[PATCH v10 25/28] gpu: nova-core: Hopper/Blackwell: add FSP Chain of Trust boot

John Hubbard posted 28 patches 1 day, 12 hours ago
[PATCH v10 25/28] gpu: nova-core: Hopper/Blackwell: add FSP Chain of Trust boot
Posted by John Hubbard 1 day, 12 hours ago
Add boot_fmc() which builds and sends the Chain of Trust message to FSP.
FmcBootArgs bundles the DMA-coherent boot parameters that FSP reads at
boot time.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 drivers/gpu/nova-core/fb.rs           |   1 -
 drivers/gpu/nova-core/firmware/fsp.rs |   1 -
 drivers/gpu/nova-core/fsp.rs          | 257 +++++++++++++++++++++++++-
 drivers/gpu/nova-core/gpu.rs          |   1 -
 drivers/gpu/nova-core/gsp/boot.rs     |  26 ++-
 drivers/gpu/nova-core/mctp.rs         |   2 -
 6 files changed, 275 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/nova-core/fb.rs b/drivers/gpu/nova-core/fb.rs
index 756ff283a908..2b3a2bb2f1db 100644
--- a/drivers/gpu/nova-core/fb.rs
+++ b/drivers/gpu/nova-core/fb.rs
@@ -294,7 +294,6 @@ pub(crate) fn new(chipset: Chipset, bar: &Bar0, gsp_fw: &GspFirmware) -> Result<
 }
 
 /// Returns the PMU reserved memory size for `chipset`.
-#[expect(dead_code)]
 pub(crate) fn calc_pmu_reserved_size(chipset: Chipset) -> u32 {
     match chipset.arch() {
         Architecture::BlackwellGB10x | Architecture::BlackwellGB20x => PMU_RESERVED_SIZE,
diff --git a/drivers/gpu/nova-core/firmware/fsp.rs b/drivers/gpu/nova-core/firmware/fsp.rs
index 3968bacb7e61..301345aa491c 100644
--- a/drivers/gpu/nova-core/firmware/fsp.rs
+++ b/drivers/gpu/nova-core/firmware/fsp.rs
@@ -14,7 +14,6 @@
     gpu::Chipset, //
 };
 
-#[expect(dead_code)]
 pub(crate) struct FspFirmware {
     /// FMC firmware image data (only the "image" ELF section).
     pub(crate) fmc_image: Coherent<[u8]>,
diff --git a/drivers/gpu/nova-core/fsp.rs b/drivers/gpu/nova-core/fsp.rs
index bc98a5c3cfaa..75e06b2d5f06 100644
--- a/drivers/gpu/nova-core/fsp.rs
+++ b/drivers/gpu/nova-core/fsp.rs
@@ -8,9 +8,25 @@
 
 use kernel::{
     device,
+    dma::{
+        Coherent,
+        CoherentBox, //
+    },
     io::poll::read_poll_timeout,
     prelude::*,
-    time::Delta, //
+    ptr::{
+        Alignable,
+        Alignment, //
+    },
+    sizes::{
+        SizeConstants,
+        SZ_2M, //
+    },
+    time::Delta,
+    transmute::{
+        AsBytes,
+        FromBytes, //
+    },
 };
 
 use crate::regs;
@@ -34,7 +50,6 @@ 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
     }
@@ -46,6 +61,89 @@ pub(crate) const fn raw(self) -> u16 {
 /// FSP secure boot completion timeout in milliseconds.
 const FSP_SECURE_BOOT_TIMEOUT_MS: i64 = 5000;
 
