(struct sdxi_cxt *cxt, struct sdxi_akey_e= nt *akey) +{ + memset(akey, 0, sizeof(*akey)); + ida_free(&cxt->akey_ida, sdxi_akey_index(cxt, akey)); +} + #endif /* DMA_SDXI_CONTEXT_H */ --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7C93C25B663; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=Wig7CMJt3shsse8yyU1KBaib9IpoeKiE+ENL19zBRj4OfBKrpMRaRgsLxc2pYMdkMewrZrYfacZSX4H6DviDhMkKhZX6M5ALusLX5yl48nFq/K9VkSlePxmuTwdLpMjqorZZ3Jt9g9Jtyv93L9J5V0HWoOMCdIrjB6beDV3Keb8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=TjBCq5GLV8eCRt3FN/z/334I1d54C9qgPI+LkaioXY4=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=gHY5aenGjtZXZ292puJTziS3QHydnNkFXYBAV/iH0R4u5WwZ9A5GpRkEYN2aiTAmqRh/8GRs0pjXhtEgoVBEU2CoOUNxB0aPzkI4v0N9tuH4hmY1QNNRiyEnbaLaXhm/sBT1Ou/BMGZXdz5jbzaVY2dSVM6zU3CPEk+stkEJebM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=mTrCklDb; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="mTrCklDb" Received: by smtp.kernel.org (Postfix) with ESMTPS id 5F8D3C2BCF4; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=TjBCq5GLV8eCRt3FN/z/334I1d54C9qgPI+LkaioXY4=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=mTrCklDbYb92Z585VHJRUrGMbb4oyg1EGe1yEYVY18nSGlhi5Ztcjg8naBGrsNPJo jHw6fmeDj5IW90bCSl66cZNGel+JMv6NbwYGNWOR2p2QdTSD7+WW7RJ478xI8XX/le x2+WfZ6WWlm4ay2/x0XLjYsakiimqt6LDRamlIsPRdrNbysgcpydDRGJvOXmktpgGv Uh3I219NzLKwcDRPiDayKzOSJpZWD9Ps7qe9sg7dELJnT7Onk0tj204hl9ZzE/WcoN q9T18/cGvsJYAe3UC4p+Zplukd5WLPRcDKN2KkJeSxIq7Ni+9LvOehzUhPrfl+h6YI exGzIsJXirvPg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 56596CD8C89; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:19 -0500 Subject: [PATCH v3 16/23] dmaengine: sdxi: Generic descriptor manipulation helpers 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: <20260605-sdxi-base-v3-16-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Frank Li , Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=4032; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=PSNXHSdeArEDKZ9yKGee2hJgxz3zpaB64VSQbAyMa80=; b=A7K3jW3eyiHO6Xb1je4yWHjHKaAcz6xIsfjtCbJ5ngPhbib8zuYvlg9ceSe6fDp2qjbPaJkNX 27LrEax5WUJAijzEqmtYpSzoMp/Js7m142WrqfJlG7vz9dicHpLYDaF X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Introduce small helper functions for manipulating certain common properties of descriptors after their operation-specific encoding has been performed but before they are submitted. sdxi_desc_set_csb() associates an optional completion status block with a descriptor. sdxi_desc_set_fence() forces retirement of any prior descriptors in the ring before the target descriptor is executed. This is useful for interrupt descriptors that signal the completion of an operation. sdxi_desc_set_sequential() ensures that all writes from prior descriptor operations in the same context are made globally visible prior to making writes from the target descriptor globally visible. sdxi_desc_make_valid() sets the descriptor validity bit, transferring ownership of the descriptor from software to the SDXI implementation. (The implementation is allowed to execute the descriptor at this point, but the caller is still obligated to push the doorbell to ensure execution occurs.) Each of the preceding functions will warn if invoked on a descriptor that has already been released to the SDXI implementation (i.e. had its validity bit set). Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Frank Li Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/descriptor.h | 64 +++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/hw.h | 9 ++++++ 2 files changed, 73 insertions(+) diff --git a/drivers/dma/sdxi/descriptor.h b/drivers/dma/sdxi/descriptor.h new file mode 100644 index 000000000000..c0f01b1be726 --- /dev/null +++ b/drivers/dma/sdxi/descriptor.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef DMA_SDXI_DESCRIPTOR_H +#define DMA_SDXI_DESCRIPTOR_H + +/* + * Facilities for encoding SDXI descriptors. + * + * Copyright Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include + +#include "hw.h" + +static inline void sdxi_desc_vl_expect(const struct sdxi_desc *desc, bool = expected) +{ + u8 vl =3D FIELD_GET(SDXI_DSC_VL, le32_to_cpu(desc->opcode)); + + WARN_RATELIMIT(vl !=3D expected, "expected vl=3D%u but got %u\n", expecte= d, vl); +} + +static inline void sdxi_desc_set_csb(struct sdxi_desc *desc, dma_addr_t ad= dr) +{ + sdxi_desc_vl_expect(desc, 0); + desc->csb_ptr =3D cpu_to_le64(FIELD_PREP(SDXI_DSC_CSB_PTR, addr >> 5)); +} + +static inline void sdxi_desc_make_valid(struct sdxi_desc *desc) +{ + u32 opcode =3D le32_to_cpu(desc->opcode); + + sdxi_desc_vl_expect(desc, 0); + FIELD_MODIFY(SDXI_DSC_VL, &opcode, 1); + /* + * Once vl is set, no more modifications to the descriptor + * payload are allowed. Ensure the vl update is ordered after + * all other initialization of the descriptor. + */ + dma_wmb(); + WRITE_ONCE(desc->opcode, cpu_to_le32(opcode)); +} + +static inline void sdxi_desc_set_fence(struct sdxi_desc *desc) +{ + u32 opcode =3D le32_to_cpu(desc->opcode); + + sdxi_desc_vl_expect(desc, 0); + FIELD_MODIFY(SDXI_DSC_FE, &opcode, 1); + desc->opcode =3D cpu_to_le32(opcode); +} + +static inline void sdxi_desc_set_sequential(struct sdxi_desc *desc) +{ + u32 opcode =3D le32_to_cpu(desc->opcode); + + sdxi_desc_vl_expect(desc, 0); + FIELD_MODIFY(SDXI_DSC_SE, &opcode, 1); + desc->opcode =3D cpu_to_le32(opcode); +} + +#endif /* DMA_SDXI_DESCRIPTOR_H */ diff --git a/drivers/dma/sdxi/hw.h b/drivers/dma/sdxi/hw.h index 4b65337a5975..29aa6c7e6c23 100644 --- a/drivers/dma/sdxi/hw.h +++ b/drivers/dma/sdxi/hw.h @@ -140,6 +140,15 @@ struct sdxi_desc { __u8 operation[52]; __le64 csb_ptr; ); + +/* For opcode field */ +#define SDXI_DSC_VL BIT(0) +#define SDXI_DSC_SE BIT(1) +#define SDXI_DSC_FE BIT(2) + +/* For csb_ptr field */ +#define SDXI_DSC_CSB_PTR GENMASK_ULL(63, 5) + }; } __packed __aligned(64); static_assert(sizeof(struct sdxi_desc) =3D=3D 64); --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 9305D26A1AF; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=kNa7qi7kO4EDuEs9j9g4295/qDDSF8C46cbXqXyELUbH+EWtd/+UNFxsQVkXPyKG4DKwe7cRkuIf9wkMkSTmvDihBXCrkKSWTXfJZFDFNBxPVayljnOSqW+hQlxvMN7Uxe51IIBxaAmVbQwDg6eNpD3oeINWoUgU45trmoLq+OY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=U8gNzA8keKKQCxluhJ7RJ/2+zPcviTUsDukEG4dg4yo=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=eAYWONP998U0JolqsFRwrgJapy1qOSRtYGYCUYvnFAuTlZwqIjToiMnXsY4j/sN2VWXjMIJ/iV8T1P53HH9mtlu4FCH8N5HRRqw50NiPBsaGV+6SNGTtczH05nM8kCXgQlR4xiFumJKU2MzCPKr0kV2OwsiqiVJEGc9rWvZwfaQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=E/sA6SEo; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="E/sA6SEo" Received: by smtp.kernel.org (Postfix) with ESMTPS id 75A2CC2BCF5; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=U8gNzA8keKKQCxluhJ7RJ/2+zPcviTUsDukEG4dg4yo=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=E/sA6SEoM+Dbp0lZVdzHn/yeODsrZKPjms82uhZ2ThxWh4FpVid8u4e5RBQ58jUWh 0x1G7aSNZ5VWS+smKMmSGyGcGnNwo56eRxITMPX2Q/4W7M9uWB8APS33o1+7G0P4nk 08i1DRCar8SYjGLpklGel1XoBaF9+TFedyuY1nDT7ghQe+hjH3E4GVJYFXrQHRB3K/ XsqyD+oqIuR7R40B/7NCTIQhDEgAxy+vDAzkV6e/Kwdj/Z+0CPIoaM0ByI5pHMuccI CtdNOxRE4NLGCEnfOjhwkab89xbyVRm/JRZ9Fc3v/pZve7jo2hq3ZwYFwuLVGAbx9q TqB+0ycHgGxDg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6C7AECD6E7C; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:20 -0500 Subject: [PATCH v3 17/23] dmaengine: sdxi: Add completion status block API 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: <20260605-sdxi-base-v3-17-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Frank Li , Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=5678; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=LMM7nU63m7NrdlpoB3bZ4tq48Kz0fepTcIp0MxorBO8=; b=OecvsX8yaM7Yges/IpoXK8V1An5ILWB9QstoREkoCMI6YF9H08ba07oZYPYQcgyLV7bUAhDoG bE+EwDZcFTYDlP4vXZz4Gi/J7BJ0foWB/aWXKGnXDkHuBsU/OF0jvwi X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Introduce an API for managing completion status blocks. These are DMA-coherent buffers that may be optionally attached to SDXI descriptors to signal completion. The SDXI implementation clears the signal field (initialized to 1) upon completion, setting an error bit in the flags field if problems were encountered executing the descriptor. Callers allocate completion blocks from a per-device DMA pool via sdxi_completion_alloc(). sdxi_completion_attach() associates a completion with a descriptor by encoding the completion's DMA address into the descriptor's csb_ptr field. sdxi_completion_poll() busy-waits until the signal field is cleared by the implementation, and is intended for descriptors that are expected to execute quickly. sdxi_completion_signaled() and sdxi_completion_errored() query the signal field and error flag of the completion, respectively. struct sdxi_completion is kept opaque to callers. A DEFINE_FREE cleanup handler is provided. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Frank Li Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/Makefile | 1 + drivers/dma/sdxi/completion.c | 87 +++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/completion.h | 25 +++++++++++++ drivers/dma/sdxi/hw.h | 1 + 4 files changed, 114 insertions(+) diff --git a/drivers/dma/sdxi/Makefile b/drivers/dma/sdxi/Makefile index 00e3f1cb0808..eacad504a816 100644 --- a/drivers/dma/sdxi/Makefile +++ b/drivers/dma/sdxi/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_SDXI_CORE) +=3D sdxi-core.o sdxi-core-y :=3D \ + completion.o \ context.o \ device.o \ ring.o diff --git a/drivers/dma/sdxi/completion.c b/drivers/dma/sdxi/completion.c new file mode 100644 index 000000000000..7ffd034b129b --- /dev/null +++ b/drivers/dma/sdxi/completion.