linux/drivers/gpu/nova-core/gpu.rs
Linus Torvalds 260f6f4fda drm for 6.17-rc1
non-drm:
 rust:
 - make ETIMEDOUT available
 - add size constants up to SZ_2G
 - add DMA coherent allocation bindings
 mtd:
 - driver for Intel GPU non-volatile storage
 i2c
 - designware quirk for Intel xe
 
 core:
 - atomic helpers: tune enable/disable sequences
 - add task info to wedge API
 - refactor EDID quirks
 - connector: move HDR sink to drm_display_info
 - fourcc: half-float and 32-bit float formats
 - mode_config: pass format info to simplify
 
 dma-buf:
 - heaps: Give CMA heap a stable name
 
 ci:
 - add device tree validation and kunit
 
 displayport:
 - change AUX DPCD access probe address
 - add quirk for DPCD probe
 - add panel replay definitions
 - backlight control helpers
 
 fbdev:
 - make CONFIG_FIRMWARE_EDID available on all arches
 
 fence:
 - fix UAF issues
 
 format-helper:
 - improve tests
 
 gpusvm:
 - introduce devmem only flag for allocation
 - add timeslicing support to GPU SVM
 
 ttm:
 - improve eviction
 
 sched:
 - tracing improvements
 - kunit improvements
 - memory leak fixes
 - reset handling improvements
 
 color mgmt:
 - add hardware gamma LUT handling helpers
 
 bridge:
 - add destroy hook
 - switch to reference counted drm_bridge allocations
 - tc358767: convert to devm_drm_bridge_alloc
 - improve CEC handling
 
 panel:
 - switch to reference counter drm_panel allocations
 - fwnode panel lookup
 - Huiling hl055fhv028c support
 - Raspberry Pi 7" 720x1280 support
 - edp: KDC KD116N3730A05, N160JCE-ELL CMN, N116BCJ-EAK
 - simple: AUO P238HAN01
 - st7701: Winstar wf40eswaa6mnn0
 - visionox: rm69299-shift
 - Renesas R61307, Renesas R69328 support
 - DJN HX83112B
 
 hdmi:
 - add CEC handling
 - YUV420 output support
 
 xe:
 - WildCat Lake support
 - Enable PanthorLake by default
 - mark BMG as SRIOV capable
 - update firmware recommendations
 - Expose media OA units
 - aux-bux support for non-volatile memory
 - MTD intel-dg driver for non-volatile memory
 - Expose fan control and voltage regulator in sysfs
 - restructure migration for multi-device
 - Restore GuC submit UAF fix
 - make GEM shrinker drm managed
 - SRIOV VF Post-migration recovery of GGTT nodes
 - W/A additions/reworks
 - Prefetch support for svm ranges
 - Don't allocate managed BO for each policy change
 - HWMON fixes for BMG
 - Create LRC BO without VM
 - PCI ID updates
 - make SLPC debugfs files optional
 - rework eviction rejection of bound external BOs
 - consolidate PAT programming logic for pre/post Xe2
 - init changes for flicker-free boot
 - Enable GuC Dynamic Inhibit Context switch
 
 i915:
 - drm_panic support for i915/xe
 - initial flip queue off by default for LNL/PNL
 - Wildcat Lake Display support
 - Support for DSC fractional link bpp
 - Support for simultaneous Panel Replay and Adaptive sync
 - Support for PTL+ double buffer LUT
 - initial PIPEDMC event handling
 - drm_panel_follower support
 - DPLL interface renames
 - allocate struct intel_display dynamically
 - flip queue preperation
 - abstract DRAM detection better
 - avoid GuC scheduling stalls
 - remove DG1 force probe requirement
 - fix MEI interrupt handler on RT kernels
 - use backlight control helpers for eDP
 - more shared display code refactoring
 
 amdgpu:
 - add userq slot to INFO ioctl
 - SR-IOV hibernation support
 - Suspend improvements
 - Backlight improvements
 - Use scaling for non-native eDP modes
 - cleaner shader updates for GC 9.x
 - Remove fence slab
 - SDMA fw checks for userq support
 - RAS updates
 - DMCUB updates
 - DP tunneling fixes
 - Display idle D3 support
 - Per queue reset improvements
 - initial smartmux support
 
