The GSP requires several areas of memory to operate. Each of these have
their own simple embedded page tables. Set these up and map them for DMA
to/from GSP using CoherentAllocation's. Return the DMA handle describing
where each of these regions are for future use when booting GSP.
Signed-off-by: Alistair Popple <apopple@nvidia.com>
---
Changes for v2:
- Renamed GspMemOjbects to Gsp as that is what they are
- Rebased on Alex's latest series
---
drivers/gpu/nova-core/gpu.rs | 2 +-
drivers/gpu/nova-core/gsp.rs | 80 +++++++++++++++++--
drivers/gpu/nova-core/gsp/fw.rs | 39 +++++++++
.../gpu/nova-core/gsp/fw/r570_144/bindings.rs | 19 +++++
4 files changed, 131 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 5da9ad726483..c939b3868271 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -221,7 +221,7 @@ pub(crate) fn new<'a>(
sec2_falcon: Falcon::new(pdev.as_ref(), spec.chipset, bar, true)?,
- gsp <- Gsp::new(),
+ gsp <- Gsp::new(pdev)?,
_: { gsp.boot(pdev, bar, spec.chipset, gsp_falcon, sec2_falcon)? },
diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs
index 503ce8ee0420..0185f66971ff 100644
--- a/drivers/gpu/nova-core/gsp.rs
+++ b/drivers/gpu/nova-core/gsp.rs
@@ -1,27 +1,91 @@
// SPDX-License-Identifier: GPL-2.0
mod boot;
-
-use kernel::prelude::*;
-
mod fw;
pub(crate) use fw::{GspFwWprMeta, LibosParams};
+use kernel::device;
+use kernel::dma::CoherentAllocation;
+use kernel::dma_write;
+use kernel::pci;
+use kernel::prelude::*;
use kernel::ptr::Alignment;
+use kernel::transmute::{AsBytes, FromBytes};
+
+use fw::LibosMemoryRegionInitArgument;
pub(crate) const GSP_PAGE_SHIFT: usize = 12;
pub(crate) const GSP_PAGE_SIZE: usize = 1 << GSP_PAGE_SHIFT;
pub(crate) const GSP_HEAP_ALIGNMENT: Alignment = Alignment::new::<{ 1 << 20 }>();
/// GSP runtime data.
-///
-/// This is an empty pinned placeholder for now.
#[pin_data]
-pub(crate) struct Gsp {}
+pub(crate) struct Gsp {
+ libos: CoherentAllocation<LibosMemoryRegionInitArgument>,
+ pub loginit: CoherentAllocation<u8>,
+ pub logintr: CoherentAllocation<u8>,
+ pub logrm: CoherentAllocation<u8>,
+}
+
+/// Creates a self-mapping page table for `obj` at its beginning.
+fn create_pte_array(obj: &mut CoherentAllocation<u8>) {
+ let num_pages = obj.size().div_ceil(GSP_PAGE_SIZE);
+ let handle = obj.dma_handle();
+
+ // SAFETY:
+ // - By the invariants of the CoherentAllocation ptr is non-NULL.
+ // - CoherentAllocation CPU addresses are always aligned to a
+ // page-boundary, satisfying the alignment requirements for
+ // from_raw_parts_mut()
+ // - The allocation size is at least as long as 8 * num_pages as
+ // GSP_PAGE_SIZE is larger than 8 bytes.
+ let ptes = unsafe {
+ let ptr = obj.start_ptr_mut().cast::<u64>().add(1);
+ core::slice::from_raw_parts_mut(ptr, num_pages)
+ };
+
+ for (i, pte) in ptes.iter_mut().enumerate() {
+ *pte = handle + ((i as u64) << GSP_PAGE_SHIFT);
+ }
+}
+
+/// Creates a new `CoherentAllocation<A>` with `name` of `size` elements, and
+/// register it into the `libos` object at argument position `libos_arg_nr`.