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI Descriptor Completion Status Block handling. + * + * Copyright Advanced Micro Devices, Inc. + */ +#include +#include +#include +#include +#include + +#include "completion.h" +#include "descriptor.h" +#include "hw.h" + +struct sdxi_completion { + struct sdxi_dev *sdxi; + struct sdxi_cst_blk *cst_blk; + dma_addr_t cst_blk_dma; +}; + +struct sdxi_completion *sdxi_completion_alloc(struct sdxi_dev *sdxi) +{ + struct sdxi_cst_blk *cst_blk; + dma_addr_t cst_blk_dma; + + /* + * Assume callers can't tolerate GFP_KERNEL and use + * GFP_NOWAIT. Add a gfp_t flags parameter if that changes. + */ + struct sdxi_completion *sc __free(kfree) =3D kmalloc(sizeof(*sc), GFP_NOW= AIT); + if (!sc) + return NULL; + + cst_blk =3D dma_pool_zalloc(sdxi->cst_blk_pool, GFP_NOWAIT, &cst_blk_dma); + if (!cst_blk) + return NULL; + + cst_blk->signal =3D cpu_to_le64(1); + + *sc =3D (typeof(*sc)) { + .sdxi =3D sdxi, + .cst_blk =3D cst_blk, + .cst_blk_dma =3D cst_blk_dma, + }; + + return_ptr(sc); +} + +void sdxi_completion_free(struct sdxi_completion *sc) +{ + dma_pool_free(sc->sdxi->cst_blk_pool, sc->cst_blk, sc->cst_blk_dma); + kfree(sc); +} + +int sdxi_completion_poll(const struct sdxi_completion *sc) +{ + unsigned long deadline =3D jiffies + msecs_to_jiffies(1000); + + while (le64_to_cpu(READ_ONCE(sc->cst_blk->signal)) !=3D 0) { + if (time_after(jiffies, deadline)) + return -ETIMEDOUT; + cpu_relax(); + } + + return sdxi_completion_errored(sc) ? -EIO : 0; +} + +bool sdxi_completion_signaled(const struct sdxi_completion *sc) +{ + dma_rmb(); + return (sc->cst_blk->signal =3D=3D 0); +} + +bool sdxi_completion_errored(const struct sdxi_completion *sc) +{ + dma_rmb(); + return FIELD_GET(SDXI_CST_BLK_ER_BIT, le32_to_cpu(sc->cst_blk->flags)); +} + + +void sdxi_completion_attach(struct sdxi_desc *desc, + const struct sdxi_completion *cs) +{ + sdxi_desc_set_csb(desc, cs->cst_blk_dma); +} diff --git a/drivers/dma/sdxi/completion.h b/drivers/dma/sdxi/completion.h new file mode 100644 index 000000000000..2d11568ac2b9 --- /dev/null +++ b/drivers/dma/sdxi/completion.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright Advanced Micro Devices, Inc. */ +#ifndef DMA_SDXI_COMPLETION_H +#define DMA_SDXI_COMPLETION_H + +#include +#include "sdxi.h" + +/* + * Polled completion status block that can be attached to a + * descriptor. + */ +struct sdxi_completion; +struct sdxi_desc; +struct sdxi_completion *sdxi_completion_alloc(struct sdxi_dev *sdxi); +void sdxi_completion_free(struct sdxi_completion *sc); +int __must_check sdxi_completion_poll(const struct sdxi_completion *sc); +void sdxi_completion_attach(struct sdxi_desc *desc, + const struct sdxi_completion *sc); +bool sdxi_completion_signaled(const struct sdxi_completion *sc); +bool sdxi_completion_errored(const struct sdxi_completion *sc); + +DEFINE_FREE(sdxi_completion, struct sdxi_completion *, if (_T) sdxi_comple= tion_free(_T)) + +#endif /* DMA_SDXI_COMPLETION_H */ diff --git a/drivers/dma/sdxi/hw.h b/drivers/dma/sdxi/hw.h index 29aa6c7e6c23..5c5bef66f1fb 100644 --- a/drivers/dma/sdxi/hw.h +++ b/drivers/dma/sdxi/hw.h @@ -125,6 +125,7 @@ static_assert(sizeof(struct sdxi_akey_ent) =3D=3D 16); struct sdxi_cst_blk { __le64 signal; __le32 flags; +#define SDXI_CST_BLK_ER_BIT BIT(31) __u8 rsvd_0[20]; } __packed __aligned(32); static_assert(sizeof(struct sdxi_cst_blk) =3D=3D 32); --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id AA0E9274B37; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=EegwiZ9WbpuTEifNn9H6Nh76w/co7SidIIGSNGdUaMgQ34084KxmOrQ85HmYFLxQ+dXtxhp0dLIh8Snja/HZbUhvvlATusoMx6fdbiWyslQQPqTKwqyOT+EI3fcEflHjEmAnxtef63T5M2hq3F+F6xjtEuJs+ST3jsysFGIODxA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=n6txK7bTZ6tY8Uejz+EZK3m2XEL1aibMBM6MtcxdWQU=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=sGWLgAuwKF6D+XcnxrI7NNvEJFgx6VR/xydqhYPg+nJigBEY7bJgNp5A5e2m9R+hB4K5gUxEKA5yPwGd4jpu4n+UvuA7kyUlkvZxTGWo6msgJNM1RM2aWFWH/tCU8PdpIecIGiuOL1gRcxVCq0eVvDddzt3wpNBD375/LnyyE4o= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=CWSw9CXC; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="CWSw9CXC" Received: by smtp.kernel.org (Postfix) with ESMTPS id 86B20C2BCC6; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=n6txK7bTZ6tY8Uejz+EZK3m2XEL1aibMBM6MtcxdWQU=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=CWSw9CXCJAYnlGD8SwCWUDvygiMfUVzqjDFLkMwKj9KSveB4cnXM1/820A8ZgqqC4 U4RJUs1KJ6cesmYpLwAt8c/mJ49gMoQaqfEixZQ+4DvzXTHXv7/t3Pmen1BfhDp/u3 mx1yy+ya2dhRiageoTakff54Lx1fAcCs3Pwqp7R3vzzW0/bfXf3uoETr7QVG0c8lL/ o5xA6c9LeNiiYaJj3VHTh51bSO2BGuTtJwfh3lkO8aXBd7PMMrhru8xCuTJFr5DkvV niFH0Ca+ZZC/eixwRaKGPZbk0p96Rij6i3rkeQCl3Z8iiiu6GFy1hB6LLIzfeEUvcU wMxuYds+P6j6g== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7F440CD6E7B; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:21 -0500 Subject: [PATCH v3 18/23] dmaengine: sdxi: Encode context start, stop, and sync descriptors 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: <20260605-sdxi-base-v3-18-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Frank Li , Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=8400; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=ITo1ztXWz4lwv5IFNFhjzv+gOZ9b0rt77cPGs8kLH9g=; b=nSRpcvQT4syanFY3qnTP82zLVSHbYHeO1flIlb2xMUP8nUJEK/MViuYAPXTdPyNujKbjkjRYu poMp8og4gNFDLmOf40IyTAAiWhpXY9rhLI8aqI/WKV4snaa5lJMaV7x X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Introduce the low-level support for serializing three operation types to the descriptor ring of the admin context: context start, context stop, and sync. Each operation has its own distinct type that overlays the generic struct sdxi_desc, along with a dedicated encoder function that accepts an operation-specific parameter struct. The parameter structs (sdxi_cxt_start, sdxi_cxt_stop, sdxi_sync) expose only a necessary subset of the available descriptor fields to callers, i.e. the target context range. These can be expanded over time as needed. Each encoder function is intended to 1) set any mandatory field values for the descriptor type (e.g. SDXI_DSC_FE=3D1 for context start); and 2) translate conventional kernel types (dma_addr_t, CPU-endian values) from the parameter block to the descriptor in memory. While they're expected to operate directly on descriptor ring memory, they do not set the descriptor validity bit. That is left to the caller, which may need to make other modifictions to the descriptor, such as attaching a completion block, before releasing it to the SDXI implementation. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Frank Li Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/Makefile | 1 + drivers/dma/sdxi/descriptor.c | 91 +++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/descriptor.h | 46 ++++++++++++++++++++++ drivers/dma/sdxi/hw.h | 64 ++++++++++++++++++++++++++++++ 4 files changed, 202 insertions(+) diff --git a/drivers/dma/sdxi/Makefile b/drivers/dma/sdxi/Makefile index eacad504a816..9b051eca9af7 100644 --- a/drivers/dma/sdxi/Makefile +++ b/drivers/dma/sdxi/Makefile @@ -3,6 +3,7 @@ obj-$(CONFIG_SDXI_CORE) +=3D sdxi-core.o sdxi-core-y :=3D \ completion.o \ context.o \ + descriptor.o \ device.o \ ring.o =20 diff --git a/drivers/dma/sdxi/descriptor.c b/drivers/dma/sdxi/descriptor.c new file mode 100644 index 000000000000..be2a9244ce19 --- /dev/null +++ b/drivers/dma/sdxi/descriptor.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI descriptor encoding. + * + * Copyright Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include + +#include "hw.h" +#include "descriptor.h" + +int sdxi_encode_cxt_start(struct sdxi_desc *desc, + const struct sdxi_cxt_start *params) +{ + u64 csb_ptr; + u32 opcode; + + opcode =3D (FIELD_PREP(SDXI_DSC_FE, 1) | + FIELD_PREP(SDXI_DSC_SUBTYPE, SDXI_DSC_OP_SUBTYPE_CXT_START_NM) | + FIELD_PREP(SDXI_DSC_TYPE, SDXI_DSC_OP_TYPE_ADMIN)); + + csb_ptr =3D FIELD_PREP(SDXI_DSC_NP, 1); + + *desc =3D (typeof(*desc)) { + .cxt_start =3D (typeof(desc->cxt_start)) { + .opcode =3D cpu_to_le32(opcode), + .cxt_start =3D cpu_to_le16(params->range.cxt_start), + .cxt_end =3D cpu_to_le16(params->range.cxt_end), + .csb_ptr =3D cpu_to_le64(csb_ptr), + }, + }; + + return 0; +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_encode_cxt_start); + +int sdxi_encode_cxt_stop(struct sdxi_desc *desc, + const struct sdxi_cxt_stop *params) +{ + u64 csb_ptr; + u32 opcode; + + opcode =3D (FIELD_PREP(SDXI_DSC_FE, 1) | + FIELD_PREP(SDXI_DSC_SUBTYPE, SDXI_DSC_OP_SUBTYPE_CXT_STOP) | + FIELD_PREP(SDXI_DSC_TYPE, SDXI_DSC_OP_TYPE_ADMIN)); + + csb_ptr =3D FIELD_PREP(SDXI_DSC_NP, 1); + + *desc =3D (typeof(*desc)) { + .cxt_stop =3D (typeof(desc->cxt_stop)) { + .opcode =3D cpu_to_le32(opcode), + .cxt_start =3D cpu_to_le16(params->range.cxt_start), + .cxt_end =3D cpu_to_le16(params->range.cxt_end), + .csb_ptr =3D cpu_to_le64(csb_ptr), + }, + }; + + return 0; +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_encode_cxt_stop); + +int sdxi_encode_sync(struct sdxi_desc *desc, const struct sdxi_sync *param= s) +{ + u64 csb_ptr; + u32 opcode; + u8 cflags; + + opcode =3D (FIELD_PREP(SDXI_DSC_SUBTYPE, SDXI_DSC_OP_SUBTYPE_SYNC) | + FIELD_PREP(SDXI_DSC_TYPE, SDXI_DSC_OP_TYPE_ADMIN)); + + cflags =3D FIELD_PREP(SDXI_DSC_SYNC_FLT, params->filter); + + csb_ptr =3D FIELD_PREP(SDXI_DSC_NP, 1); + + *desc =3D (typeof(*desc)) { + .sync =3D (typeof(desc->sync)) { + .opcode =3D cpu_to_le32(opcode), + .cflags =3D cflags, + .cxt_start =3D cpu_to_le16(params->range.cxt_start), + .cxt_end =3D cpu_to_le16(params->range.cxt_end), + .csb_ptr =3D cpu_to_le64(csb_ptr), + }, + }; + + return 0; +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_encode_sync); diff --git a/drivers/dma/sdxi/descriptor.h b/drivers/dma/sdxi/descriptor.h index c0f01b1be726..5b8fd7cbaa03 100644 --- a/drivers/dma/sdxi/descriptor.h +++ b/drivers/dma/sdxi/descriptor.h @@ -9,6 +9,7 @@ */ =20 #include +#include #include #include #include @@ -61,4 +62,49 @@ static inline void sdxi_desc_set_sequential(struct sdxi_= desc *desc) desc->opcode =3D cpu_to_le32(opcode); } =20 +struct sdxi_cxt_range { + u16 cxt_start; + u16 cxt_end; +}; + +static inline struct sdxi_cxt_range sdxi_cxt_range(u16 a, u16 b) +{ + return (struct sdxi_cxt_range) { + .cxt_start =3D min(a, b), + .cxt_end =3D max(a, b), + }; +} + +static inline struct sdxi_cxt_range sdxi_cxt_range_single(u16 nr) +{ + return sdxi_cxt_range(nr, nr); +} + +struct sdxi_cxt_start { + struct sdxi_cxt_range range; +}; + +int sdxi_encode_cxt_start(struct sdxi_desc *desc, + const struct sdxi_cxt_start *params); + +struct sdxi_cxt_stop { + struct sdxi_cxt_range range; +}; + +int