+/// GSP FMC initialization parameters.
+#[repr(C)]
+#[derive(Debug, Clone, Copy, Default)]
+struct GspFmcInitParams {
+    /// CC initialization "registry keys".
+    regkeys: u32,
+}
+
+// SAFETY: GspFmcInitParams is a simple C struct with only primitive types.
+unsafe impl AsBytes for GspFmcInitParams {}
+// SAFETY: All bit patterns are valid for the primitive fields.
+unsafe impl FromBytes for GspFmcInitParams {}
+
+/// GSP ACR (Authenticated Code RAM) boot parameters.
+#[repr(C)]
+#[derive(Debug, Clone, Copy, Default)]
+struct GspAcrBootGspRmParams {
+    /// Physical memory aperture through which gspRmDescPa is accessed.
+    target: u32,
+    /// Size in bytes of the GSP-RM descriptor structure.
+    gsp_rm_desc_size: u32,
+    /// Physical offset in the target aperture of the GSP-RM descriptor structure.
+    gsp_rm_desc_offset: u64,
+    /// Physical offset in FB to set the start of the WPR containing GSP-RM.
+    wpr_carveout_offset: u64,
+    /// Size in bytes of the WPR containing GSP-RM.
+    wpr_carveout_size: u32,
+    /// Whether to boot GSP-RM or GSP-Proxy through ACR.
+    b_is_gsp_rm_boot: u32,
+}
+
+// SAFETY: GspAcrBootGspRmParams is a simple C struct with only primitive types.
+unsafe impl AsBytes for GspAcrBootGspRmParams {}
+// SAFETY: All bit patterns are valid for the primitive fields.
+unsafe impl FromBytes for GspAcrBootGspRmParams {}
+
+/// GSP RM boot parameters.
+#[repr(C)]
+#[derive(Debug, Clone, Copy, Default)]
+struct GspRmParams {
+    /// Physical memory aperture through which bootArgsOffset is accessed.
+    target: u32,
+    /// Physical offset in the memory aperture that will be passed to GSP-RM.
+    boot_args_offset: u64,
+}
+
+// SAFETY: GspRmParams is a simple C struct with only primitive types.
+unsafe impl AsBytes for GspRmParams {}
+// SAFETY: All bit patterns are valid for the primitive fields.
+unsafe impl FromBytes for GspRmParams {}
+
+/// GSP SPDM (Security Protocol and Data Model) parameters.
+#[repr(C)]
+#[derive(Debug, Clone, Copy, Default)]
+struct GspSpdmParams {
+    /// Physical memory aperture through which all addresses are accessed.
+    target: u32,
+    /// Physical offset in the memory aperture where SPDM payload buffer is stored.
+    payload_buffer_offset: u64,
+    /// Size of the above payload buffer.
+    payload_buffer_size: u32,
+}
+
+// SAFETY: GspSpdmParams is a simple C struct with only primitive types.
+unsafe impl AsBytes for GspSpdmParams {}
+// SAFETY: All bit patterns are valid for the primitive fields.
+unsafe impl FromBytes for GspSpdmParams {}
+
+/// Complete GSP FMC boot parameters passed to FSP.
+#[repr(C)]
+#[derive(Debug, Clone, Copy, Default)]
+pub(crate) struct GspFmcBootParams {
+    init_params: GspFmcInitParams,
+    boot_gsp_rm_params: GspAcrBootGspRmParams,
+    gsp_rm_params: GspRmParams,
+    gsp_spdm_params: GspSpdmParams,
+}
+
+// SAFETY: GspFmcBootParams is composed of C structs with only primitive types.
+unsafe impl AsBytes for GspFmcBootParams {}
+// SAFETY: All bit patterns are valid for the primitive fields.
+unsafe impl FromBytes for GspFmcBootParams {}
+
 /// Size constraints for FSP security signatures (Hopper/Blackwell).
 const FSP_HASH_SIZE: usize = 48; // SHA-384 hash
 const FSP_PKEY_SIZE: usize = 384; // RSA-3072 public key
@@ -69,6 +167,35 @@ 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)]
@@ -89,6 +216,73 @@ 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 Coherent<[u8]>,
+    fmc_boot_params: Coherent<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.
+    #[allow(clippy::too_many_arguments)]
+    pub(crate) fn new(
+        dev: &device::Device<device::Bound>,
+        chipset: crate::gpu::Chipset,
+        fmc_image_fw: &'a Coherent<[u8]>,
+        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 mut fmc_boot_params = CoherentBox::<GspFmcBootParams>::zeroed(dev, GFP_KERNEL)?;
+
+        // Blackwell FSP expects wpr_carveout_offset and wpr_carveout_size to be zero;
+        // it obtains WPR info from other sources.
+        fmc_boot_params.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()
+        };
+
+        fmc_boot_params.gsp_rm_params = GspRmParams {
+            target: GSP_DMA_TARGET_NONCOHERENT_SYSTEM,
+            boot_args_offset: libos_addr,
+        };
+
+        let fmc_boot_params: Coherent<GspFmcBootParams> = fmc_boot_params.into();
+
+        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;
 
@@ -188,8 +382,65 @@ pub(crate) fn extract_fmc_signatures(
         Ok(signatures)
     }
 
+    /// 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.
+    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::calc_pmu_reserved_size(args.chipset)))
+                .ok_or(EINVAL)?;
+
+            frts_reserved_size
+                .align_up(Alignment::new::<SZ_2M>())
+                .ok_or(EINVAL)?
+        } else {
+            0
+        };
+        let frts_size: u32 = if !args.resume { u32::SZ_1M } 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.
-    #[expect(dead_code)]
     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 5d7fd810687d..0a05d038ab76 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -141,7 +141,6 @@ 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/gsp/boot.rs b/drivers/gpu/nova-core/gsp/boot.rs
index 739624af1cef..703c9ee48363 100644
--- a/drivers/gpu/nova-core/gsp/boot.rs
+++ b/drivers/gpu/nova-core/gsp/boot.rs
@@ -33,7 +33,10 @@
         gsp::GspFirmware,
         FIRMWARE_VERSION, //
     },
-    fsp::Fsp,
+    fsp::{
+        FmcBootArgs,
+        Fsp, //
+    },
     gpu::{
         Architecture,
         Chipset, //
@@ -203,16 +206,29 @@ fn boot_via_fsp(
         bar: &Bar0,
         chipset: Chipset,
         _gsp_falcon: &Falcon<Gsp>,
-        _wpr_meta: &Coherent<GspFwWprMeta>,
-        _libos: &Coherent<[LibosMemoryRegionInitArgument]>,
+        wpr_meta: &Coherent<GspFwWprMeta>,
+        libos: &Coherent<[LibosMemoryRegionInitArgument]>,
     ) -> Result {
-        let _fsp_falcon = Falcon::<FspEngine>::new(dev, chipset)?;
+        let fsp_falcon = Falcon::<FspEngine>::new(dev, chipset)?;
 
         let fsp_fw = FspFirmware::new(dev, chipset, FIRMWARE_VERSION)?;
-        let _signatures = Fsp::extract_fmc_signatures(dev, fsp_fw.fmc_elf.data())?;
+        let signatures = Fsp::extract_fmc_signatures(dev, fsp_fw.fmc_elf.data())?;
 
         Fsp::wait_secure_boot(dev, bar, chipset.arch())?;
 
+        let args = FmcBootArgs::new(
+            dev,
+            chipset,
+            &fsp_fw.fmc_image,
+            wpr_meta.dma_handle(),
+            core::mem::size_of::<GspFwWprMeta>() as u32,
+            libos.dma_handle(),
+            false,
+            &signatures,
+        )?;
+
+        Fsp::boot_fmc(dev, bar, &fsp_falcon, &args)?;
+
         Err(ENOTSUPP)
     }
 
diff --git a/drivers/gpu/nova-core/mctp.rs b/drivers/gpu/nova-core/mctp.rs
index 680ed19d196e..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)]
-- 
2.53.0