 amdkfd:
 - enable KFD on loongarch
 - mtype fix for ext coherent system memory
 
 radeon:
 - CS validation additional GL extensions
 - drop console lock during suspend/resume
 - bump driver version
 
 msm:
 - VM BIND support
 - CI: infrastructure updates
 - UBWC single source of truth
 - decouple GPU and KMS support
 - DP: rework I/O accessors
 - DPU: SM8750 support
 - DSI: SM8750 support
 - GPU: X1-45 support and speedbin support for X1-85
 - MDSS: SM8750 support
 
 nova:
 - register! macro improvements
 - DMA object abstraction
 - VBIOS parser + fwsec lookup
 - sysmem flush page support
 - falcon: generic falcon boot code and HAL
 - FWSEC-FRTS: fb setup and load/execute
 
 ivpu:
 - Add Wildcat Lake support
 - Add turbo flag
 
 ast:
 - improve hardware generations implementation
 
 imx:
 - IMX8qxq Display Controller support
 
 lima:
 - Rockchip RK3528 GPU support
 
 nouveau:
 - fence handling cleanup
 
 panfrost:
 - MT8370 support
 - bo labeling
 - 64-bit register access
 
 qaic:
 - add RAS support
 
 rockchip:
 - convert inno_hdmi to a bridge
 
 rz-du:
 - add RZ/V2H(P) support
 - MIPI-DSI DCS support
 
 sitronix:
 - ST7567 support
 
 sun4i:
 - add H616 support
 
 tidss:
 - add TI AM62L support
 - AM65x OLDI bridge support
 
 bochs:
 - drm panic support
 
 vkms:
 - YUV and R* format support
 - use faux device
 
 vmwgfx:
 - fence improvements
 
 hyperv:
 - move out of simple
 - add drm_panic support
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEEKbZHaGwW9KfbeusDHTzWXnEhr4FAmiJM/0ACgkQDHTzWXnE
 hr6MpA/+JJKGdSdrE95QkaMcOZh/3e3areGXZ0V/RrrJXdB4/DoAfQSHhF0H7m7y
 MhBGVLGNMXq7KHrz28p1MjLHrE1mwmvJ6hZ4J076ed4u9naoCD0m6k5w5wiue+KL
 HyPR54ADxN0BYmgV0l/B0wj42KsHyTO4x4hdqPJu02V9Dtmx6FCh2ujkOF3p9nbK
 GMwWDttl4KEKljD0IvQ9YIYJ66crYGx/XmZi7JoWRrS104K/h1u8qZuXBp5jVKTy
 OZRAVyLdmJqdTOLH7l599MBBcEd/bNV37/LVwF4T5iFunEKOAiyN0QY0OR+IeRVh
 ZfOv2/gp4UNyIfyahQ7LKLgEilNPGHoPitvDJPvBZxW2UjwXVNvA1QfdK5DAlVRS
 D5NoFRjlFFCz8/c2hQwlKJ9o7eVgH3/pK0mwR7SPGQTuqzLFCrAfCuzUvg/gV++6
 JFqmGKMHeCoxO2o4GMrwjFttStP41usxtV/D+grcbPteNO9UyKJS4C38n4eamJXM
 a9Sy9APuAb6F0w5+yMItEF7TQifgmhIbm5AZHlxE1KoDQV6TdiIf1Gou5LeDGoL6
 OACbXHJPL52tUnfCRpbfI4tE/IVyYsfL01JnvZ5cZZWItXfcIz76ykJri+E0G60g
 yRl/zkimHKO4B0l/HSzal5xROXr+3VzeWehEiz/ot1VriP5OesA=
 =n9MO
 -----END PGP SIGNATURE-----

Merge tag 'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights:

   - Intel xe enable Panthor Lake, started adding WildCat Lake

   - amdgpu has a bunch of reset improvments along with the usual IP
     updates

   - msm got VM_BIND support which is important for vulkan sparse memory

   - more drm_panic users

   - gpusvm common code to handle a bunch of core SVM work outside
     drivers.