sdxi_encode_cxt_stop(struct sdxi_desc *desc, + const struct sdxi_cxt_stop *params); + +struct sdxi_sync { + enum sdxi_sync_filter { + SDXI_SYNC_FLT_CXT =3D 0x0, + SDXI_SYNC_FLT_STOP =3D 0x1, + SDXI_SYNC_FLT_AKEY =3D 0x2, + SDXI_SYNC_FLT_RKEY =3D 0x3, + SDXI_SYNC_FLT_FN =3D 0x4, + } filter; + struct sdxi_cxt_range range; +}; + +int sdxi_encode_sync(struct sdxi_desc *desc, const struct sdxi_sync *param= s); + #endif /* DMA_SDXI_DESCRIPTOR_H */ diff --git a/drivers/dma/sdxi/hw.h b/drivers/dma/sdxi/hw.h index 5c5bef66f1fb..d340ed7dc061 100644 --- a/drivers/dma/sdxi/hw.h +++ b/drivers/dma/sdxi/hw.h @@ -146,12 +146,76 @@ struct sdxi_desc { #define SDXI_DSC_VL BIT(0) #define SDXI_DSC_SE BIT(1) #define SDXI_DSC_FE BIT(2) +#define SDXI_DSC_SUBTYPE GENMASK(15, 8) +#define SDXI_DSC_TYPE GENMASK(26, 16) =20 /* For csb_ptr field */ +#define SDXI_DSC_NP BIT_ULL(0) #define SDXI_DSC_CSB_PTR GENMASK_ULL(63, 5) =20 +#define define_sdxi_dsc(tag_, name_, op_body_) \ + struct tag_ { \ + __le32 opcode; \ + op_body_ \ + __le64 csb_ptr; \ + } __packed __aligned(64) name_; \ + static_assert(sizeof(struct tag_) =3D=3D \ + sizeof(struct sdxi_dsc_generic)); \ + static_assert(offsetof(struct tag_, csb_ptr) =3D=3D \ + offsetof(struct sdxi_dsc_generic, csb_ptr)) + + /* SDXI 1.0 Table 6-14: DSC_CXT_START Descriptor Format */ + define_sdxi_dsc(sdxi_dsc_cxt_start, cxt_start, + __u8 rsvd_0; + __u8 vflags; + __le16 vf_num; + __le16 cxt_start; + __le16 cxt_end; + __u8 rsvd_1[4]; + __le64 db_value; + __u8 rsvd_2[32]; + ); + + /* SDXI 1.0 Table 6-15: DSC_CXT_STOP Descriptor Format */ + define_sdxi_dsc(sdxi_dsc_cxt_stop, cxt_stop, + __u8 rsvd_0; + __u8 vflags; + __le16 vf_num; + __le16 cxt_start; + __le16 cxt_end; + __u8 rsvd_1[44]; + ); + + /* SDXI 1.0 Table 6-22: DSC_SYNC Descriptor Format */ + define_sdxi_dsc(sdxi_dsc_sync, sync, + __u8 cflags; + __u8 vflags; + __le16 vf_num; + __le16 cxt_start; + __le16 cxt_end; + __le16 key_start; + __le16 key_end; + __u8 rsvd_0[40]; + ); +/* For use with sync.cflags */ +#define SDXI_DSC_SYNC_FLT GENMASK(2, 0) + +#undef define_sdxi_dsc }; } __packed __aligned(64); static_assert(sizeof(struct sdxi_desc) =3D=3D 64); =20 +/* SDXI 1.0 Table 6-1: SDXI Operation Groups */ +enum sdxi_dsc_type { + SDXI_DSC_OP_TYPE_ADMIN =3D 0x002, +}; + +/* SDXI 1.0 Table 6-2: SDXI Operation Groups, Types, and Subtypes */ +enum sdxi_dsc_subtype { + /* Administrative */ + SDXI_DSC_OP_SUBTYPE_CXT_START_NM =3D 0x03, + SDXI_DSC_OP_SUBTYPE_CXT_STOP =3D 0x04, + SDXI_DSC_OP_SUBTYPE_SYNC =3D 0x06, +}; + #endif /* DMA_SDXI_HW_H */ --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id BC9F3279336; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=uKYq9ctEw+Ukai4DFNJUbRRynIw7yvPF6n1PfpmVd5NWrDZrdXBbuIbIJ0QSxD5liIhwE941yB/NW82Nmv8ni/I6jD2QW1yInn/GH08QnqADJdp13a+vjvaJTcrxcEvk4FTM47WmoTxuSeoKA9YvVJJGWzQFCnLbiBvzfwjlfjw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=XNMxRjNWQZv1sZpGhMm8KbMRB44Aeh/fKvTyGO6KSrM=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=fIZD1+q7RTiIrGazVpSwga9lnXHGvJwT95JaNU9HkfngNtDphAjnjNlA1M6GFF8/YzJWSOBbfFI8G7Drfm0dFGCcnv5nZOds3qa7SfN6qbjIlAIbTs6YgbzvDQ81zPFtwgt9TTbjcxtyNKi2/iFCAr/WwxYSLOIdJu2GpjL5Nr0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=VqUAPY1/; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="VqUAPY1/" Received: by smtp.kernel.org (Postfix) with ESMTPS id 9F1AAC2BCFB; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=XNMxRjNWQZv1sZpGhMm8KbMRB44Aeh/fKvTyGO6KSrM=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=VqUAPY1/ghwHdJswlWKZ0F5ucUA3sfEPJCuHSyIT0ARdOzRteG7RexbuFke3Wc4sZ RnOEkJNhnVVVjR8hunOsxC1az6h6pDOSmUdIIULuWiLj8DoOHdxDMWkPsmPKEMy/DG /sE5I/vYBsyz5fp5JV7JUVKE/44LSlPfEjw34VLQaKqqG+IaOoAOPqc2qojr08yLps DikTILjViWOyVfw47Kg0qAzmUVpb97ytSVbVYmiv++3k1xcAaZhQrbWTzmgpiAFUqe Ufk979ULnqxfGA6iE3Qb0E1wkrpoZf9KrTMqcmkN93jevR7LHxL1RM5u+MXCIe5jN2 NiU5GQUcawIzg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 90001CD6E7C; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:22 -0500 Subject: [PATCH v3 19/23] dmaengine: sdxi: Provide context start and stop APIs 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: <20260605-sdxi-base-v3-19-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=3811; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=a8RlzeUJApQL3roCOqXKGm7r59rjbXIKAHqZ0W+U7Qo=; b=ErRDUoZcunLBgZc6QZG1VjBkv6/G0jO31CX0CVoWt54GZDeaB4TovJT4Nh5mQ2CRbmtokjjuG 79gvNiKu7lvDGkZveVj2HRA6pVMV4Aypf60jyVokNmOOK0fB2y9VqRR X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Starting and stopping SDXI client contexts is implemented by submitting special-purpose descriptors to a function's admin context. Introduce high-level context start and stop APIs that operate on struct sdxi_cxt objects, encapsulating the administrative descriptor submission and completion signaling. These are intended for use by clients such as the DMA engine provider to come. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/context.c | 77 ++++++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/context.h | 3 ++ 2 files changed, 80 insertions(+) diff --git a/drivers/dma/sdxi/context.c b/drivers/dma/sdxi/context.c index 9b0984842d9a..afd341416342 100644 --- a/drivers/dma/sdxi/context.c +++ b/drivers/dma/sdxi/context.c @@ -22,7 +22,9 @@ #include #include =20 +#include "completion.h" #include "context.h" +#include "descriptor.h" #include "hw.h" #include "ring.h" #include "sdxi.h" @@ -335,6 +337,81 @@ int sdxi_admin_cxt_init(struct sdxi_dev *sdxi) return devm_add_action_or_reset(sdxi->dev, free_admin_cxt, sdxi); } =20 +int sdxi_start_cxt(struct sdxi_cxt *cxt) +{ + struct sdxi_cxt *adm =3D to_admin_cxt(cxt); + struct sdxi_desc *desc; + struct sdxi_ring_resv resv; + int err; + + might_sleep(); + + struct sdxi_completion *sc __free(sdxi_completion) =3D + sdxi_completion_alloc(cxt->sdxi); + + if (!sc) + return -ENOMEM; + + /* This is not how to start the admin context. */ + if (WARN_ON(adm =3D=3D cxt)) + return -EINVAL; + + err =3D sdxi_ring_reserve(adm->ring_state, 1, &resv); + if (err) + return err; + + desc =3D sdxi_ring_resv_next(&resv); + sdxi_encode_cxt_start(desc, &(const struct sdxi_cxt_start) { + .range =3D sdxi_cxt_range_single(cxt->id), + }); + sdxi_completion_attach(desc, sc); + sdxi_desc_make_valid(desc); + sdxi_cxt_push_doorbell(adm, sdxi_ring_resv_dbval(&resv)); + + return sdxi_completion_poll(sc); +} + +void sdxi_stop_cxt(struct sdxi_cxt *cxt) +{ + struct sdxi_cxt *adm =3D to_admin_cxt(cxt); + struct sdxi_desc *stop, *sync; + struct sdxi_ring_resv resv; + int err; + + might_sleep(); + + struct sdxi_completion *sc __free(sdxi_completion) =3D + sdxi_completion_alloc(cxt->sdxi); + + if (!sc) + return; + + /* This is not how to stop the admin context. */ + if (WARN_ON(adm =3D=3D cxt)) + return; + + err =3D sdxi_ring_reserve(adm->ring_state, 2, &resv); + if (WARN_ON_ONCE(err)) + return; + + stop =3D sdxi_ring_resv_next(&resv); + sync =3D sdxi_ring_resv_next(&resv); + + sdxi_encode_cxt_stop(stop, &(const struct sdxi_cxt_stop) { + .range =3D sdxi_cxt_range_single(cxt->id), + }); + sdxi_encode_sync(sync, &(const struct sdxi_sync) { + .filter =3D SDXI_SYNC_FLT_STOP, + .range =3D sdxi_cxt_range_single(cxt->id), + }); + sdxi_completion_attach(sync, sc); + sdxi_desc_make_valid(stop); + sdxi_desc_make_valid(sync); + sdxi_cxt_push_doorbell(adm, sdxi_ring_resv_dbval(&resv)); + + WARN_ON(sdxi_completion_poll(sc)); +} + /* * Temporary owner for context id until it can be assigned to a * context object; enables scope-based cleanup. diff --git a/drivers/dma/sdxi/context.h b/drivers/dma/sdxi/context.h index a8511f18db5d..880e7a289810 100644 --- a/drivers/dma/sdxi/context.h +++ b/drivers/dma/sdxi/context.h @@ -68,6 +68,9 @@ int sdxi_admin_cxt_init(struct sdxi_dev *sdxi); struct sdxi_cxt *sdxi_cxt_new(struct sdxi_dev *sdxi); void sdxi_cxt_exit(struct sdxi_cxt *cxt); =20 +int sdxi_start_cxt(struct sdxi_cxt *cxt); +void sdxi_stop_cxt(struct sdxi_cxt *cxt); + static inline struct sdxi_cxt *to_admin_cxt(const struct sdxi_cxt *cxt) { return cxt->sdxi->admin_cxt; --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id CF00927FD44; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=psE5nCjfJr1ecWAS8h80s8SSzwdbNS35Tlu5noyq9TY+Kc5n4pvhRjqU73iLYFpPCPV+DdwT/mK1tshn8mnimTZ3VPPhNNI48us2lhbfXBHQrx1qPTJRwcOz0rCQF1Prc//qRjEM4QpweEFN4xx6EKJAmMgZOUvDd3xoxEvhbPQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=CfhFOUVHuW3ofHeuIzbI6s3yDV2GuJ9tuZ5kbiDPJLE=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=LpHqo0ZaKJMr0k+27PXvlTA4Ei5GKG6+i6HNnAKGmmtYYNJGk+eVv5c8pML/yNV6OtoW1nRwxMw+63rqf8xgUtFaS/WWejrwBSOboqIpihrabWZICUhkkvofuE5x4BtLCjJTKA50sh5TUlCEkQvLSqO26adprgPega3gROS8Gws= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=pHHOazkR; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="pHHOazkR" Received: by smtp.kernel.org (Postfix) with ESMTPS id AF024C2BCB9; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=CfhFOUVHuW3ofHeuIzbI6s3yDV2GuJ9tuZ5kbiDPJLE=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=pHHOazkR86s08QozvI0+OCkw/JFU+Eg9BDCzbqHz8gnde8ppUCWNOWwqaQnSxbi75 uWv576bDLoktMJ3birP8n/aCjTAg8yVs//zPLHELUqAKwz4w7e9QfrPgIsc2xmlp5g CWqtd4RiKRa8efnWYSBceiTXnfNdiHRRi88hyKAfPQyM/6sjJuSmmXql4++7jpgKUo 5TZhWYeX5QRc8xEnQGQBwzbeKnMQCZ5TpmW1e798ATlBjzJskXTdxlMOJJG0gbqvqC r8oYkiUpBd7xBnBKm0ftHceFbxggqhymGByR9BfSZDzX4jbhy9vzYByyQ2tQms6C/X S7fshkKnqARfw== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9E4EDCD8C8B; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:23 -0500 Subject: [PATCH v3 20/23] dmaengine: sdxi: Encode nop, copy, and interrupt descriptors 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: <20260605-sdxi-base-v3-20-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Frank Li , Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=7417; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=a3ebJiN0ISff/LauBhfxJYv8Eu1uDiFLARue6Sq4bgQ=; b=xw7bfXU473M7bwYRtBCXxTQeO80J8zGtOPND3NQ1rI9Av7/XX5oV2HKl5d4eQgeaG9zvjU7gw mnznC8N7daPDGFRTSwo5/OJwOwCnJse+Ayo3nycQwt3z3siGN8tWW+q X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Introduce low-level support for serializing three operation types to the descriptor ring of a client context: nop, copy, and interrupt. As with the administrative descriptor support introduced earlier, each operation has its own distinct type that overlays the generic struct sdxi_desc, along with a dedicated encoder function that accepts an operation-specific parameter struct. Copy descriptors are used to implement memcpy offload for the DMA engine provider, and interrupt descriptors are used to signal the completion of preceding descriptors in the ring. Nops can be used in error paths where a ring reservation has been obtained and the caller needs to submit valid descriptors before returning. Conditionally expose sdxi_encode_size32() for unit testing. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Frank Li Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/descriptor.c | 107 ++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/descriptor.h | 25 ++++++++++ drivers/dma/sdxi/hw.h | 33 +++++++++++++ 3 files changed, 165 insertions(+) diff --git a/drivers/dma/sdxi/descriptor.c b/drivers/dma/sdxi/descriptor.c index be2a9244ce19..41019e747528 100644 --- a/drivers/dma/sdxi/descriptor.c +++ b/drivers/dma/sdxi/descriptor.c @@ -7,12 +7,119 @@ =20 #include #include +#include +#include +#include #include #include =20 #include "hw.h" #include "descriptor.h" =20 +VISIBLE_IF_KUNIT int __must_check sdxi_encode_size32(u64 size, __le32 *des= t) +{ + /* + * sizes are encoded as value - 1: + * value encoding + * 1 0 + * 2 1 + * ... + * 4G 0xffffffff + */ + if (WARN_ON_ONCE(size > SZ_4G) || + WARN_ON_ONCE(size =3D=3D 0)) + return -EINVAL; + size =3D clamp_val(size, 1, SZ_4G); + *dest =3D cpu_to_le32((u32)(size - 1)); + return 0; +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_encode_size32); + +void sdxi_serialize_nop(struct sdxi_desc *desc) +{ + u32 opcode =3D (FIELD_PREP(SDXI_DSC_SUBTYPE, SDXI_DSC_OP_SUBTYPE_NOP) | + FIELD_PREP(SDXI_DSC_TYPE, SDXI_DSC_OP_TYPE_DMAB)); + u64 csb_ptr =3D FIELD_PREP(SDXI_DSC_NP, 1); + + *desc =3D (typeof(*desc)) { + .nop =3D (typeof(desc->nop)) { + .opcode =3D cpu_to_le32(opcode), + .csb_ptr =3D cpu_to_le64(csb_ptr), + }, + }; + +} + +int sdxi_encode_copy(struct sdxi_desc *desc, const struct sdxi_copy *param= s) +{ + u64 csb_ptr; + u32 opcode; + __le32 size; + int err; + + err =3D sdxi_encode_size32(params->len, &size); + if (err) + return err; + /* + * Reject overlapping src and dst. "Software ... shall not + * overlap the source buffer, destination buffer, Atomic + * Return Data, or completion status block." - SDXI 1.0 5.6 + * Memory Consistency Model + */ + if (range_overlaps(&(const struct range) { + .start =3D params->src, + .end =3D params->src + params->len - 1, + }, + &(const struct range) { + .start =3D params->dst, + .end =3D params->dst + params->len - 1, + })) + return -EINVAL; + + opcode =3D (FIELD_PREP(SDXI_DSC_SUBTYPE, SDXI_DSC_OP_SUBTYPE_COPY) | + FIELD_PREP(SDXI_DSC_TYPE, SDXI_DSC_OP_TYPE_DMAB)); + + csb_ptr =3D FIELD_PREP(SDXI_DSC_NP, 1); + + *desc =3D (typeof(*desc)) { + .copy =3D (typeof(desc->copy)) { + .opcode =3D cpu_to_le32(opcode), + .size =3D size, + .akey0 =3D cpu_to_le16(params->src_akey), + .akey1 =3D cpu_to_le16(params->dst_akey), + .addr0 =3D cpu_to_le64(params->src), + .addr1 =3D cpu_to_le64(params->dst), + .csb_ptr =3D cpu_to_le64(csb_ptr), + }, + }; + + return 0; +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_encode_copy); + +int sdxi_encode_intr(struct sdxi_desc *desc, + const struct sdxi_intr *params) +{ + u64 csb_ptr; + u32 opcode; + + opcode =3D (FIELD_PREP(SDXI_DSC_SUBTYPE, SDXI_DSC_OP_SUBTYPE_INTR) | + FIELD_PREP(SDXI_DSC_TYPE, SDXI_DSC_OP_TYPE_INTR)); + + csb_ptr =3D FIELD_PREP(SDXI_DSC_NP, 1); + + *desc =3D (typeof(*desc)) { + .intr =3D (typeof(desc->intr)) { + .opcode =3D cpu_to_le32(opcode), + .akey =3D cpu_to_le16(params->akey), + .csb_ptr =3D cpu_to_le64(csb_ptr), + }, + }; + + return 0; +} +EXPORT_SYMBOL_IF_KUNIT(sdxi_encode_intr); + int sdxi_encode_cxt_start(struct sdxi_desc *desc, const struct sdxi_cxt_start *params) { diff --git a/drivers/dma/sdxi/descriptor.h b/drivers/dma/sdxi/descriptor.h index 5b8fd7cbaa03..14f92c8dea1d 100644 --- a/drivers/dma/sdxi/descriptor.h +++ b/drivers/dma/sdxi/descriptor.h @@ -9,6 +9,7 @@ */ =20 #include +#include #include #include #include @@ -16,6 +17,10 @@ =20 #include "hw.h" =20 +#if IS_ENABLED(CONFIG_KUNIT) +int __must_check sdxi_encode_size32(u64 size, __le32 *dest); +#endif + static inline void sdxi_desc_vl_expect(const struct sdxi_desc *desc, bool = expected) { u8 vl =3D FIELD_GET(SDXI_DSC_VL, le32_to_cpu(desc->opcode)); @@ -80,6 +85,26 @@ static inline struct sdxi_cxt_range sdxi_cxt_range_singl= e(u16 nr) return sdxi_cxt_range(nr, nr); } =20 +void sdxi_serialize_nop(struct sdxi_desc *desc); + +struct sdxi_copy { + dma_addr_t src; + dma_addr_t dst; + u64 len; + u16 src_akey; + u16 dst_akey; +}; + +int sdxi_encode_copy(struct sdxi_desc *desc, + const struct sdxi_copy *params); + +struct sdxi_intr { + u16 akey; +}; + +int sdxi_encode_intr(struct sdxi_desc *desc, + const struct sdxi_intr *params); + struct sdxi_cxt_start { struct sdxi_cxt_range range; }; diff --git a/drivers/dma/sdxi/hw.h b/drivers/dma/sdxi/hw.h index d340ed7dc061..566bebf3f356 100644 --- a/drivers/dma/sdxi/hw.h +++ b/drivers/dma/sdxi/hw.h @@ -164,6 +164,30 @@ struct sdxi_desc { static_assert(offsetof(struct tag_, csb_ptr) =3D=3D \ offsetof(struct sdxi_dsc_generic, csb_ptr)) =20 + /* SDXI 1.0 Table 6-6: DSC_DMAB_NOP Descriptor Format */ + define_sdxi_dsc(sdxi_dsc_dmab_nop, nop, + __u8 rsvd_0[52]; + ); + + /* SDXI 1.0 Table 6-8: DSC_DMAB_COPY Descriptor Format */ + define_sdxi_dsc(sdxi_dsc_dmab_copy, copy, + __le32 size; + __u8 attr; + __u8 rsvd_0[3]; + __le16 akey0; + __le16 akey1; + __le64 addr0; + __le64 addr1; + __u8 rsvd_1[24]; + ); + + /* SDXI 1.0 Table 6-12: DSC_INTR Descriptor Format */ + define_sdxi_dsc(sdxi_dsc_intr, intr, + __u8 rsvd_0[8]; + __le16 akey; + __u8 rsvd_1[42]; + ); + /* SDXI 1.0 Table 6-14: DSC_CXT_START Descriptor Format */ define_sdxi_dsc(sdxi_dsc_cxt_start, cxt_start, __u8 rsvd_0; @@ -207,11 +231,20 @@ static_assert(sizeof(struct sdxi_desc) =3D=3D 64); =20 /* SDXI 1.0 Table 6-1: SDXI Operation Groups */ enum sdxi_dsc_type { + SDXI_DSC_OP_TYPE_DMAB =3D 0x001, SDXI_DSC_OP_TYPE_ADMIN =3D 0x002, + SDXI_DSC_OP_TYPE_INTR =3D 0x004, }; =20 /* SDXI 1.0 Table 6-2: SDXI Operation Groups, Types, and Subtypes */ enum sdxi_dsc_subtype { + /* DMA Base */ + SDXI_DSC_OP_SUBTYPE_NOP =3D 0x01, + SDXI_DSC_OP_SUBTYPE_COPY =3D 0x03, + + /* Interrupt */ + SDXI_DSC_OP_SUBTYPE_INTR =3D 0x00, + /* Administrative */ SDXI_DSC_OP_SUBTYPE_CXT_START_NM =3D 0x03, SDXI_DSC_OP_SUBTYPE_CXT_STOP =3D 0x04, --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id D913228466C; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; cv=none; b=Tl/FGDDJM27lq5eyuNvt3CnkBJAe+/j4ziPKpjoWjpT0FKsk75WzQ7KTadc99NVt09pEQm5LyZrxd8h988z99w5aJvR2pPZT+EKAq6be2a1HncplY2I38twDem3Y/y4KzpAt4qD5tyiFvtCjmFjrZm98e0HQOpl8LiDPojU+ls8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704143; c=relaxed/simple; bh=zLabyLQRZIl2DcTEPEg1bI7m03FwAhgCrQS9aVdJ5p0=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=giWu+o7NVXyI9YivWGerDOHodHwfC+LyY94FzEZQ1EWX1IxsgOaYmQryWwWjd3KUw6CBSn4X4ABpTE82jpe01epL/nVKOjuFTAfUxpQSKFZVGvrICGx0B2cgYa/erEvol66D3qi51sm0ivy3NP6qihZ+IrZZy3FvsjiJbFEz0hQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=igzyZaTt; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="igzyZaTt" Received: by smtp.kernel.org (Postfix) with ESMTPS id BC591C4AF0C; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=zLabyLQRZIl2DcTEPEg1bI7m03FwAhgCrQS9aVdJ5p0=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=igzyZaTtui39G0pgAT/TMMWw3r9oW6uzjEldujX8VFx/h4e9tvcOwkjCse9BNVRGe ohhCb4aJvlnZtZH523ZfVL3oWjspkIK/oNSfc/sXkiNuDsFSdvoaFzWz+n9xRxmsOl KdhNFbClFYwGwuFulcdPi0nFdj+GZ+UCNURo6iO9p5Ox9JyiGP0pD/7suDLI5VHK4z 31sidLDVajH08jkxZRZgX5nxQAokPrXTU0ujIHf8k2CDaqkKWJqjCoSnJrVMSRV3gb N2+9P4EoZ/hYpfGjnMvXrb9sZilj+rCf51A1DrPK9NapSH0DHhb7X8l+BEmb+L5Jz+ lxz1qtbCt1ngw== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id B1744CD8C88; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:24 -0500 Subject: [PATCH v3 21/23] dmaengine: sdxi: Add unit tests for descriptor encoding 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: <20260605-sdxi-base-v3-21-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=16289; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=+n9tpFLSoSlcH4n+Lx44mfnpemlDlz0QrjZPuZ9jOe0=; b=w1oiCOndBieU+ZWD3iiYwdu+bng3yWlCaQ+jpsgtAjy5sE9EpzNKsoK2wu+meozf7nIXcvcZ9 mpuokDkzMCCBk8S7Dfmqb48b2umA0MxJcPdHiGplGmJHj/uiOcFoKC8 X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Test the encoder function for each descriptor type currently used by the driver. The production code uses the GENMASK()/BIT() family of macros to support encoding descriptors. The tests for that code use the packing API to decode descriptors produced by that code without relying on those bitmask definitions. By limiting what's shared between the real code and the tests we gain confidence in both. If both the driver code and the tests rely on the bitfield macros, and then upon adding a new descriptor field the author mistranslates the bit numbering from the spec, that error is more likely to propagate to the tests undetected than if the test code relies on a separate mechanism for decoding descriptors. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/Kconfig | 1 + drivers/dma/sdxi/Makefile | 1 + drivers/dma/sdxi/descriptor_kunit.c | 484 ++++++++++++++++++++++++++++++++= ++++ 3 files changed, 486 insertions(+) diff --git a/drivers/dma/sdxi/Kconfig b/drivers/dma/sdxi/Kconfig index 7217375c9216..314b3e725ccb 100644 --- a/drivers/dma/sdxi/Kconfig +++ b/drivers/dma/sdxi/Kconfig @@ -31,6 +31,7 @@ config SDXI_KUNIT_TEST tristate "SDXI unit tests" if !KUNIT_ALL_TESTS depends on SDXI_CORE && KUNIT default KUNIT_ALL_TESTS + select PACKING help KUnit tests for parts of the SDXI driver. Does not require SDXI hardware. diff --git a/drivers/dma/sdxi/Makefile b/drivers/dma/sdxi/Makefile index 9b051eca9af7..5218ae2c86ae 100644 --- a/drivers/dma/sdxi/Makefile +++ b/drivers/dma/sdxi/Makefile @@ -11,4 +11,5 @@ obj-$(CONFIG_SDXI_PCI) +=3D sdxi-pci.o sdxi-pci-y :=3D pci.o =20 obj-$(CONFIG_SDXI_KUNIT_TEST) +=3D \ + descriptor_kunit.o \ ring_kunit.o diff --git a/drivers/dma/sdxi/descriptor_kunit.c b/drivers/dma/sdxi/descrip= tor_kunit.c new file mode 100644 index 000000000000..1f3c2e7ab2dd --- /dev/null +++ b/drivers/dma/sdxi/descriptor_kunit.c @@ -0,0 +1,484 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI descriptor encoding tests. + * + * Copyright Advanced Micro Devices, Inc. + * + * While the driver code uses bitfield macros (BIT, GENMASK) to encode + * descriptors, these tests use the packing API to decode them. + * Capturing the descriptor layout using PACKED_FIELD() is basically a + * copy-paste exercise since SDXI defines control structure fields in + * terms of bit offsets. Eschewing the bitfield constants such as + * SDXI_DSC_VL in the test code makes it possible for the tests to + * detect any mistakes in defining them. + * + * Note that the checks in unpack_fields() can be quite time-consuming + * at build time. Uncomment '#define SKIP_PACKING_CHECKS' below if + * that's too annoying when working on this code. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "descriptor.h" + +/* #define SKIP_PACKING_CHECKS */ + +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); + +enum { + SDXI_PACKING_QUIRKS =3D QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST, +}; + + +#define desc_field(_high, _low, _target_struct, _member) \ + PACKED_FIELD(_high, _low, _target_struct, _member) +#define desc_flag(_bit, _target_struct, _member) \ + desc_field(_bit, _bit, _target_struct, _member) + +/* DMAB_COPY */ +struct unpacked__copy { + u32 size; + u8 attr_src; + u8 attr_dst; + u16 akey0; + u16 akey1; + u64 addr0; + u64 addr1; +}; + +#define copy_field(_high, _low, _member) \ + desc_field(_high, _low, struct unpacked__copy, _member) + +static const struct packed_field_u16 copy_subfields[] =3D { + copy_field(63, 32, size), + copy_field(67, 64, attr_src), + copy_field(71, 68, attr_dst), + copy_field(111, 96, akey0), + copy_field(127, 112, akey1), + copy_field(191, 128, addr0), + copy_field(255, 192, addr1), +}; + +/* DSC_INTR */ +struct unpacked__intr { + u16 akey; +}; + +#define intr_field(_high, _low, _member) \ + desc_field(_high, _low, struct unpacked__intr, _member) + +static const struct packed_field_u16 intr_subfields[] =3D { + intr_field(111, 96, akey), +}; + +/* DSC_SYNC */ +struct unpacked__sync { + u8 flt; + bool vf; + u16 vf_num; + u16 cxt_start; + u16 cxt_end; + u16 key_start; + u16 key_end; +}; + +#define sync_field(_high, _low, _member) \ + desc_field(_high, _low, struct unpacked__sync, _member) +#define sync_flag(_bit, _member) sync_field(_bit, _bit, _member) + +static const struct packed_field_u16 sync_subfields[] =3D { + sync_field(34, 32, flt), + sync_flag(47, vf), + sync_field(63, 48, vf_num), + sync_field(79, 64, cxt_start), + sync_field(95, 80, cxt_end), + sync_field(111, 96, key_start), + sync_field(127, 112, key_end), +}; + +/* DSC_CXT_START */ +struct unpacked__cxt_start { + bool dv; + bool vf; + u16 vf_num; + u16 cxt_start; + u16 cxt_end; + u64 db_value; +}; + +#define cxt_start_field(_high, _low, _member) \ + desc_field(_high, _low, struct unpacked__cxt_start, _member) +#define cxt_start_flag(_bit, _member) cxt_start_field(_bit, _bit, _member) + +static const struct packed_field_u16 cxt_start_subfields[] =3D { + cxt_start_flag(46, dv), + cxt_start_flag(47, vf), + cxt_start_field(63, 48, vf_num), + cxt_start_field(79, 64, cxt_start), + cxt_start_field(95, 80, cxt_end), + cxt_start_field(191, 128, db_value), +}; + +/* DSC_CXT_STOP */ +struct unpacked__cxt_stop { + bool hs; + bool vf; + u16 vf_num; + u16 cxt_start; + u16 cxt_end; +}; + +#define cxt_stop_field(_high, _low, _member) \ + desc_field(_high, _low, struct unpacked__cxt_stop, _member) +#define cxt_stop_flag(_bit, _member) cxt_stop_field(_bit, _bit, _member) + +static const struct packed_field_u16 cxt_stop_subfields[] =3D { + cxt_stop_flag(45, hs), + cxt_stop_flag(47, vf), + cxt_stop_field(63, 48, vf_num), + cxt_stop_field(79, 64, cxt_start), + cxt_stop_field(95, 80, cxt_end), +}; + +/* DSC_GENERIC */ +struct unpacked_desc { + u64 csb_ptr; + u16 type; + u8 subtype; + bool vl; + bool se; + bool fe; + bool ch; + bool csr; + bool rb; + bool np; + union { + struct unpacked__copy copy; + struct unpacked__intr intr; + struct unpacked__sync sync; + struct unpacked__cxt_start cxt_start; + struct unpacked__cxt_stop cxt_stop; + }; +}; + +#define generic_field(_high, _low, _member) \ + desc_field(_high, _low, struct unpacked_desc, _member) +#define generic_flag(_bit, _member) generic_field(_bit, _bit, _member) + +static const struct packed_field_u16 generic_subfields[] =3D { + generic_flag(0, vl), + generic_flag(1, se), + generic_flag(2, fe), + generic_flag(3, ch), + generic_flag(4, csr), + generic_flag(5, rb), + generic_field(15, 8, subtype), + generic_field(26, 16, type), + generic_flag(448, np), + generic_field(511, 453, csb_ptr), +}; + +#ifndef SKIP_PACKING_CHECKS +#define define_unpack_fn(_T) \ + static void unpack_ ## _T(struct unpacked_desc *to, \ + const struct sdxi_desc *from) \ + { \ + unpack_fields(from, sizeof(*from), to, \ + generic_subfields, SDXI_PACKING_QUIRKS); \ + unpack_fields(from, sizeof(*from), &to->_T, \ + _T ## _subfields, SDXI_PACKING_QUIRKS); \ + } +#else +#define define_unpack_fn(_T) \ + static void unpack_ ## _T(struct unpacked_desc *to, \ + const struct sdxi_desc *from) \ + { \ + unpack_fields_u16(from, sizeof(*from), to, \ + generic_subfields, \ + ARRAY_SIZE(generic_subfields), \ + SDXI_PACKING_QUIRKS); \ + unpack_fields_u16(from, sizeof(*from), &to->_T, \ + _T ## _subfields, \ + ARRAY_SIZE(_T ## _subfields), \ + SDXI_PACKING_QUIRKS); \ + } +#endif /* SKIP_PACKING_CHECKS */ + +define_unpack_fn(intr) +define_unpack_fn(copy) +define_unpack_fn(sync) +define_unpack_fn(cxt_start) +define_unpack_fn(cxt_stop) + +static void desc_poison(struct sdxi_desc *d) +{ + memset(d, 0xff, sizeof(*d)); +} + +static void encode_size32(struct kunit *t) +{ + __le32 res =3D cpu_to_le32(U32_MAX); + + /* Valid sizes. */ + KUNIT_EXPECT_EQ(t, 0, sdxi_encode_size32(1, &res)); + KUNIT_EXPECT_EQ(t, 0, le32_to_cpu(res)); + + KUNIT_EXPECT_EQ(t, 0, sdxi_encode_size32(SZ_4K, &res)); + KUNIT_EXPECT_EQ(t, SZ_4K - 1, le32_to_cpu(res)); + + KUNIT_EXPECT_EQ(t, 0, sdxi_encode_size32(SZ_4M, &res)); + KUNIT_EXPECT_EQ(t, SZ_4M - 1, le32_to_cpu(res)); + + KUNIT_EXPECT_EQ(t, 0, sdxi_encode_size32(SZ_4G - 1, &res)); + KUNIT_EXPECT_EQ(t, SZ_4G - 2, le32_to_cpu(res)); + + KUNIT_EXPECT_EQ(t, 0, sdxi_encode_size32(SZ_4G, &res)); + KUNIT_EXPECT_EQ(t, SZ_4G - 1, le32_to_cpu(res)); + + /* Invalid sizes. Ensure the out parameter is unmodified. */ +#define RES_VAL 0x843829 + res =3D cpu_to_le32(RES_VAL); + + KUNIT_EXPECT_EQ(t, -EINVAL, sdxi_encode_size32(0, &res)); + KUNIT_EXPECT_EQ(t, RES_VAL, le32_to_cpu(res)); + + KUNIT_EXPECT_EQ(t, -EINVAL, sdxi_encode_size32(SZ_4G + 1, &res)); + KUNIT_EXPECT_EQ(t, RES_VAL, le32_to_cpu(res)); + + KUNIT_EXPECT_EQ(t, -EINVAL, sdxi_encode_size32(SZ_8G, &res)); + KUNIT_EXPECT_EQ(t, RES_VAL, le32_to_cpu(res)); + + KUNIT_EXPECT_EQ(t, -EINVAL, sdxi_encode_size32(U64_MAX, &res)); + KUNIT_EXPECT_EQ(t, RES_VAL, le32_to_cpu(res)); + +#undef RES_VAL +} + +static void copy(struct kunit *t) +{ + struct unpacked_desc unpacked; + struct sdxi_desc desc =3D {}; + struct sdxi_copy copy =3D { + .src =3D 0x1000, + .dst =3D 0x2000, + .len =3D 4096, + .src_akey =3D 0, + .dst_akey =3D 0, + }; + + KUNIT_EXPECT_EQ(t, 0, sdxi_encode_copy(&desc, ©)); + + unpack_copy(&unpacked, &desc); + KUNIT_EXPECT_EQ(t, unpacked.vl, 0); + KUNIT_EXPECT_EQ(t, unpacked.ch, 0); + KUNIT_EXPECT_EQ(t, unpacked.subtype, SDXI_DSC_OP_SUBTYPE_COPY); + KUNIT_EXPECT_EQ(t, unpacked.type, SDXI_DSC_OP_TYPE_DMAB); + KUNIT_EXPECT_EQ(t, unpacked.csb_ptr, 0); + KUNIT_EXPECT_EQ(t, unpacked.np, 1); + + KUNIT_EXPECT_EQ(t, unpacked.copy.size, copy.len - 1); + + /* Zero isn't a valid size. */ + desc_poison(&desc); + copy.len =3D 0; + KUNIT_EXPECT_EQ(t, -EINVAL, sdxi_encode_copy(&desc, ©)); + + /* But 1 is. */ + desc_poison(&desc); + copy.len =3D 1; + KUNIT_EXPECT_EQ(t, 0, sdxi_encode_copy(&desc, ©)); + unpack_copy(&unpacked, &desc); + KUNIT_EXPECT_EQ(t, unpacked.copy.size, copy.len - 1); + + /* SDXI forbids overlapping source and destination. */ + desc_poison(&desc); + copy.len =3D 4097; + KUNIT_EXPECT_EQ(t, -EINVAL, sdxi_encode_copy(&desc, ©)); + copy =3D (typeof(copy)) { + .src =3D 0x4000, + .dst =3D 0x4000, + .len =3D 1, + .src_akey =3D 0, + .dst_akey =3D 0, + }; + KUNIT_EXPECT_EQ(t, -EINVAL, sdxi_encode_copy(&desc, ©)); + + desc_poison(&desc); + KUNIT_EXPECT_EQ(t, 0, + sdxi_encode_copy(&desc, + &(struct sdxi_copy) { + .src =3D 0x1000, + .dst =3D 0x2000, + .len =3D 0x100, + .src_akey =3D 1, + .dst_akey =3D 2, + })); + KUNIT_EXPECT_EQ(t, 0x1000, le64_to_cpu(desc.copy.addr0)); + KUNIT_EXPECT_EQ(t, 0x2000, le64_to_cpu(desc.copy.addr1)); + KUNIT_EXPECT_EQ(t, 0x100, 1 + le32_to_cpu(desc.copy.size)); + KUNIT_EXPECT_EQ(t, 1, le16_to_cpu(desc.copy.akey0)); + KUNIT_EXPECT_EQ(t, 2, le16_to_cpu(desc.copy.akey1)); + + unpack_copy(&unpacked, &desc); + KUNIT_EXPECT_EQ(t, unpacked.vl, 0); + KUNIT_EXPECT_EQ(t, unpacked.ch, 0); + KUNIT_EXPECT_EQ(t, unpacked.subtype, SDXI_DSC_OP_SUBTYPE_COPY); + KUNIT_EXPECT_EQ(t, unpacked.type, SDXI_DSC_OP_TYPE_DMAB); + KUNIT_EXPECT_EQ(t, unpacked.csb_ptr, 0); + KUNIT_EXPECT_EQ(t, unpacked.np, 1); + + KUNIT_EXPECT_EQ(t, unpacked.copy.size, 0x100 - 1); +} + +static void intr(struct kunit *t) +{ + struct unpacked_desc unpacked; + struct sdxi_intr intr =3D { + .akey =3D 1234, + }; + struct sdxi_desc desc; + + desc_poison(&desc); + KUNIT_EXPECT_EQ(t, 0, sdxi_encode_intr(&desc, &intr)); + + unpack_intr(&unpacked, &desc); + KUNIT_EXPECT_EQ(t, unpacked.vl, 0); + KUNIT_EXPECT_EQ(t, unpacked.ch, 0); + KUNIT_EXPECT_EQ(t, unpacked.subtype, SDXI_DSC_OP_SUBTYPE_INTR); + KUNIT_EXPECT_EQ(t, unpacked.type, SDXI_DSC_OP_TYPE_INTR); + KUNIT_EXPECT_EQ(t, unpacked.csb_ptr, 0); + KUNIT_EXPECT_EQ(t, unpacked.np, 1); + + KUNIT_EXPECT_EQ(t, unpacked.intr.akey, 1234); +} + +static void cxt_start(struct