+fn create_coherent_dma_object<A: AsBytes + FromBytes>(
+ dev: &device::Device<device::Bound>,
+ name: &'static str,
+ size: usize,
+ libos: &mut CoherentAllocation<LibosMemoryRegionInitArgument>,
+ libos_arg_nr: usize,
+) -> Result<CoherentAllocation<A>> {
+ let obj = CoherentAllocation::<A>::alloc_coherent(dev, size, GFP_KERNEL | __GFP_ZERO)?;
+
+ dma_write!(libos[libos_arg_nr] = LibosMemoryRegionInitArgument::new(name, &obj))?;
+
+ Ok(obj)
+}
impl Gsp {
- pub(crate) fn new() -> impl PinInit<Self> {
- pin_init!(Self {})
+ pub(crate) fn new(pdev: &pci::Device<device::Bound>) -> Result<impl PinInit<Self, Error>> {
+ let dev = pdev.as_ref();
+ let mut libos = CoherentAllocation::<LibosMemoryRegionInitArgument>::alloc_coherent(
+ dev,
+ GSP_PAGE_SIZE / size_of::<LibosMemoryRegionInitArgument>(),
+ GFP_KERNEL | __GFP_ZERO,
+ )?;
+ let mut loginit = create_coherent_dma_object::<u8>(dev, "LOGINIT", 0x10000, &mut libos, 0)?;
+ create_pte_array(&mut loginit);
+ let mut logintr = create_coherent_dma_object::<u8>(dev, "LOGINTR", 0x10000, &mut libos, 1)?;
+ create_pte_array(&mut logintr);
+ let mut logrm = create_coherent_dma_object::<u8>(dev, "LOGRM", 0x10000, &mut libos, 2)?;
+ create_pte_array(&mut logrm);
+
+ Ok(try_pin_init!(Self {
+ libos,
+ loginit,
+ logintr,
+ logrm,
+ }))
}
}
diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs
index 181baa401770..dd1e7fc85d85 100644
--- a/drivers/gpu/nova-core/gsp/fw.rs
+++ b/drivers/gpu/nova-core/gsp/fw.rs
@@ -7,8 +7,10 @@
use core::ops::Range;
+use kernel::dma::CoherentAllocation;
use kernel::ptr::Alignable;
use kernel::sizes::SZ_1M;
+use kernel::transmute::{AsBytes, FromBytes};
use crate::gpu::Chipset;
use crate::gsp;
@@ -99,3 +101,40 @@ pub(crate) fn wpr_heap_size(&self, chipset: Chipset, fb_size: u64) -> u64 {
/// addresses of the GSP bootloader and firmware.
#[repr(transparent)]
pub(crate) struct GspFwWprMeta(bindings::GspFwWprMeta);
+
+#[repr(transparent)]
+pub(crate) struct LibosMemoryRegionInitArgument(bindings::LibosMemoryRegionInitArgument);
+
+// SAFETY: Padding is explicit and will not contain uninitialized data.
+unsafe impl AsBytes for LibosMemoryRegionInitArgument {}
+
+// SAFETY: This struct only contains integer types for which all bit patterns
+// are valid.
+unsafe impl FromBytes for LibosMemoryRegionInitArgument {}
+
+impl LibosMemoryRegionInitArgument {
+ pub(crate) fn new<A: AsBytes + FromBytes>(
+ name: &'static str,
+ obj: &CoherentAllocation<A>,
+ ) -> Self {
+ /// Generates the `ID8` identifier required for some GSP objects.
+ fn id8(name: &str) -> u64 {
+ let mut bytes = [0u8; core::mem::size_of::<u64>()];
+
+ for (c, b) in name.bytes().rev().zip(&mut bytes) {
+ *b = c;
+ }
+
+ u64::from_ne_bytes(bytes)
+ }
+
+ Self(bindings::LibosMemoryRegionInitArgument {
+ id8: id8(name),
+ pa: obj.dma_handle(),
+ size: obj.size() as u64,
+ kind: bindings::LibosMemoryRegionKind_LIBOS_MEMORY_REGION_CONTIGUOUS as u8,
+ loc: bindings::LibosMemoryRegionLoc_LIBOS_MEMORY_REGION_LOC_SYSMEM as u8,
+ ..Default::default()
+ })
+ }
+}
diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs
index 0407000cca22..6a14cc324391 100644
--- a/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs
+++ b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs
@@ -124,3 +124,22 @@ fn default() -> Self {
}
}
}
+pub type LibosAddress = u64_;
+pub const LibosMemoryRegionKind_LIBOS_MEMORY_REGION_NONE: LibosMemoryRegionKind = 0;
+pub const LibosMemoryRegionKind_LIBOS_MEMORY_REGION_CONTIGUOUS: LibosMemoryRegionKind = 1;
+pub const LibosMemoryRegionKind_LIBOS_MEMORY_REGION_RADIX3: LibosMemoryRegionKind = 2;
+pub type LibosMemoryRegionKind = ffi::c_uint;
+pub const LibosMemoryRegionLoc_LIBOS_MEMORY_REGION_LOC_NONE: LibosMemoryRegionLoc = 0;
+pub const LibosMemoryRegionLoc_LIBOS_MEMORY_REGION_LOC_SYSMEM: LibosMemoryRegionLoc = 1;
+pub const LibosMemoryRegionLoc_LIBOS_MEMORY_REGION_LOC_FB: LibosMemoryRegionLoc = 2;
+pub type LibosMemoryRegionLoc = ffi::c_uint;
+#[repr(C)]
+#[derive(Debug, Default, Copy, Clone)]
+pub struct LibosMemoryRegionInitArgument {
+ pub id8: LibosAddress,
+ pub pa: LibosAddress,
+ pub size: LibosAddress,
+ pub kind: u8_,
+ pub loc: u8_,
+ pub __bindgen_padding_0: [u8; 6usize],
+}
--
2.50.1Hi Alistair,
On Mon Sep 22, 2025 at 8:30 PM JST, Alistair Popple wrote:
> The GSP requires several areas of memory to operate. Each of these have
> their own simple embedded page tables. Set these up and map them for DMA
> to/from GSP using CoherentAllocation's. Return the DMA handle describing
> where each of these regions are for future use when booting GSP.
