From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-lf1-f50.google.com (mail-lf1-f50.google.com [209.85.167.50]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 6196D20E6EE for ; Thu, 23 Jan 2025 10:43:56 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.167.50 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1737629039; cv=none; b=gsFHDCTUUKcL3D2Xvyy7W0ELqBkyboux12IsArIeikEhDQ85GXME6oRoA07JLNaVlh4xxcDgf0rn0wu0I+9S+IbdHi+U5fdd0+Fg8DJehyiTr1Rxncg4luNFhVT8HhJISg5tI8MtWXpC08mBoAEq5imPnXBaEuZlf5uYSg0vELA= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1737629039; c=relaxed/simple; bh=A81Dn1Fs+f579XHqKrFftv0/wbKO0KgyoGrMVeZ9Qrg=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=ka3r3xc4QL1fFCF0TaMCZl70Ui0I7Iv5gKT8HjrrE/KvPGoJK7NggwSmpA3Ul7hD5LpM2PF/bsmPWeuWdxDZ50k2Rb+Ml7pnc0KxNGnA4/tQ86+zgcaqDPo033FgiXHvSC4TH5vCDmUFigq1zWZ2YV/okniHHuYjAxE9w1eylQU= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=ItY7NLoc; arc=none smtp.client-ip=209.85.167.50 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="ItY7NLoc" Received: by mail-lf1-f50.google.com with SMTP id 2adb3069b0e04-53e389d8dc7so882316e87.0 for ; Thu, 23 Jan 2025 02:43:56 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1737629034; x=1738233834; darn=lists.linux.dev; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=kSY83d3vWtDpbwnz/2tvzzgog+EHfgVcX3FixpXY9WY=; b=ItY7NLochGo1KnjO9Ft2r2zP+fwYZ8xQn8iJVJx8csmOEGVEVobTmvTFIzu0yWZWbr MKNv7re2jPaSXuRgLtHnA+8rEwarOxpZpjvm1WaNrXMJq+Wz1Wd4WgWFOgiYepv68+mO dMtdfLWR7X8CKVc/I9boQyJnX33jaIU2bG5Dhlj2Jpdz71Pa6wdXORcTQqPEIPUZN8Ss Jeo8aTMasxIiJJMDh8iFY5vLwlZX37Fdh/0qMV9JpIqyWJz/TBnMwpt4cRGUlXMAE0yD lYI0BXpBz9Cc3KuLZL8Uw5vqj4JwAl1LKbR/HKm34ygEyNqsOPxFvbgiATYMQdCWpOgs lluw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1737629034; x=1738233834; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=kSY83d3vWtDpbwnz/2tvzzgog+EHfgVcX3FixpXY9WY=; b=I5FCXfn7kIQ+hwa7rNhDk14yFPtJkQibj/EqFPKsG/tlwcl0qpwSNSocENa7qMWgFt r5PKPggmZFT8Gg452BUihzqX14f11oAahOBJnCxEBACHqOCuAeLbWYoJpi7AdXXocC16 ZRs0e0mK5HwQknfFa87A7/osjz25Lu9ubzfQQt/b1g4+jKuXDxV0xWg3ZwM+uf2ke8D3 5mGliIc9c31GEBmG/QHQ1HQ02D2DXvxlCuiGRYqE/N1JpQogxxLcWcUJ/mkpRxgrXcwG ZBI7ugTPBJ6IdyAybVxWwErANs313HA4byTgBb3yPARAIjLGm2jzQs9VHK5/ti6SlIwq Lyrg== X-Forwarded-Encrypted: i=1; AJvYcCXEtyFhpj2Nv+pZGuTZBuG//v245UJiqH3tn67RzS4roBEdEGFFLxKxbAlqz2kVFsMUaY8PsA==@lists.linux.dev X-Gm-Message-State: AOJu0YzJmX+PtRZKHnw6uZ9elTmNvKu+HDLgXJpBLTDdnVWTz0WE4RX0 s2nBYvAN/Uxk+Yji+0Lqou6HU2CsufChqt7NViKhydjpJSoaEQJW X-Gm-Gg: ASbGnct4dNqXCJnv30mlaR4HVU+oRiuBG0bgPO9IJ98mqNgf/3zhBtfLZ61B7TukyM5 +4I8gdK/Do0lA0QWOPWPv/CJMU/BUd6kNArHlltduyVPma3PUnSX/9auvB7Ur9CwzQXuhlUK4jC 1RosDNifpeLb/vfzNTdjmcLrSLU6ca2ZC+fxnotQ9yZ/bYFxQmGkU5NpGRclrgfWpA9iJBxC9gC WcE7vbN1Uqdn1z1oOqXnaojuMFEmNLemy4DHxDQWXO/jdz/cYZPnJTBXjUJR07L61eBgcg0JXbj Q1EN+Sf2B59NQyWcQj+W7IUCCUWYKJ5QHpQ7Vg9JoAnU27Ix6pI= X-Google-Smtp-Source: AGHT+IFTE145iWigVz7U1b1eLG+HVja8LX4jND2xki1OlFkXgaokSRg/0Pt4/T8Us3RAVW+GocTx/A== X-Received: by 2002:ac2:4155:0:b0:53e:395c:688e with SMTP id 2adb3069b0e04-5439c216b55mr6587969e87.10.1737629034066; Thu, 23 Jan 2025 02:43:54 -0800 (PST) Received: from abj-NUC9VXQNX.. (87-94-132-183.rev.dnainternet.fi. [87.94.132.183]) by smtp.gmail.com with ESMTPSA id 2adb3069b0e04-5439af0ea8esm2579873e87.80.2025.01.23.02.43.51 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 23 Jan 2025 02:43:52 -0800 (PST) From: Abdiel Janulgue To: rust-for-linux@vger.kernel.org, daniel.almeida@collabora.com, dakr@kernel.org, robin.murphy@arm.com, aliceryhl@google.com Cc: Miguel Ojeda , Alex Gaynor , Boqun Feng , Gary Guo , =?UTF-8?q?Bj=C3=B6rn=20Roy=20Baron?