kunit *t) +{ + struct unpacked_desc unpacked; + struct sdxi_cxt_start start =3D { + .range =3D sdxi_cxt_range_single(2), + }; + struct sdxi_desc desc; + + desc_poison(&desc); + KUNIT_ASSERT_EQ(t, 0, sdxi_encode_cxt_start(&desc, &start)); + + unpack_cxt_start(&unpacked, &desc); + + /* Check op-specific fields. */ + KUNIT_EXPECT_EQ(t, 0, desc.cxt_start.vflags); + + /* + * Check generic fields. Some flags have mandatory values + * according to the operation type. + */ + KUNIT_EXPECT_EQ(t, unpacked.vl, 0); + KUNIT_EXPECT_EQ(t, unpacked.se, 0); + KUNIT_EXPECT_EQ(t, unpacked.fe, 1); + KUNIT_EXPECT_EQ(t, unpacked.ch, 0); + KUNIT_EXPECT_EQ(t, unpacked.subtype, SDXI_DSC_OP_SUBTYPE_CXT_START_NM); + KUNIT_EXPECT_EQ(t, unpacked.type, SDXI_DSC_OP_TYPE_ADMIN); + KUNIT_EXPECT_EQ(t, unpacked.csb_ptr, 0); + KUNIT_EXPECT_EQ(t, unpacked.np, 1); + + KUNIT_EXPECT_FALSE(t, unpacked.cxt_start.dv); + KUNIT_EXPECT_FALSE(t, unpacked.cxt_start.vf); + KUNIT_EXPECT_EQ(t, unpacked.cxt_start.cxt_start, 2); + KUNIT_EXPECT_EQ(t, unpacked.cxt_start.cxt_end, 2); + KUNIT_EXPECT_EQ(t, unpacked.cxt_start.vf_num, 0); + KUNIT_EXPECT_EQ(t, unpacked.cxt_start.db_value, 0); +} + +static void cxt_stop(struct kunit *t) +{ + struct unpacked_desc unpacked; + struct sdxi_cxt_stop stop =3D { + .range =3D sdxi_cxt_range_single(2), + }; + struct sdxi_desc desc; + + desc_poison(&desc); + KUNIT_ASSERT_EQ(t, 0, sdxi_encode_cxt_stop(&desc, &stop)); + + unpack_cxt_stop(&unpacked, &desc); + + /* Check op-specific fields. */ + KUNIT_EXPECT_EQ(t, 0, desc.cxt_start.vflags); + + /* + * Check generic fields. Some flags have mandatory values + * according to the operation type. + */ + KUNIT_EXPECT_EQ(t, unpacked.vl, 0); + KUNIT_EXPECT_EQ(t, unpacked.se, 0); + KUNIT_EXPECT_EQ(t, unpacked.fe, 1); + KUNIT_EXPECT_EQ(t, unpacked.ch, 0); + KUNIT_EXPECT_EQ(t, unpacked.subtype, SDXI_DSC_OP_SUBTYPE_CXT_STOP); + KUNIT_EXPECT_EQ(t, unpacked.type, SDXI_DSC_OP_TYPE_ADMIN); + KUNIT_EXPECT_EQ(t, unpacked.csb_ptr, 0); + KUNIT_EXPECT_EQ(t, unpacked.np, 1); + + KUNIT_EXPECT_FALSE(t, unpacked.cxt_stop.hs); + KUNIT_EXPECT_FALSE(t, unpacked.cxt_stop.vf); + KUNIT_EXPECT_EQ(t, unpacked.cxt_stop.cxt_start, 2); + KUNIT_EXPECT_EQ(t, unpacked.cxt_stop.cxt_end, 2); + KUNIT_EXPECT_EQ(t, unpacked.cxt_stop.vf_num, 0); +} + +static void sync(struct kunit *t) +{ + struct sdxi_sync sync =3D { + .filter =3D SDXI_SYNC_FLT_STOP, + .range =3D sdxi_cxt_range(1, U16_MAX), + }; + struct sdxi_desc desc; + struct unpacked_desc unpacked; + + desc_poison(&desc); + KUNIT_ASSERT_EQ(t, 0, sdxi_encode_sync(&desc, &sync)); + unpack_sync(&unpacked, &desc); + + KUNIT_EXPECT_EQ(t, unpacked.type, SDXI_DSC_OP_TYPE_ADMIN); + KUNIT_EXPECT_EQ(t, unpacked.subtype, SDXI_DSC_OP_SUBTYPE_SYNC); + KUNIT_EXPECT_EQ(t, unpacked.ch, 0); + KUNIT_EXPECT_EQ(t, unpacked.sync.flt, SDXI_SYNC_FLT_STOP); + KUNIT_EXPECT_EQ(t, unpacked.sync.cxt_start, 1); + KUNIT_EXPECT_EQ(t, unpacked.sync.cxt_end, U16_MAX); +} + +static struct kunit_case generic_desc_tcs[] =3D { + KUNIT_CASE(encode_size32), + KUNIT_CASE(copy), + KUNIT_CASE(intr), + KUNIT_CASE(cxt_start), + KUNIT_CASE(cxt_stop), + KUNIT_CASE(sync), + {} +}; + +static int generic_desc_setup_device(struct kunit *t) +{ + struct device *dev =3D kunit_device_register(t, "sdxi-mock-device"); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(t, dev); + t->priv =3D dev; + return 0; +} + +static struct kunit_suite generic_desc_ts =3D { + .name =3D "Generic SDXI descriptor encoding", + .test_cases =3D generic_desc_tcs, + .init =3D generic_desc_setup_device, +}; +kunit_test_suite(generic_desc_ts); + +MODULE_DESCRIPTION("SDXI descriptor encoding tests"); +MODULE_AUTHOR("Nathan Lynch"); +MODULE_LICENSE("GPL"); --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id EDBA028641E; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704144; cv=none; b=mY+Q3tE/HhTTEHO3g4hSEBeyFmt4o3FhrY/PH8gVCD1L7hW4mNAzXyYrkWz65dp4JeND+34WFHI5Q6HUAxGi0uYt1ElZ1g2fI8Qsfj3Q9JXtrxnFk/t3QQU+Fj4kwx6sPiMCxeQEolDfDCCMfAfMjuzmt0+dIuth2CTQ8K8dnBA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704144; c=relaxed/simple; bh=4rQ7SHuShPecsqwQ8fZplFGBmiR2B3O2AZi5n7+SMAk=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=ErX5uXfxGA10fZ9K0aSPjQh/IyZ3AhkSQtg92wsiSLjCu72xkOqRX8URNy8rwbWQHgYSnsSJckfF5JhLqSPsmnkjavf1lJvDHpfRrynUFi5NArlz4/labdywwtZ6r8bnI5DOOW+4i2QxDKjS/yGs/t+6ez89YbGDm3Ce9yPPmhI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=oWtfupyS; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="oWtfupyS" Received: by smtp.kernel.org (Postfix) with ESMTPS id CFD31C2BCF5; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=4rQ7SHuShPecsqwQ8fZplFGBmiR2B3O2AZi5n7+SMAk=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=oWtfupyS0bIkJqiHYdjjdse4vh97sxZh06bDri37HYpDdtfH2k11jknUCMpHh8Hak ZD3EyZVdkO6pxq3G3NkJv6fG/Ovwx4bcYpypm/w7Q3n4qg5YYNOHpT+w9HxYC7N10O AjQdtduiA8/yqWOoT8LsmdhGeB7sVBVEk+f6GxrZe/Z/X8aX53A5yVEJp4xM5EIGhx I/S11C9NT+bzaFu7Ki0m8Zj5W5lqkyGQe2VlyqG77zzoT8i/AY9STWarD81wncpVmq lD+ZJASwQhCxuM/7Ts+B2YZa0/1RVmKXkc42QrogT2zYa+QI6UlbRDeaMidLlU69QW j6Q5xhjXoLUEg== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id C7835CD6E7B; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:25 -0500 Subject: [PATCH v3 22/23] dmaengine: sdxi: MSI/MSI-X vector allocation and mapping 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: <20260605-sdxi-base-v3-22-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Frank Li , Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=6724; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=55V3Gi65dyKbTVEytbitSLn8sTX3+Q0lnJO/cdnFbfo=; b=h8JqKAtK7xHYtj1OcazHbQJC/0YkmSP8WP63ExLXaqD6GFo2p0T6KP4vZNw0iaXvoqkGl6nMf Q1H5ULGr8obC0izw4dicptDYrzR9i67VBMSrNfOMsBmhXOlYfsekjSx X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch During PCI probe, allocate a vector per context supported by the function as reported by the capability register, plus one for the error log interrupt, which is always vector 0. The rest of the vector range is available for use with interrupt-generating descriptors. Introduce sdxi_alloc_vector() and sdxi_free_vector() which are thin wrappers around the IDA that tracks the allocated vector range. Introduce sdxi_vector_to_irq() which invokes a new get_irq() bus op to translate the device-relative index to the Linux IRQ number for use with request_irq() etc. For PCI this dispatches to pci_irq_vector(). Code such as the DMA engine provider that intends to submit interrupt descriptors should prepare by using sdxi_alloc_vector() and sdxi_vector_to_irq(), and clean up by using sdxi_free_vector(). Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Frank Li Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/device.c | 4 ++++ drivers/dma/sdxi/pci.c | 28 ++++++++++++++++++++++- drivers/dma/sdxi/sdxi.h | 57 +++++++++++++++++++++++++++++++++++++++++++= ++++ 3 files changed, 88 insertions(+), 1 deletion(-) diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index d3d1ad2f2eff..26be376c9545 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -334,6 +335,7 @@ int sdxi_register(struct device *dev, const struct sdxi= _bus_ops *ops) =20 sdxi->dev =3D dev; sdxi->bus_ops =3D ops; + ida_init(&sdxi->vectors); xa_init_flags(&sdxi->client_cxts, XA_FLAGS_ALLOC1); dev_set_drvdata(dev, sdxi); =20 @@ -355,6 +357,8 @@ void sdxi_unregister(struct device *dev) sdxi_cxt_exit(cxt); xa_destroy(&sdxi->client_cxts); =20 + ida_destroy(&sdxi->vectors); + sdxi_dev_stop(sdxi); } EXPORT_SYMBOL_NS_GPL(sdxi_unregister, "SDXI"); diff --git a/drivers/dma/sdxi/pci.c b/drivers/dma/sdxi/pci.c index 4d7d6812da6d..4f981e843138 100644 --- a/drivers/dma/sdxi/pci.c +++ b/drivers/dma/sdxi/pci.c @@ -5,6 +5,7 @@ * Copyright Advanced Micro Devices, Inc. */ =20 +#include #include #include #include @@ -13,6 +14,7 @@ #include #include =20 +#include "mmio.h" #include "sdxi.h" =20 enum sdxi_mmio_bars { @@ -29,7 +31,8 @@ static int sdxi_pci_init(struct sdxi_dev *sdxi) { struct pci_dev *pdev =3D sdxi_to_pci_dev(sdxi); struct device *dev =3D &pdev->dev; - int ret; + unsigned int cap1_max_cxt; + int vecs, ret; =20 ret =3D pcim_enable_device(pdev); if (ret) @@ -49,12 +52,35 @@ static int sdxi_pci_init(struct sdxi_dev *sdxi) return dev_err_probe(dev, PTR_ERR(sdxi->dbs), "failed to map doorbell region\n"); =20 + /* + * Allocate the minimum required set of vectors plus one for + * each client context supported by the function. + */ + cap1_max_cxt =3D FIELD_GET(SDXI_MMIO_CAP1_MAX_CXT, + sdxi_read64(sdxi, SDXI_MMIO_CAP1)); + vecs =3D pci_alloc_irq_vectors(pdev, SDXI_MIN_VECTORS, + SDXI_MIN_VECTORS + cap1_max_cxt, + PCI_IRQ_MSI | PCI_IRQ_MSIX); + if (vecs < 0) + return dev_err_probe(dev, vecs, + "failed to allocate MSIs (max_cxt=3D%u)\n", + cap1_max_cxt); + + sdxi->nr_vectors =3D vecs; + dev_dbg(sdxi->dev, "allocated %u vectors\n", sdxi->nr_vectors); + pci_set_master(pdev); return 0; } =20 +static int sdxi_pci_get_irq(struct sdxi_dev *sdxi, unsigned int nr) +{ + return pci_irq_vector(sdxi_to_pci_dev(sdxi), nr); +} + static const struct sdxi_bus_ops sdxi_pci_ops =3D { .init =3D sdxi_pci_init, + .get_irq =3D sdxi_pci_get_irq, }; =20 static int sdxi_pci_probe(struct pci_dev *pdev, diff --git a/drivers/dma/sdxi/sdxi.h b/drivers/dma/sdxi/sdxi.h index 4e29d1f90dae..72482d7c301e 100644 --- a/drivers/dma/sdxi/sdxi.h +++ b/drivers/dma/sdxi/sdxi.h @@ -8,8 +8,10 @@ #ifndef DMA_SDXI_H #define DMA_SDXI_H =20 +#include #include #include +#include #include #include #include @@ -25,6 +27,21 @@ #define L1_CXT_CTRL_PTR_SHIFT 6 #define L1_CXT_AKEY_PTR_SHIFT 12 =20 +enum { + /* + * Per SDXI 1.0 3.4 Error Log, the error log interrupt is + * always vector 0. + */ + SDXI_ERROR_VECTOR =3D 0, + + /* + * Request at least one vector to account for the error log + * interrupt. Increment this if the driver gains more + * dedicated interrupts (e.g. one for the admin context). + */ + SDXI_MIN_VECTORS =3D 1, +}; + struct sdxi_dev; =20 /** @@ -37,6 +54,10 @@ struct sdxi_bus_ops { * function initialization. */ int (*init)(struct sdxi_dev *sdxi); + /** + * @get_irq: Map device interrupt index to Linux IRQ number. + */ + int (*get_irq)(struct sdxi_dev *sdxi, unsigned int index); }; =20 struct