[PATCH v8 24/31] gpu: nova-core: Hopper/Blackwell: add FSP Chain of Trust boot

John Hubbard posted 31 patches 1 week, 1 day ago
There is a newer version of this series
[PATCH v8 24/31] gpu: nova-core: Hopper/Blackwell: add FSP Chain of Trust boot
Posted by John Hubbard 1 week, 1 day ago
Add boot_fmc() which builds and sends the Chain of Trust message to FSP,
and FmcBootArgs which bundles the DMA-coherent boot parameters that FSP
reads at boot time. The FspFirmware struct fields become pub(crate) and
fmc_full changes from DmaObject to KVec<u8> for CPU-side signature
extraction.

Co-developed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 drivers/gpu/nova-core/firmware/fsp.rs |  12 +-
 drivers/gpu/nova-core/fsp.rs          | 177 +++++++++++++++++++++++++-
 drivers/gpu/nova-core/gpu.rs          |   1 -
 drivers/gpu/nova-core/mctp.rs         |   7 -
 4 files changed, 182 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/nova-core/firmware/fsp.rs b/drivers/gpu/nova-core/firmware/fsp.rs
index 5aedee8e6d41..e5059d59a4b7 100644
--- a/drivers/gpu/nova-core/firmware/fsp.rs
+++ b/drivers/gpu/nova-core/firmware/fsp.rs
@@ -14,24 +14,22 @@
     gpu::Chipset, //
 };
 
-#[expect(unused)]
+#[expect(dead_code)]
 pub(crate) struct FspFirmware {
     /// FMC firmware image data (only the "image" ELF section).
-    fmc_image: DmaObject,
+    pub(crate) fmc_image: DmaObject,
     /// Full FMC ELF data (for signature extraction).
     pub(crate) fmc_full: KVec<u8>,
 }
 
 impl FspFirmware {
-    #[expect(unused)]
+    #[expect(dead_code)]
     pub(crate) fn new(
         dev: &device::Device<device::Bound>,
         chipset: Chipset,
         ver: &str,
     ) -> Result<Self> {
         let fw = super::request_firmware(dev, chipset, "fmc", ver)?;
-        let mut fmc_full = KVec::with_capacity(fw.data().len(), GFP_KERNEL)?;
-        fmc_full.extend_from_slice(fw.data(), GFP_KERNEL)?;
 
         // FSP expects only the "image" section, not the entire ELF file.
         let fmc_image_data = elf::elf_section(fw.data(), "image").ok_or_else(|| {
@@ -39,6 +37,10 @@ pub(crate) fn new(
             EINVAL
         })?;
 
+        // Copy the full ELF into a kernel vector for CPU-side signature extraction.
+        let mut fmc_full = KVec::with_capacity(fw.data().len(), GFP_KERNEL)?;
+        fmc_full.extend_from_slice(fw.data(), GFP_KERNEL)?;
+
         Ok(Self {
             fmc_image: DmaObject::from_data(dev, fmc_image_data)?,
             fmc_full,
diff --git a/drivers/gpu/nova-core/fsp.rs b/drivers/gpu/nova-core/fsp.rs
index 18edf7a1a8e4..faa0b3ae88ba 100644
--- a/drivers/gpu/nova-core/fsp.rs
+++ b/drivers/gpu/nova-core/fsp.rs
@@ -8,8 +8,17 @@
 
 use kernel::{
     device,
+    dma::CoherentAllocation,
     io::poll::read_poll_timeout,
     prelude::*,
+    ptr::{
+        Alignable,
+        Alignment, //
+    },
+    sizes::{
+        SZ_1M,
+        SZ_2M, //
+    },
     time::Delta,
     transmute::{
         AsBytes,
@@ -38,7 +47,6 @@ pub(crate) const fn new(version: u16) -> Self {
     }
 
     /// Return the raw protocol version number for the wire format.
-    #[expect(dead_code)]
     pub(crate) const fn raw(self) -> u16 {
         self.0
     }
@@ -156,6 +164,35 @@ struct NvdmPayloadCommandResponse {
     error_code: u32,
 }
 