= , Benno Lossin , Andreas Hindborg , Trevor Gross , Valentin Obst , linux-kernel@vger.kernel.org (open list), Christoph Hellwig , Marek Szyprowski , airlied@redhat.com, iommu@lists.linux.dev (open list:DMA MAPPING HELPERS), Abdiel Janulgue Subject: [PATCH v11 2/3] rust: add dma coherent allocator abstraction. Date: Thu, 23 Jan 2025 12:42:58 +0200 Message-ID: <20250123104333.1340512-3-abdiel.janulgue@gmail.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20250123104333.1340512-1-abdiel.janulgue@gmail.com> References: <20250123104333.1340512-1-abdiel.janulgue@gmail.com> Precedence: bulk X-Mailing-List: iommu@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Add a simple dma coherent allocator rust abstraction. Based on Andreas Hindborg's dma abstractions from the rnvme driver, which was also based on earlier work by Wedson Almeida Filho. Signed-off-by: Abdiel Janulgue --- rust/bindings/bindings_helper.h | 1 + rust/kernel/dma.rs | 282 ++++++++++++++++++++++++++++++++ rust/kernel/lib.rs | 1 + 3 files changed, 284 insertions(+) create mode 100644 rust/kernel/dma.rs diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 5c4dfe22f41a..49bf713b9bb6 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs new file mode 100644 index 000000000000..83afc606d67a --- /dev/null +++ b/rust/kernel/dma.rs @@ -0,0 +1,282 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Direct memory access (DMA). +//! +//! C header: [`include/linux/dma-mapping.h`](srctree/include/linux/dma-mapping.h) + +use crate::{ + bindings, build_assert, + device::Device, + error::code::*, + error::Result, + transmute::{AsBytes, FromBytes}, + types::ARef, +}; + +/// Possible attributes associated with a DMA mapping. +/// +/// They can be combined with the operators `|`, `&`, and `!`. +/// +/// Values can be used from the [`attrs`] module. +#[derive(Clone, Copy, PartialEq)] +#[repr(transparent)] +pub struct Attrs(u32); + +impl Attrs { + /// Get the raw representation of this attribute. + pub(crate) fn as_raw(self) -> crate::ffi::c_ulong { + self.0 as _ + } + + /// Check whether `flags` is contained in `self`. + pub fn contains(self, flags: Attrs) -> bool { + (self & flags) == flags + } +} + +impl core::ops::BitOr for Attrs { + type Output = Self; + fn bitor(self, rhs: Self) -> Self::Output { + Self(self.0 | rhs.0) + } +} + +impl core::ops::BitAnd for Attrs { + type Output = Self; + fn bitand(self, rhs: Self) -> Self::Output { + Self(self.0 & rhs.0) + } +} + +impl core::ops::Not for Attrs { + type Output = Self; + fn not(self) -> Self::Output { + Self(!self.0) + } +} + +/// DMA mapping attrributes. +pub mod attrs { + use super::Attrs; + + /// Specifies that reads and writes to the mapping may be weakly ordered, that is that reads + /// and writes may pass each other. + pub const DMA_ATTR_WEAK_ORDERING: Attrs = Attrs(bindings::DMA_ATTR_WEAK_ORDERING); + + /// Specifies that writes to the mapping may be buffered to improve performance. + pub const DMA_ATTR_WRITE_COMBINE: Attrs = Attrs(bindings::DMA_ATTR_WRITE_COMBINE); + + /// Lets the platform to avoid creating a kernel virtual mapping for the allocated buffer. + pub const DMA_ATTR_NO_KERNEL_MAPPING: Attrs = Attrs(bindings::DMA_ATTR_NO_KERNEL_MAPPING); + + /// Allows platform code to skip synchronization of the CPU cache for the given buffer assuming + /// that it has been already transferred to 'device' domain. + pub const DMA_ATTR_SKIP_CPU_SYNC: Attrs = Attrs(bindings::DMA_ATTR_SKIP_CPU_SYNC); + + /// Forces contiguous allocation of the buffer in physical memory. + pub const DMA_ATTR_FORCE_CONTIGUOUS: Attrs = Attrs(bindings::DMA_ATTR_FORCE_CONTIGUOUS); + + /// This is a hint to the DMA-mapping subsystem that it's probably not worth the time to try + /// to allocate memory to in a way that gives better TLB efficiency. + pub const DMA_ATTR_ALLOC_SINGLE_PAGES: Attrs = Attrs(bindings::DMA_ATTR_ALLOC_SINGLE_PAGES); + + /// This tells the DMA-mapping subsystem to suppress allocation failure reports (similarly to + /// __GFP_NOWARN). + pub const DMA_ATTR_NO_WARN: Attrs = Attrs(bindings::DMA_ATTR_NO_WARN); + + /// Used to indicate that the buffer is fully accessible at an elevated privilege level (and + /// ideally inaccessible or at least read-only at lesser-privileged levels). + pub const DMA_ATTR_PRIVILEGED: Attrs = Attrs(bindings::DMA_ATTR_PRIVILEGED); +} + +/// An abstraction of the `dma_alloc_coherent` API. +/// +/// This is an abstraction around the `dma_alloc_coherent` API which is used to allocate and map +/// large consistent DMA regions. +/// +/// A [`CoherentAllocation`] instance contains a pointer to the allocated region (in the +/// processor's virtual address space) and the device address which can be given to the device +/// as the DMA address base of the region. The region is released once [`CoherentAllocation`] +/// is dropped. +/// +/// # Invariants +/// +/// For the lifetime of an instance of [`CoherentAllocation`], the cpu address is a valid pointer +/// to an allocated region of consistent memory and we hold a reference to the device. +pub struct CoherentAllocation { + dev: ARef, + dma_handle: bindings::dma_addr_t, + count: usize, + cpu_addr: *mut T, + dma_attrs: Attrs, +} + +impl CoherentAllocation { + /// Allocates a region of `size_of:: * count` of consistent memory. + /// + /// # Examples + /// + /// ``` + /// use kernel::device::Device; + /// use kernel::dma::{attrs::*, CoherentAllocation}; + /// + /// # fn test(dev: &Device) -> Result { + /// let c: CoherentAllocation = CoherentAllocation::alloc_attrs(dev.into(), 4, GFP_KERNEL, + /// DMA_ATTR_NO_WARN)?; + /// # Ok::<(), Error>(()) } + /// ``` + pub fn alloc_attrs( + dev: ARef, + count: usize, + gfp_flags: kernel::alloc::Flags, + dma_attrs: Attrs, + ) -> Result> { + build_assert!( + core::mem::size_of::() > 0, + "It doesn't make sense for the allocated type to be a ZST" + ); + + let size = count + .checked_mul(core::mem::size_of::()) + .ok_or(EOVERFLOW)?; + let mut dma_handle = 0; + // SAFETY: device pointer is guaranteed as valid by invariant on `Device`. + // We ensure that we catch the failure on this function and throw an ENOMEM + let ret = unsafe { + bindings::dma_alloc_attrs( + dev.as_raw(), + size, + &mut dma_handle, + gfp_flags.as_raw(), + dma_attrs.as_raw(), + ) + }; + if ret.is_null() { + return Err(ENOMEM); + } + // INVARIANT: We just successfully allocated a coherent region which is accessible for + // `count` elements, hence the cpu address is valid. We also hold a refcounted reference + // to the device. + Ok(Self { + dev, + dma_handle, + count, + cpu_addr: ret as *mut T, + dma_attrs, + }) + } + + /// Performs the same functionality as `alloc_attrs`, except the `dma_attrs` is 0 by default. + pub fn alloc_coherent( + dev: ARef, + count: usize, + gfp_flags: kernel::alloc::Flags, + ) -> Result> { + CoherentAllocation::alloc_attrs(dev, count, gfp_flags, Attrs(0)) + } + + /// Returns the device, base address, dma handle, attributes and the size of the + /// allocated region. + /// + /// The caller takes ownership of the returned resources, i.e., will have the responsibility + /// in calling `bindings::dma_free_attrs`. The allocated region is valid as long as + /// the returned