sdxi_dev { @@ -59,12 +80,48 @@ struct sdxi_dev { struct dma_pool *cxt_ctl_pool; struct dma_pool *cst_blk_pool; =20 + unsigned int nr_vectors; + struct ida vectors; + struct sdxi_cxt *admin_cxt; struct xarray client_cxts; /* context id -> (struct sdxi_cxt *) */ =20 const struct sdxi_bus_ops *bus_ops; }; =20 +/** + * sdxi_alloc_vector() - Allocate an interrupt vector. + * + * A vector that will have the same lifetime as the device does not + * need to be released explicitly. Otherwise the vector must be + * released with sdxi_free_vector(). + */ +static inline int sdxi_alloc_vector(struct sdxi_dev *sdxi) +{ + return ida_alloc_range(&sdxi->vectors, SDXI_MIN_VECTORS, + sdxi->nr_vectors - 1, GFP_KERNEL); +} + +/** + * sdxi_free_vector() - Release a previously allocated index. + */ +static inline void sdxi_free_vector(struct sdxi_dev *sdxi, unsigned int nr) +{ + ida_free(&sdxi->vectors, nr); +} + +/** + * sdxi_vector_to_irq() - Translate an allocated interrupt vector to + * Linux IRQ number suitable for passing to + * request_irq() et al. + */ +static inline int sdxi_vector_to_irq(struct sdxi_dev *sdxi, unsigned int n= r) +{ + /* Moan if the index isn't currently allocated. */ + WARN_ON_ONCE(!ida_exists(&sdxi->vectors, nr)); + return sdxi->bus_ops->get_irq(sdxi, nr); +} + int sdxi_register(struct device *dev, const struct sdxi_bus_ops *ops); void sdxi_unregister(struct device *dev); =20 --=20 2.54.0 From nobody Mon Jun 8 06:35:40 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1003E2BEFE8; Sat, 6 Jun 2026 00:02:24 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704144; cv=none; b=YRQ/HFh+hvYe9MZTGSj6saz5Nhd1ozDgk05IlpR9Q5fRDE71FXsqTwkPxA1YM5cMVPfqcRXxTKcYIOy+P6TowQlLOirBFep6WcDlcBGffp6yuD+SmWmWjHGBEX4fthbuga9K0fUwavmov7x9WzmzhD0Jl0pdYAf1huLNZg82xLs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1780704144; c=relaxed/simple; bh=CN0I+xotu9H3/eU6UYvjHZjRPVYXAIfurZFwH5UCUG8=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=YkYwSG2pTcBNsAB/wdU16q3xy/M5fdCPfB5n31/NKKxMSRoBZmU4SJWdHJVfz+EQq0uhaCLphD6pEimF0wzK4f4g6wwbk4Pmrp99eG0NoDOLjMcqhj52o6IFudWmxhNgRq8L8w6TzMxxT05M1M2Kr0QG8DGoM7lH5GM05AJ2ug0= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=olh+U113; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="olh+U113" Received: by smtp.kernel.org (Postfix) with ESMTPS id E52ACC2BCB4; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1780704143; bh=CN0I+xotu9H3/eU6UYvjHZjRPVYXAIfurZFwH5UCUG8=; h=From:Date:Subject:References:In-Reply-To:To:Cc:Reply-To:From; b=olh+U113Hm3X1ZPUtaIcgd1lam7bI/lhYkknzx9J7YBNui6a6WNu4ZtYM0RvIC/AJ R5BTlopZjrys85AGx6b77Esv3Myd/TzxM31a7p1QYWa1PLxah5sd+JFUgspi7yEJGI JIAduFGIj+I4KjtgMqhrLGdB5XsQKmk3hPE4Ohl5nhUnMqTp9ISqSuQpKHQnp5OZ/F XURi87kfkzF6adqEu4GL738T50gktzznDuITDMZtHzrcODEGP+5v2NUTA6YjvQUJor m/93B8e2gRy+uWpyNyDgoFT6+D/N3VP10MZenM/TmhiP0DLcA0m2Iwi9mguVKN0vYc Vx+nCIH2ttdEw== Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id DCB0ECD8C8B; Sat, 6 Jun 2026 00:02:23 +0000 (UTC) From: Nathan Lynch via B4 Relay Date: Fri, 05 Jun 2026 19:02:26 -0500 Subject: [PATCH v3 23/23] dmaengine: sdxi: Add DMA engine provider 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: <20260605-sdxi-base-v3-23-4d38ca2bdffe@amd.com> References: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> In-Reply-To: <20260605-sdxi-base-v3-0-4d38ca2bdffe@amd.com> To: Vinod Koul , Frank Li Cc: Bjorn Helgaas , David Rientjes , John.Kariuki@amd.com, Jonathan Cameron , Kinsey Ho , Mario Limonciello , PradeepVineshReddy.Kodamati@amd.com, Shivank Garg , Stephen Bates , Tycho Andersen , Wei Huang , Wei Xu , dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org, Nathan Lynch X-Mailer: b4 0.15.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1780704140; l=17048; i=nathan.lynch@amd.com; s=20260410; h=from:subject:message-id; bh=F11Z7ijEZLO1+5NUxTgTWxs5O81cPT3FIiv2kCF1Bkg=; b=BvxGqrUKZPk/Hw4EzjNM5dw6jjTqbLhs+g1xPzyawD+4j6U1p86mfusIjCJgv5Nv/F0ys2zIC LVWpSqhebMvCWXvw7vydSxodJNppVLlnuGGarns/DkgSX3KGxQpTMzT X-Developer-Key: i=nathan.lynch@amd.com; a=ed25519; pk=PK4ozhq+/z9/2Jl5rgDmvHa9raVomv79qM8p1RAFpEw= X-Endpoint-Received: by B4 Relay for nathan.lynch@amd.com/20260410 with auth_id=728 X-Original-From: Nathan Lynch Reply-To: nathan.lynch@amd.com From: Nathan Lynch Register a DMA engine provider that implements memcpy. The number of channels per SDXI function can be controlled via a module parameter (dma_channels). The provider uses the virt-dma library. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Signed-off-by: Nathan Lynch --- drivers/dma/sdxi/Kconfig | 1 + drivers/dma/sdxi/Makefile | 1 + drivers/dma/sdxi/device.c | 2 + drivers/dma/sdxi/dma.c | 501 ++++++++++++++++++++++++++++++++++++++++++= ++++ drivers/dma/sdxi/dma.h | 11 + 5 files changed, 516 insertions(+) diff --git a/drivers/dma/sdxi/Kconfig b/drivers/dma/sdxi/Kconfig index 314b3e725ccb..85e23608405c 100644 --- a/drivers/dma/sdxi/Kconfig +++ b/drivers/dma/sdxi/Kconfig @@ -4,6 +4,7 @@ config SDXI_CORE # SDXI 1.0 9 MMIO Control Registers. depends on 64BIT select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS help Enable support for Smart Data Accelerator Interface (SDXI) Platform Data Mover devices. SDXI is a vendor-neutral diff --git a/drivers/dma/sdxi/Makefile b/drivers/dma/sdxi/Makefile index 5218ae2c86ae..d7ea5776191e 100644 --- a/drivers/dma/sdxi/Makefile +++ b/drivers/dma/sdxi/Makefile @@ -5,6 +5,7 @@ sdxi-core-y :=3D \ context.o \ descriptor.o \ device.o \ + dma.o \ ring.o =20 obj-$(CONFIG_SDXI_PCI) +=3D sdxi-pci.o diff --git a/drivers/dma/sdxi/device.c b/drivers/dma/sdxi/device.c index 26be376c9545..d6097a6d8992 100644 --- a/drivers/dma/sdxi/device.c +++ b/drivers/dma/sdxi/device.c @@ -22,6 +22,7 @@ #include =20 #include "context.h" +#include "dma.h" #include "hw.h" #include "mmio.h" #include "sdxi.h" @@ -321,6 +322,7 @@ static int sdxi_device_init(struct sdxi_dev *sdxi) if (err) return err; =20 + sdxi_dma_register(sdxi); return 0; } =20 diff --git a/drivers/dma/sdxi/dma.c b/drivers/dma/sdxi/dma.c new file mode 100644 index 000000000000..01c85cc2763d --- /dev/null +++ b/drivers/dma/sdxi/dma.c @@ -0,0 +1,501 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SDXI dmaengine provider + * + * Copyright Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../dmaengine.h" +#include "../virt-dma.h" +#include "completion.h" +#include "context.h" +#include "descriptor.h" +#include "dma.h" +#include "ring.h" +#include "sdxi.h" + +static unsigned short dma_channels =3D 1; +module_param(dma_channels, ushort, 0644); +MODULE_PARM_DESC(dma_channels, "DMA channels per function (default: 1)"); + +/* + * An SDXI context is allocated for each channel configured. + * + * Each context has a descriptor ring with a minimum of 1K entries. + * SDXI supports a variety of primitive operations, e.g. copy, + * interrupt, nop. Each Linux virtual DMA descriptor may be composed + * of a grouping of SDXI descriptors in the ring. E.g. two SDXI + * descriptors (copy, then interrupt) to implement a + * dma_async_tx_descriptor for memcpy with DMA_PREP_INTERRUPT flag. + * + * dma_device->device_prep_dma_* functions reserve space in the + * descriptor ring and serialize SDXI descriptors implementing the + * operation to the reserved slots, leaving their valid (vl) bits + * clear. A single virtual descriptor is added to the allocated list. + * + * dma_async_tx_descriptor->tx_submit() invokes vchan_tx_submit(), + * which merely assigns a cookie and moves the txd to the submitted + * list without entering the SDXI provider code. + * + * dma_device->device_issue_pending() (sdxi_dma_issue_pending()) sets vl + * on each SDXI descriptor reachable from the submitted list, then + * rings the context doorbell. The submitted txds are moved to the + * issued list via vchan_issue_pending(). + */ + +struct sdxi_dma_chan { + struct virt_dma_chan vchan; + struct sdxi_cxt *cxt; + unsigned int vector; + unsigned int irq; + struct sdxi_akey_ent *akey; +}; + +struct sdxi_dma_dev { + struct dma_device dma_dev; + size_t nr_channels; + struct sdxi_dma_chan sdchan[] __counted_by(nr_channels); +}; + +/* + * A virtual descriptor can correspond to a group of SDXI hardware descrip= tors. + */ +struct sdxi_dma_desc { + struct virt_dma_desc vdesc; + struct sdxi_ring_resv resv; + struct sdxi_completion *completion; +}; + +static struct sdxi_dma_chan *to_sdxi_dma_chan(const struct dma_chan *dma_c= han) +{ + const struct virt_dma_chan *vchan; + + vchan =3D container_of_const(dma_chan, struct virt_dma_chan, chan); + return container_of(vchan, struct sdxi_dma_chan, vchan); +} + +static struct sdxi_dma_desc * +to_sdxi_dma_desc(const struct virt_dma_desc *vdesc) +{ + return container_of(vdesc, struct sdxi_dma_desc, vdesc); +} + +static void sdxi_tx_desc_free(struct virt_dma_desc *vdesc) +{ + struct sdxi_dma_desc *sddesc =3D to_sdxi_dma_desc(vdesc); + + sdxi_completion_free(sddesc->completion); + kfree(to_sdxi_dma_desc(vdesc)); +} + +static struct sdxi_dma_desc * +prep_memcpy_intr(struct dma_chan *dma_chan, const struct sdxi_copy *params) +{ + struct sdxi_cxt *cxt =3D to_sdxi_dma_chan(dma_chan)->cxt; + struct sdxi_akey_ent *akey =3D to_sdxi_dma_chan(dma_chan)->akey; + struct sdxi_desc *copy, *intr; + + struct sdxi_completion *comp __free(sdxi_completion) =3D sdxi_completion_= alloc(cxt->sdxi); + if (!comp) + return NULL; + + struct sdxi_dma_desc *sddesc __free(kfree) =3D kzalloc(sizeof(*sddesc), G= FP_NOWAIT); + if (!sddesc) + return NULL; + + if (sdxi_ring_try_reserve(cxt->ring_state, 2, &sddesc->resv)) + return NULL; + + copy =3D sdxi_ring_resv_next(&sddesc->resv); + (void)sdxi_encode_copy(copy, params); /* Caller checked validity. */ + sdxi_desc_set_fence(copy); /* Conservatively fence every descriptor. */ + sdxi_completion_attach(copy, comp); + + sddesc->completion =3D no_free_ptr(comp); + + intr =3D sdxi_ring_resv_next(&sddesc->resv); + sdxi_encode_intr(intr, &(const struct sdxi_intr) { + .akey =3D sdxi_akey_index(cxt, akey), + }); + /* Raise the interrupt only after the copy has completed. */ + sdxi_desc_set_fence(intr); + return_ptr(sddesc); +} + +static struct sdxi_dma_desc * +prep_memcpy_nointr(struct dma_chan *dma_chan, const struct sdxi_copy *para= ms) +{ + struct sdxi_cxt *cxt =3D to_sdxi_dma_chan(dma_chan)->cxt; + struct sdxi_desc *copy; + + struct sdxi_completion *comp __free(sdxi_completion) =3D sdxi_completion_= alloc(cxt->sdxi); + if (!comp) + return NULL; + + struct sdxi_dma_desc *sddesc __free(kfree) =3D kzalloc(sizeof(*sddesc), G= FP_NOWAIT); + if (!sddesc) + return NULL; + + if (sdxi_ring_try_reserve(cxt->ring_state, 1, &sddesc->resv)) + return NULL; + + copy =3D sdxi_ring_resv_next(&sddesc->resv); + (void)sdxi_encode_copy(copy, params); /* Caller checked validity. */ + sdxi_completion_attach(copy, comp); + + sddesc->completion =3D no_free_ptr(comp); + return_ptr(sddesc); +} + +static struct dma_async_tx_descriptor * +sdxi_dma_prep_memcpy(struct dma_chan *dma_chan, dma_addr_t dst, + dma_addr_t src, size_t len, unsigned long flags) +{ + struct sdxi_akey_ent *akey =3D to_sdxi_dma_chan(dma_chan)->akey; + struct sdxi_cxt *cxt =3D to_sdxi_dma_chan(dma_chan)->cxt; + u16 akey_index =3D sdxi_akey_index(cxt, akey); + struct sdxi_dma_desc *sddesc; + struct sdxi_copy copy =3D { + .src =3D src, + .dst =3D dst, + .src_akey =3D akey_index, + .dst_akey =3D akey_index, + .len =3D len, + }; + + /* + * Perform a trial encode to a dummy descriptor on the stack + * so we can reject bad inputs without touching the ring + * state. + */ + if (sdxi_encode_copy(&(struct sdxi_desc){}, ©)) + return NULL; + + sddesc =3D (flags & DMA_PREP_INTERRUPT) ? + prep_memcpy_intr(dma_chan, ©) : + prep_memcpy_nointr(dma_chan, ©); + + if (!sddesc) + return NULL; + + return vchan_tx_prep(to_virt_chan(dma_chan), &sddesc->vdesc, flags); +} + +static enum dma_status sdxi_tx_status(struct dma_chan *chan, + dma_cookie_t cookie, + struct dma_tx_state *state) +{ + struct sdxi_dma_chan *sdchan =3D to_sdxi_dma_chan(chan); + struct sdxi_dma_desc *sddesc; + enum dma_status status; + struct virt_dma_desc *vdesc; + + status =3D dma_cookie_status(chan, cookie, state); + if (status =3D=3D DMA_COMPLETE) + return status; + + guard(spinlock_irqsave)(&sdchan->vchan.lock); + + vdesc =3D vchan_find_desc(&sdchan->vchan, cookie); + if (!vdesc) + return status; + + sddesc =3D to_sdxi_dma_desc(vdesc); + + if (WARN_ON_ONCE(!sddesc->completion)) + return DMA_ERROR; + + if (!sdxi_completion_signaled(sddesc->completion)) + return DMA_IN_PROGRESS; + + if (sdxi_completion_errored(sddesc->completion)) + return DMA_ERROR; + + list_del(&vdesc->node); + vchan_cookie_complete(vdesc); + + return dma_cookie_status(chan, cookie, state); +} + +static void sdxi_dma_issue_pending(struct dma_chan *dma_chan) +{ + struct virt_dma_chan *vchan =3D to_virt_chan(dma_chan); + struct virt_dma_desc *vdesc; + u64 dbval =3D 0; + + scoped_guard(spinlock_irqsave, &vchan->lock) { + /* + * This can happen with racing submitters. + */ + if (list_empty(&vchan->desc_submitted)) + return; + + list_for_each_entry(vdesc, &vchan->desc_submitted, node) { + struct sdxi_dma_desc *sddesc =3D to_sdxi_dma_desc(vdesc); + struct sdxi_desc *hwdesc; + + sdxi_ring_resv_foreach(&sddesc->resv, hwdesc) + sdxi_desc_make_valid(hwdesc); + /* + * The reservations ought to be ordered + * ascending, but use umax() just in case. + */ + dbval =3D umax(sdxi_ring_resv_dbval(&sddesc->resv), dbval); + } + + vchan_issue_pending(vchan); + } + + /* + * The implementation is required to handle out-of-order + * doorbell updates; we can do this after dropping the + * lock. + */ + sdxi_cxt_push_doorbell(to_sdxi_dma_chan(dma_chan)->cxt, dbval); +} + +static int sdxi_dma_terminate_all(struct dma_chan *dma_chan) +{ + struct virt_dma_chan *vchan =3D to_virt_chan(dma_chan); + u64 dbval =3D 0; + + /* + * Allocated and submitted txds are in the ring but not valid + * yet. Overwrite them with nops and then set their valid + * bits. + * + * The implementation may start consuming these as soon as the + * valid bits flip. sdxi_dma_synchronize() will ensure they're + * all done. + */ + scoped_guard(spinlock_irqsave, &vchan->lock) { + struct virt_dma_desc *vdesc; + LIST_HEAD(head); + + list_splice_tail_init(&vchan->desc_allocated, &head); + list_splice_tail_init(&vchan->desc_submitted, &head); + + if (list_empty(&head)) + return 0; + + list_for_each_entry(vdesc, &head, node) { + struct sdxi_dma_desc *sddesc =3D to_sdxi_dma_desc(vdesc); + struct sdxi_desc *hwdesc; + + sdxi_ring_resv_foreach(&sddesc->resv, hwdesc) { + sdxi_serialize_nop(hwdesc); + sdxi_desc_make_valid(hwdesc); + } + + dbval =3D umax(sdxi_ring_resv_dbval(&sddesc->resv), dbval); + } + + list_splice_tail(&head, &vchan->desc_terminated); + } + + sdxi_cxt_push_doorbell(to_sdxi_dma_chan(dma_chan)->cxt, dbval); + + return 0; +} + +static void sdxi_dma_synchronize(struct dma_chan *dma_chan) +{ + struct sdxi_cxt *cxt =3D to_sdxi_dma_chan(dma_chan)->cxt; + struct sdxi_ring_resv resv; + struct sdxi_desc *nop; + int err; + + /* Submit a single nop with fence and wait for it to complete. */ + + if (sdxi_ring_reserve(cxt->ring_state, 1, &resv)) + return; + + struct sdxi_completion *comp __free(sdxi_completion) =3D sdxi_completion_= alloc(cxt->sdxi); + if (!comp) + return; + + nop =3D sdxi_ring_resv_next(&resv); + sdxi_serialize_nop(nop); + sdxi_completion_attach(nop, comp); + sdxi_desc_set_fence(nop); + sdxi_desc_make_valid(nop); + sdxi_cxt_push_doorbell(cxt, sdxi_ring_resv_dbval(&resv)); + + err =3D sdxi_completion_poll(comp); + WARN_ONCE(err, "got %d polling cst_blk", err); + + vchan_synchronize(to_virt_chan(dma_chan)); +} + +static irqreturn_t sdxi_dma_cxt_irq(int irq, void *data) +{ + struct sdxi_dma_chan *sdchan =3D data; + struct virt_dma_chan *vchan =3D &sdchan->vchan; + struct virt_dma_desc *vdesc; + bool completed =3D false; + + guard(spinlock_irqsave)(&vchan->lock); + + while ((vdesc =3D vchan_next_desc(vchan))) { + struct sdxi_dma_desc *sddesc =3D to_sdxi_dma_desc(vdesc); + + if (!sdxi_completion_signaled(sddesc->completion)) + break; + + list_del(&vdesc->node); + vchan_cookie_complete(&sddesc->vdesc); + completed =3D true; + } + + if (completed) + sdxi_ring_wake_up(sdchan->cxt->ring_state); + + return IRQ_HANDLED; +} + +static int sdxi_dma_alloc_chan_resources(struct dma_chan *dma_chan) +{ + struct sdxi_dev *sdxi =3D dev_get_drvdata(dma_chan->device->dev); + struct sdxi_dma_chan *sdchan =3D to_sdxi_dma_chan(dma_chan); + int vector, irq, err; + + sdchan->cxt =3D sdxi_cxt_new(sdxi); + if (!sdchan->cxt) + return -ENOMEM; + /* + * This irq and akey setup should perhaps all be pushed into + * the context allocation. + */ + err =3D vector =3D sdxi_alloc_vector(sdxi); + if (vector < 0) + goto exit_cxt; + + sdchan->vector =3D vector; + + err =3D irq =3D sdxi_vector_to_irq(sdxi, vector); + if (irq < 0) + goto free_vector; + + sdchan->irq =3D irq; + + /* + * Note this akey entry is used for both the completion + * interrupt and source and destination access for copies. + */ + sdchan->akey =3D sdxi_alloc_akey(sdchan->cxt); + if (!sdchan->akey) { + err =3D -ENOMEM; + goto free_vector; + } + + *sdchan->akey =3D (typeof(*sdchan->akey)) { + .intr_num =3D cpu_to_le16(FIELD_PREP(SDXI_AKEY_ENT_VL, 1) | + FIELD_PREP(SDXI_AKEY_ENT_IV, 1) | + FIELD_PREP(SDXI_AKEY_ENT_INTR_NUM, + vector)), + }; + + err =3D request_irq(sdchan->irq, sdxi_dma_cxt_irq, + IRQF_TRIGGER_NONE, "SDXI DMAengine", sdchan); + if (err) + goto free_akey; + + err =3D sdxi_start_cxt(sdchan->cxt); + if (err) + goto free_irq; + + return 0; +free_irq: + free_irq(sdchan->irq, sdchan); +free_akey: + sdxi_free_akey(sdchan->cxt, sdchan->akey); +free_vector: + sdxi_free_vector(sdxi, vector); +exit_cxt: + sdxi_cxt_exit(sdchan->cxt); + return err; +} + +static void sdxi_dma_free_chan_resources(struct dma_chan *dma_chan) +{ + struct sdxi_dma_chan *sdchan =3D to_sdxi_dma_chan(dma_chan); + + sdxi_stop_cxt(sdchan->cxt); + free_irq(sdchan->irq, sdchan); + sdxi_free_vector(sdchan->cxt->sdxi, sdchan->vector); + sdxi_free_akey(sdchan->cxt, sdchan->akey); + vchan_free_chan_resources(to_virt_chan(dma_chan)); + sdxi_cxt_exit(sdchan->cxt); +} + +int sdxi_dma_register(struct sdxi_dev *sdxi) +{ + struct device *dev =3D sdxi->dev; + struct sdxi_dma_dev *sddev; + struct dma_device *dma_dev; + int err; + + if (!dma_channels) + return 0; + /* + * Note that this code assumes the device supports the + * interrupt operation group (IntrGrp), which is optional. See + * SDXI 1.0 Table 6-1 SDXI Operation Groups. + * + * TODO: check sdxi->op_grp_cap for IntrGrp support and error + * out if it's missing. + */ + + sddev =3D devm_kzalloc(dev, struct_size(sddev, sdchan, dma_channels), + GFP_KERNEL); + if (!sddev) + return -ENOMEM; + + sddev->nr_channels =3D dma_channels; + + dma_dev =3D &sddev->dma_dev; + *dma_dev =3D (typeof(*dma_dev)) { + .dev =3D dev, + .src_addr_widths =3D DMA_SLAVE_BUSWIDTH_64_BYTES, + .dst_addr_widths =3D DMA_SLAVE_BUSWIDTH_64_BYTES, + .directions =3D BIT(DMA_MEM_TO_MEM), + .residue_granularity =3D DMA_RESIDUE_GRANULARITY_DESCRIPTOR, + + .device_alloc_chan_resources =3D sdxi_dma_alloc_chan_resources, + .device_free_chan_resources =3D sdxi_dma_free_chan_resources, + + .device_prep_dma_memcpy =3D sdxi_dma_prep_memcpy, + + .device_terminate_all =3D sdxi_dma_terminate_all, + .device_synchronize =3D sdxi_dma_synchronize, + .device_tx_status =3D sdxi_tx_status, + .device_issue_pending =3D sdxi_dma_issue_pending, + }; + + dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask); + INIT_LIST_HEAD(&dma_dev->channels); + + for (size_t i =3D 0; i < sddev->nr_channels; ++i) { + struct sdxi_dma_chan *sdchan =3D &sddev->sdchan[i]; + + sdchan->vchan.desc_free =3D sdxi_tx_desc_free; + vchan_init(&sdchan->vchan, &sddev->dma_dev); + } + + err =3D dmaenginem_async_device_register(dma_dev); + if (err) + return dev_warn_probe(dev, err, "failed to register dma device\n"); + + return 0; +} diff --git a/drivers/dma/sdxi/dma.h b/drivers/dma/sdxi/dma.h new file mode 100644 index 000000000000..d38870ea7d91 --- /dev/null +++ b/drivers/dma/sdxi/dma.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright Advanced Micro Devices, Inc. */ + +#ifndef DMA_SDXI_DMA_H +#define DMA_SDXI_DMA_H + +struct sdxi_dev; + +int sdxi_dma_register(struct sdxi_dev *sdxi); + +#endif /* DMA_SDXI_DMA_H */ --=20 2.54.0