+/// NVDM (NVIDIA Device Management) COT (Chain of Trust) payload structure.
+/// This is the main message payload sent to FSP for Chain of Trust.
+#[repr(C, packed)]
+#[derive(Clone, Copy)]
+struct NvdmPayloadCot {
+    version: u16,
+    size: u16,
+    gsp_fmc_sysmem_offset: u64,
+    frts_sysmem_offset: u64,
+    frts_sysmem_size: u32,
+    frts_vidmem_offset: u64,
+    frts_vidmem_size: u32,
+    hash384: [u8; FSP_HASH_SIZE],
+    public_key: [u8; FSP_PKEY_SIZE],
+    signature: [u8; FSP_SIG_SIZE],
+    gsp_boot_args_sysmem_offset: u64,
+}
+
+/// Complete FSP message structure with MCTP and NVDM headers.
+#[repr(C, packed)]
+#[derive(Clone, Copy)]
+struct FspMessage {
+    mctp_header: u32,
+    nvdm_header: u32,
+    cot: NvdmPayloadCot,
+}
+
+// SAFETY: FspMessage is a packed C struct with only integral fields.
+unsafe impl AsBytes for FspMessage {}
 /// Complete FSP response structure with MCTP and NVDM headers.
 #[repr(C, packed)]
 #[derive(Clone, Copy)]
@@ -176,6 +213,84 @@ pub(crate) trait MessageToFsp: AsBytes {
     /// NVDM type identifying this message to FSP.
     const NVDM_TYPE: u32;
 }
+
+impl MessageToFsp for FspMessage {
+    const NVDM_TYPE: u32 = NvdmType::Cot as u32;
+}
+
+/// Bundled arguments for FMC boot via FSP Chain of Trust.
+pub(crate) struct FmcBootArgs<'a> {
+    chipset: crate::gpu::Chipset,
+    fmc_image_fw: &'a crate::dma::DmaObject,
+    fmc_boot_params: CoherentAllocation<GspFmcBootParams>,
+    resume: bool,
+    signatures: &'a FmcSignatures,
+}
+
+impl<'a> FmcBootArgs<'a> {
+    /// Build FMC boot arguments, allocating the DMA-coherent boot parameter
+    /// structure that FSP will read.
+    #[expect(dead_code)]
+    #[allow(clippy::too_many_arguments)]
+    pub(crate) fn new(
+        dev: &device::Device<device::Bound>,
+        chipset: crate::gpu::Chipset,
+        fmc_image_fw: &'a crate::dma::DmaObject,
+        wpr_meta_addr: u64,
+        wpr_meta_size: u32,
+        libos_addr: u64,
+        resume: bool,
+        signatures: &'a FmcSignatures,
+    ) -> Result<Self> {
+        // `GSP_DMA_TARGET_*` is not in the current Rust bindings yet.
+        const GSP_DMA_TARGET_COHERENT_SYSTEM: u32 = 1;
+        const GSP_DMA_TARGET_NONCOHERENT_SYSTEM: u32 = 2;
+
+        let fmc_boot_params = CoherentAllocation::<GspFmcBootParams>::alloc_coherent(
+            dev,
+            1,
+            GFP_KERNEL | __GFP_ZERO,
+        )?;
+
+        // Blackwell FSP expects wpr_carveout_offset and wpr_carveout_size to be zero;
+        // it obtains WPR info from other sources.
+        kernel::dma_write!(
+            fmc_boot_params,
+            [0]?.boot_gsp_rm_params,
+            GspAcrBootGspRmParams {
+                target: GSP_DMA_TARGET_COHERENT_SYSTEM,
+                gsp_rm_desc_size: wpr_meta_size,
+                gsp_rm_desc_offset: wpr_meta_addr,
+                b_is_gsp_rm_boot: 1,
+                ..Default::default()
+            }
+        );
+
+        kernel::dma_write!(
+            fmc_boot_params,
+            [0]?.gsp_rm_params,
+            GspRmParams {
+                target: GSP_DMA_TARGET_NONCOHERENT_SYSTEM,
+                boot_args_offset: libos_addr,
+            }
+        );
+
+        Ok(Self {
+            chipset,
+            fmc_image_fw,
+            fmc_boot_params,
+            resume,
+            signatures,
+        })
+    }
+
+    /// DMA address of the FMC boot parameters, needed after boot for lockdown
+    /// release polling.
+    #[expect(dead_code)]
+    pub(crate) fn boot_params_dma_handle(&self) -> u64 {
+        self.fmc_boot_params.dma_handle()
+    }
+}
 /// FSP interface for Hopper/Blackwell GPUs.
 pub(crate) struct Fsp;
 
@@ -277,8 +392,66 @@ pub(crate) fn extract_fmc_signatures(
         Ok(signatures)
     }
 