  Detail summary:

  Changes outside drm subdirectory:
   - 'shrink_shmem_memory()' for better shmem/hibernate interaction
   - Rust support infrastructure:
      - make ETIMEDOUT available
      - add size constants up to SZ_2G
      - add DMA coherent allocation bindings
   - mtd driver for Intel GPU non-volatile storage
   - i2c designware quirk for Intel xe

  core:
   - atomic helpers: tune enable/disable sequences
   - add task info to wedge API
   - refactor EDID quirks
   - connector: move HDR sink to drm_display_info
   - fourcc: half-float and 32-bit float formats
   - mode_config: pass format info to simplify

  dma-buf:
   - heaps: Give CMA heap a stable name

  ci:
   - add device tree validation and kunit

  displayport:
   - change AUX DPCD access probe address
   - add quirk for DPCD probe
   - add panel replay definitions
   - backlight control helpers

  fbdev:
   - make CONFIG_FIRMWARE_EDID available on all arches

  fence:
   - fix UAF issues

  format-helper:
   - improve tests

  gpusvm:
   - introduce devmem only flag for allocation
   - add timeslicing support to GPU SVM

  ttm:
   - improve eviction

  sched:
   - tracing improvements
   - kunit improvements
   - memory leak fixes
   - reset handling improvements

  color mgmt:
   - add hardware gamma LUT handling helpers

  bridge:
   - add destroy hook
   - switch to reference counted drm_bridge allocations
   - tc358767: convert to devm_drm_bridge_alloc
   - improve CEC handling

  panel:
   - switch to reference counter drm_panel allocations
   - fwnode panel lookup
   - Huiling hl055fhv028c support
   - Raspberry Pi 7" 720x1280 support
   - edp: KDC KD116N3730A05, N160JCE-ELL CMN, N116BCJ-EAK
   - simple: AUO P238HAN01
   - st7701: Winstar wf40eswaa6mnn0
   - visionox: rm69299-shift
   - Renesas R61307, Renesas R69328 support
   - DJN HX83112B

  hdmi:
   - add CEC handling
   - YUV420 output support

  xe:
   - WildCat Lake support
   - Enable PanthorLake by default
   - mark BMG as SRIOV capable
   - update firmware recommendations
   - Expose media OA units
   - aux-bux support for non-volatile memory
   - MTD intel-dg driver for non-volatile memory
   - Expose fan control and voltage regulator in sysfs
   - restructure migration for multi-device
   - Restore GuC submit UAF fix
   - make GEM shrinker drm managed
   - SRIOV VF Post-migration recovery of GGTT nodes
   - W/A additions/reworks
   - Prefetch support for svm ranges
   - Don't allocate managed BO for each policy change
   - HWMON fixes for BMG
   - Create LRC BO without VM
   - PCI ID updates
   - make SLPC debugfs files optional
   - rework eviction rejection of bound external BOs
   - consolidate PAT programming logic for pre/post Xe2
   - init changes for flicker-free boot
   - Enable GuC Dynamic Inhibit Context switch

  i915:
   - drm_panic support for i915/xe
   - initial flip queue off by default for LNL/PNL
   - Wildcat Lake Display support
   - Support for DSC fractional link bpp
   - Support for simultaneous Panel Replay and Adaptive sync
   - Support for PTL+ double buffer LUT
   - initial PIPEDMC event handling
   - drm_panel_follower support
   - DPLL interface renames
   - allocate struct intel_display dynamically
   - flip queue preperation
   - abstract DRAM detection better
   - avoid GuC scheduling stalls
   - remove DG1 force probe requirement
   - fix MEI interrupt handler on RT kernels
   - use backlight control helpers for eDP
   - more shared display code refactoring

  amdgpu:
   - add userq slot to INFO ioctl
   - SR-IOV hibernation support
   - Suspend improvements
   - Backlight improvements
   - Use scaling for non-native eDP modes
   - cleaner shader updates for GC 9.x
   - Remove fence slab
   - SDMA fw checks for userq support
   - RAS updates
   - DMCUB updates
   - DP tunneling fixes
   - Display idle D3 support
   - Per queue reset improvements
   - initial smartmux support

  amdkfd:
   - enable KFD on loongarch
   - mtype fix for ext coherent system memory

  radeon:
   - CS validation additional GL extensions
   - drop console lock during suspend/resume
   - bump driver version