>
> Signed-off-by: Alistair Popple <apopple@nvidia.com>
>
> ---
>
> Changes for v2:
>
> - Renamed GspMemOjbects to Gsp as that is what they are
> - Rebased on Alex's latest series
> ---
> drivers/gpu/nova-core/gpu.rs | 2 +-
> drivers/gpu/nova-core/gsp.rs | 80 +++++++++++++++++--
> drivers/gpu/nova-core/gsp/fw.rs | 39 +++++++++
> .../gpu/nova-core/gsp/fw/r570_144/bindings.rs | 19 +++++
> 4 files changed, 131 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
> index 5da9ad726483..c939b3868271 100644
> --- a/drivers/gpu/nova-core/gpu.rs
> +++ b/drivers/gpu/nova-core/gpu.rs
> @@ -221,7 +221,7 @@ pub(crate) fn new<'a>(
>
> sec2_falcon: Falcon::new(pdev.as_ref(), spec.chipset, bar, true)?,
>
> - gsp <- Gsp::new(),
> + gsp <- Gsp::new(pdev)?,
>
> _: { gsp.boot(pdev, bar, spec.chipset, gsp_falcon, sec2_falcon)? },
>
> diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs
> index 503ce8ee0420..0185f66971ff 100644
> --- a/drivers/gpu/nova-core/gsp.rs
> +++ b/drivers/gpu/nova-core/gsp.rs
> @@ -1,27 +1,91 @@
> // SPDX-License-Identifier: GPL-2.0
>
> mod boot;
> -
> -use kernel::prelude::*;
> -
Oops, not sure why I put that here but thanks for fixing this.
> mod fw;
>
> pub(crate) use fw::{GspFwWprMeta, LibosParams};
>
> +use kernel::device;
> +use kernel::dma::CoherentAllocation;
> +use kernel::dma_write;
> +use kernel::pci;
> +use kernel::prelude::*;
> use kernel::ptr::Alignment;
> +use kernel::transmute::{AsBytes, FromBytes};
> +
> +use fw::LibosMemoryRegionInitArgument;
>
> pub(crate) const GSP_PAGE_SHIFT: usize = 12;
> pub(crate) const GSP_PAGE_SIZE: usize = 1 << GSP_PAGE_SHIFT;
> pub(crate) const GSP_HEAP_ALIGNMENT: Alignment = Alignment::new::<{ 1 << 20 }>();
>
> /// GSP runtime data.
> -///
> -/// This is an empty pinned placeholder for now.
> #[pin_data]
> -pub(crate) struct Gsp {}
> +pub(crate) struct Gsp {
> + libos: CoherentAllocation<LibosMemoryRegionInitArgument>,
> + pub loginit: CoherentAllocation<u8>,
> + pub logintr: CoherentAllocation<u8>,
> + pub logrm: CoherentAllocation<u8>,
These don't need to be public for now.
> +}
> +
> +/// Creates a self-mapping page table for `obj` at its beginning.
> +fn create_pte_array(obj: &mut CoherentAllocation<u8>) {
> + let num_pages = obj.size().div_ceil(GSP_PAGE_SIZE);
> + let handle = obj.dma_handle();
> +
> + // SAFETY:
> + // - By the invariants of the CoherentAllocation ptr is non-NULL.
> + // - CoherentAllocation CPU addresses are always aligned to a
> + // page-boundary, satisfying the alignment requirements for
> + // from_raw_parts_mut()
> + // - The allocation size is at least as long as 8 * num_pages as
> + // GSP_PAGE_SIZE is larger than 8 bytes.