-    /// Send message to FSP and wait for response.
+    /// Boot GSP FMC via FSP Chain of Trust.
+    ///
+    /// Builds the COT message from the pre-configured [`FmcBootArgs`], sends it
+    /// to FSP, and waits for the response.
     #[expect(dead_code)]
+    pub(crate) fn boot_fmc(
+        dev: &device::Device<device::Bound>,
+        bar: &crate::driver::Bar0,
+        fsp_falcon: &crate::falcon::Falcon<crate::falcon::fsp::Fsp>,
+        args: &FmcBootArgs<'_>,
+    ) -> Result {
+        dev_dbg!(dev, "Starting FSP boot sequence for {}\n", args.chipset);
+
+        let fmc_addr = args.fmc_image_fw.dma_handle();
+        let fmc_boot_params_addr = args.fmc_boot_params.dma_handle();
+
+        // frts_offset is relative to FB end: FRTS_location = FB_END - frts_offset
+        let frts_offset = if !args.resume {
+            let frts_reserved_size = crate::fb::calc_non_wpr_heap_size(args.chipset)
+                .checked_add(u64::from(crate::fb::PMU_RESERVED_SIZE))
+                .ok_or(EINVAL)?;
+
+            frts_reserved_size
+                .align_up(Alignment::new::<SZ_2M>())
+                .ok_or(EINVAL)?
+        } else {
+            0
+        };
+        let frts_size: u32 = if !args.resume { SZ_1M as u32 } else { 0 };
+
+        let msg = KBox::new(
+            FspMessage {
+                mctp_header: MctpHeader::single_packet().raw(),
+                nvdm_header: NvdmHeader::new(NvdmType::Cot).raw(),
+
+                cot: NvdmPayloadCot {
+                    version: args.chipset.fsp_cot_version().ok_or(ENOTSUPP)?.raw(),
+                    size: u16::try_from(core::mem::size_of::<NvdmPayloadCot>())
+                        .map_err(|_| EINVAL)?,
+                    gsp_fmc_sysmem_offset: fmc_addr,
+                    frts_sysmem_offset: 0,
+                    frts_sysmem_size: 0,
+                    frts_vidmem_offset: frts_offset,
+                    frts_vidmem_size: frts_size,
+                    hash384: args.signatures.hash384,
+                    public_key: args.signatures.public_key,
+                    signature: args.signatures.signature,
+                    gsp_boot_args_sysmem_offset: fmc_boot_params_addr,
+                },
+            },
+            GFP_KERNEL,
+        )?;
+
+        Self::send_sync_fsp(dev, bar, fsp_falcon, &*msg)?;
+
+        dev_dbg!(dev, "FSP Chain of Trust completed successfully\n");
+        Ok(())
+    }
+
+    /// Send message to FSP and wait for response.
     fn send_sync_fsp<M>(
         dev: &device::Device<device::Bound>,
         bar: &crate::driver::Bar0,
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index eb7f8be893b0..424ded73de2a 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -138,7 +138,6 @@ pub(crate) const fn needs_fwsec_bootloader(self) -> bool {
     ///
     /// Hopper (GH100) uses version 1, Blackwell uses version 2.
     /// Returns `None` for architectures that do not use FSP.
-    #[expect(dead_code)]
     pub(crate) const fn fsp_cot_version(&self) -> Option<FspCotVersion> {
         match self.arch() {
             Architecture::Hopper => Some(FspCotVersion::new(1)),
diff --git a/drivers/gpu/nova-core/mctp.rs b/drivers/gpu/nova-core/mctp.rs
index 9e052d916e79..c23e8ec69636 100644
--- a/drivers/gpu/nova-core/mctp.rs
+++ b/drivers/gpu/nova-core/mctp.rs
@@ -6,8 +6,6 @@
 //! Device Management) messages between the kernel driver and GPU firmware
 //! processors such as FSP and GSP.
 
-#![expect(dead_code)]
-
 /// NVDM message type identifiers carried over MCTP.
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 #[repr(u8)]
@@ -101,11 +99,6 @@ pub(crate) fn nvdm_type(self) -> core::result::Result<NvdmType, u8> {
         NvdmType::try_from(self.raw_nvdm_type())
     }
 
-    /// Extract the NVDM type field as a raw value.
-    pub(crate) fn nvdm_type_raw(self) -> u32 {
-        u32::from(self.raw_nvdm_type())
-    }
-
     /// Set the NVDM type field from a typed value.
     pub(crate) fn set_nvdm_type(self, nvdm_type: NvdmType) -> Self {
         self.set_raw_nvdm_type(u8::from(nvdm_type))
-- 
2.53.0