  msm:
   - VM BIND support
   - CI: infrastructure updates
   - UBWC single source of truth
   - decouple GPU and KMS support
   - DP: rework I/O accessors
   - DPU: SM8750 support
   - DSI: SM8750 support
   - GPU: X1-45 support and speedbin support for X1-85
   - MDSS: SM8750 support

  nova:
   - register! macro improvements
   - DMA object abstraction
   - VBIOS parser + fwsec lookup
   - sysmem flush page support
   - falcon: generic falcon boot code and HAL
   - FWSEC-FRTS: fb setup and load/execute

  ivpu:
   - Add Wildcat Lake support
   - Add turbo flag

  ast:
   - improve hardware generations implementation

  imx:
   - IMX8qxq Display Controller support

  lima:
   - Rockchip RK3528 GPU support

  nouveau:
   - fence handling cleanup

  panfrost:
   - MT8370 support
   - bo labeling
   - 64-bit register access

  qaic:
   - add RAS support

  rockchip:
   - convert inno_hdmi to a bridge

  rz-du:
   - add RZ/V2H(P) support
   - MIPI-DSI DCS support

  sitronix:
   - ST7567 support

  sun4i:
   - add H616 support

  tidss:
   - add TI AM62L support
   - AM65x OLDI bridge support

  bochs:
   - drm panic support

  vkms:
   - YUV and R* format support
   - use faux device

  vmwgfx:
   - fence improvements

  hyperv:
   - move out of simple
   - add drm_panic support"

* tag 'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel: (1479 commits)
  drm/tidss: oldi: convert to devm_drm_bridge_alloc() API
  drm/tidss: encoder: convert to devm_drm_bridge_alloc()
  drm/amdgpu: move reset support type checks into the caller
  drm/amdgpu/sdma7: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma6: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma5.2: re-emit unprocessed state on ring reset
  drm/amdgpu/sdma5: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx12: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx11: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx10: re-emit unprocessed state on ring reset
  drm/amdgpu/gfx9.4.3: re-emit unprocessed state on kcq reset
  drm/amdgpu/gfx9: re-emit unprocessed state on kcq reset
  drm/amdgpu: Add WARN_ON to the resource clear function
  drm/amd/pm: Use cached metrics data on SMUv13.0.6
  drm/amd/pm: Use cached data for min/max clocks
  gpu: nova-core: fix bounds check in PmuLookupTableEntry::new
  drm/amdgpu: Replace HQD terminology with slots naming
  drm/amdgpu: Add user queue instance count in HW IP info
  drm/amd/amdgpu: Add helper functions for isp buffers
  drm/amd/amdgpu: Initialize swnode for ISP MFD device
  ...
2025-07-30 19:26:49 -07:00