device exists. + pub fn into_parts( + self, + ) -> ( + ARef, + *mut T, + bindings::dma_addr_t, + crate::ffi::c_ulong, + usize, + ) { + let size = self.count * core::mem::size_of::(); + let ret = ( + // SAFETY: `&self.dev` is valid for reads. + unsafe { core::ptr::read(&self.dev) }, + self.cpu_addr, + self.dma_handle, + self.dma_attrs.as_raw(), + size, + ); + core::mem::forget(self); + ret + } + + /// Returns the base address to the allocated region in the CPU's virtual address space. + pub fn start_ptr(&self) -> *const T { + self.cpu_addr + } + + /// Returns the base address to the allocated region in the CPU's virtual address space as + /// a mutable pointer. + pub fn start_ptr_mut(&mut self) -> *mut T { + self.cpu_addr + } + + /// Returns a DMA handle which may given to the device as the DMA address base of + /// the region. + pub fn dma_handle(&self) -> bindings::dma_addr_t { + self.dma_handle + } + + /// Reads data from the region starting from `offset` as a slice. + /// `offset` and `count` are in units of `T`, not the number of bytes. + /// + /// Due to the safety requirements of slice, the data returned should be regarded by the + /// caller as a snapshot of the region when this function is called, as the region could + /// be modified by the device at anytime. For ringbuffer type of r/w access or use-cases + /// where the pointer to the live data is needed, `start_ptr()` or `start_ptr_mut()` + /// could be used instead. + /// + /// # Safety + /// + /// Callers must ensure that no hardware operations that involve the buffer are currently + /// taking place while the returned slice is live. + pub unsafe fn as_slice(&self, offset: usize, count: usize) -> Result<&[T]> { + if offset + count >= self.count { + return Err(EINVAL); + } + // SAFETY: + // - The pointer is valid due to type invariant on `CoherentAllocation`, + // we've just checked that the range and index is within bounds. The immutability of the + // of data is also guaranteed by the safety requirements of the function. + // - `offset` can't overflow since it is smaller than `self.count` and we've checked + // that `self.count` won't overflow early in the constructor. + Ok(unsafe { core::slice::from_raw_parts(self.cpu_addr.add(offset), count) }) + } + + /// Writes data to the region starting from `offset`. `offset` is in units of `T`, not the + /// number of bytes. + pub fn write(&self, src: &[T], offset: usize) -> Result { + if offset + src.len() >= self.count { + return Err(EINVAL); + } + // SAFETY: + // - The pointer is valid due to type invariant on `CoherentAllocation` + // and we've just checked that the range and index is within bounds. + // - `offset` can't overflow since it is smaller than `self.count` and we've checked + // that `self.count` won't overflow early in the constructor. + unsafe { + core::ptr::copy_nonoverlapping(src.as_ptr(), self.cpu_addr.add(offset), src.len()) + }; + Ok(()) + } +} + +impl Drop for CoherentAllocation { + fn drop(&mut self) { + let size = self.count * core::mem::size_of::(); + // SAFETY: the device, cpu address, and the dma handle is valid due to the + // type invariants on `CoherentAllocation`. + unsafe { + bindings::dma_free_attrs( + self.dev.as_raw(), + size, + self.cpu_addr as _, + self.dma_handle, + self.dma_attrs.as_raw(), + ) + } + } +} diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 545d1170ee63..36ac88fd91e7 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -37,6 +37,7 @@ pub mod build_assert; pub mod cred; pub mod device; +pub mod dma; pub mod error; #[cfg(CONFIG_RUST_FW_LOADER_ABSTRACTIONS)] pub mod firmware; -- 2.43.0