> + let ptes = unsafe {
> + let ptr = obj.start_ptr_mut().cast::<u64>().add(1);
> + core::slice::from_raw_parts_mut(ptr, num_pages)
> + };
I think we also need to provide the same guarantees as
`CoherentAllocation::as_slice_mut`:
* Callers must ensure that the device does not read/write to/from memory
while the returned slice is live.
* Callers must ensure that this call does not race with a read or write
to the same region while the returned slice is live.
Unfortunately I don't think these are covered by this function alone -
it could perfectly be called on an allocation that is currently in use
by the hardware. So technically `create_pte_arrays` in its present form
should be unsafe, but that also would be overkill here since it is a
local function and we control the conditions into which it is called.
This PTE business, where we are taking any coherent allocation and
reinterpreting its bytes to create a page table, does not look very
clean to me anyway, so maybe we can solve this with a redesign. I'd
rather have that part of the object explicitly laid out, as it is for
`GspMem` later in this series (albeit with `u8` instead of `u64`):
struct GspMem {
ptes: [u8; GSP_PAGE_SIZE],
...
What would work best here IMHO would be to have a dedicated type for the
array of PTEs, which is placed at the beginning of each object
requesting one. Then we could have an init generic method for it that
takes a reference to any object and `dma_write!`s its entries, avoiding
the slice and having a guarantee that we have exclusive access to the
object since we just created it one line above. I need to think a bit
more about this but this should be a solid basis.
As it happens, loginit, logintr and logrm all have the same size, so we
should be able to declare a new type for these 3.
> +
> + for (i, pte) in ptes.iter_mut().enumerate() {
> + *pte = handle + ((i as u64) << GSP_PAGE_SHIFT);
> + }
> +}
> +
> +/// Creates a new `CoherentAllocation<A>` with `name` of `size` elements, and
> +/// register it into the `libos` object at argument position `libos_arg_nr`.
> +fn create_coherent_dma_object<A: AsBytes + FromBytes>(
> + dev: &device::Device<device::Bound>,
> + name: &'static str,
> + size: usize,
> + libos: &mut CoherentAllocation<LibosMemoryRegionInitArgument>,
> + libos_arg_nr: usize,
> +) -> Result<CoherentAllocation<A>> {
> + let obj = CoherentAllocation::<A>::alloc_coherent(dev, size, GFP_KERNEL | __GFP_ZERO)?;
> +
> + dma_write!(libos[libos_arg_nr] = LibosMemoryRegionInitArgument::new(name, &obj))?;
Once we have a dedicated type for DMA objects with PTEs, I suggest to
move this `dma_write` outside of this function. It doesn't bring any
value to have it here, and that way we can remove
`create_coherent_dma_object` altogether. Let me clarify below.
> +
> + Ok(obj)
> +}
>
> impl Gsp {
> - pub(crate) fn new() -> impl PinInit<Self> {
> - pin_init!(Self {})
> + pub(crate) fn new(pdev: &pci::Device<device::Bound>) -> Result<impl PinInit<Self, Error>> {
> + let dev = pdev.as_ref();
> + let mut libos = CoherentAllocation::<LibosMemoryRegionInitArgument>::alloc_coherent(
> + dev,
> + GSP_PAGE_SIZE / size_of::<LibosMemoryRegionInitArgument>(),
> + GFP_KERNEL | __GFP_ZERO,
> + )?;
> + let mut loginit = create_coherent_dma_object::<u8>(dev, "LOGINIT", 0x10000, &mut libos, 0)?;
> + create_pte_array(&mut loginit);
> + let mut logintr = create_coherent_dma_object::<u8>(dev, "LOGINTR", 0x10000, &mut libos, 1)?;
> + create_pte_array(&mut logintr);
> + let mut logrm = create_coherent_dma_object::<u8>(dev, "LOGRM", 0x10000, &mut libos, 2)?;
> + create_pte_array(&mut logrm);
So with the proper PTE-prefixed type, this code would become:
let loginit = PteDmaObject::new(dev)?;
let logintr = PteDmaObject::new(dev)?;
let logrm = PteDmaObject::new(dev)?;
dma_write!(libos[0] = LibosMemoryRegionInitArgument::new("LOGINIT", &loginit))?;
dma_write!(libos[1] = LibosMemoryRegionInitArgument::new("LOGINTR", &logintr))?;
dma_write!(libos[2] = LibosMemoryRegionInitArgument::new("LOGRM", &logrm))?;
Note how loginit and friends now don't need to be mutable anymore.
It's getting late here so let me continue the review tomorrow. :)
© 2016 - 2025 Red Hat, Inc.