312 lines
8.7 KiB
Rust

// SPDX-License-Identifier: GPL-2.0
use kernel::{device, devres::Devres, error::code::*, pci, prelude::*, sync::Arc};
use crate::driver::Bar0;
use crate::falcon::{gsp::Gsp, sec2::Sec2, Falcon};
use crate::fb::FbLayout;
use crate::fb::SysmemFlush;
use crate::firmware::fwsec::{FwsecCommand, FwsecFirmware};
use crate::firmware::{Firmware, FIRMWARE_VERSION};
use crate::gfw;
use crate::regs;
use crate::util;
use crate::vbios::Vbios;
use core::fmt;
macro_rules! define_chipset {
({ $($variant:ident = $value:expr),* $(,)* }) =>
{
/// Enum representation of the GPU chipset.
#[derive(fmt::Debug, Copy, Clone, PartialOrd, Ord, PartialEq, Eq)]
pub(crate) enum Chipset {
$($variant = $value),*,
}
impl Chipset {
pub(crate) const ALL: &'static [Chipset] = &[
$( Chipset::$variant, )*
];
pub(crate) const NAMES: [&'static str; Self::ALL.len()] = [
$( util::const_bytes_to_str(
util::to_lowercase_bytes::<{ stringify!($variant).len() }>(
stringify!($variant)
).as_slice()
), )*
];
}
// TODO[FPRI]: replace with something like derive(FromPrimitive)
impl TryFrom<u32> for Chipset {
type Error = kernel::error::Error;
fn try_from(value: u32) -> Result<Self, Self::Error> {
match value {
$( $value => Ok(Chipset::$variant), )*
_ => Err(ENODEV),
}
}
}
}
}
define_chipset!({
// Turing
TU102 = 0x162,
TU104 = 0x164,
TU106 = 0x166,
TU117 = 0x167,
TU116 = 0x168,
// Ampere
GA100 = 0x170,
GA102 = 0x172,
GA103 = 0x173,
GA104 = 0x174,
GA106 = 0x176,
GA107 = 0x177,
// Ada
AD102 = 0x192,
AD103 = 0x193,
AD104 = 0x194,
AD106 = 0x196,
AD107 = 0x197,
});
impl Chipset {
pub(crate) fn arch(&self) -> Architecture {
match self {
Self::TU102 | Self::TU104 | Self::TU106 | Self::TU117 | Self::TU116 => {
Architecture::Turing
}
Self::GA100 | Self::GA102 | Self::GA103 | Self::GA104 | Self::GA106 | Self::GA107 => {
Architecture::Ampere
}
Self::AD102 | Self::AD103 | Self::AD104 | Self::AD106 | Self::AD107 => {
Architecture::Ada
}
}
}
}
// TODO
//
// The resulting strings are used to generate firmware paths, hence the
// generated strings have to be stable.
//
// Hence, replace with something like strum_macros derive(Display).
//
// For now, redirect to fmt::Debug for convenience.
impl fmt::Display for Chipset {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "{self:?}")
}
}
/// Enum representation of the GPU generation.
#[derive(fmt::Debug)]
pub(crate) enum Architecture {
Turing = 0x16,
Ampere = 0x17,
Ada = 0x19,
}
impl TryFrom<u8> for Architecture {
type Error = Error;
fn try_from(value: u8) -> Result<Self> {
match value {
0x16 => Ok(Self::Turing),
0x17 => Ok(Self::Ampere),
0x19 => Ok(Self::Ada),
_ => Err(ENODEV),
}
}
}
pub(crate) struct Revision {
major: u8,
minor: u8,
}
impl Revision {
fn from_boot0(boot0: regs::NV_PMC_BOOT_0) -> Self {
Self {
major: boot0.major_revision(),
minor: boot0.minor_revision(),
}
}
}
impl fmt::Display for Revision {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "{:x}.{:x}", self.major, self.minor)
}
}
/// Structure holding the metadata of the GPU.
pub(crate) struct Spec {
chipset: Chipset,
/// The revision of the chipset.
revision: Revision,
}
impl Spec {
fn new(bar: &Bar0) -> Result<Spec> {
let boot0 = regs::NV_PMC_BOOT_0::read(bar);
Ok(Self {
chipset: boot0.chipset()?,
revision: Revision::from_boot0(boot0),
})
}
}
/// Structure holding the resources required to operate the GPU.
#[pin_data(PinnedDrop)]
pub(crate) struct Gpu {
spec: Spec,
/// MMIO mapping of PCI BAR 0
bar: Arc<Devres<Bar0>>,
fw: Firmware,
/// System memory page required for flushing all pending GPU-side memory writes done through
/// PCIE into system memory, via sysmembar (A GPU-initiated HW memory-barrier operation).
sysmem_flush: SysmemFlush,
}
#[pinned_drop]
impl PinnedDrop for Gpu {
fn drop(self: Pin<&mut Self>) {
// Unregister the sysmem flush page before we release it.
self.bar
.try_access_with(|b| self.sysmem_flush.unregister(b));
}
}
impl Gpu {
/// Helper function to load and run the FWSEC-FRTS firmware and confirm that it has properly
/// created the WPR2 region.
///
/// TODO: this needs to be moved into a larger type responsible for booting the whole GSP
/// (`GspBooter`?).
fn run_fwsec_frts(
dev: &device::Device<device::Bound>,
falcon: &Falcon<Gsp>,
bar: &Bar0,
bios: &Vbios,
fb_layout: &FbLayout,
) -> Result<()> {
// Check that the WPR2 region does not already exists - if it does, we cannot run
// FWSEC-FRTS until the GPU is reset.
if regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound() != 0 {
dev_err!(
dev,
"WPR2 region already exists - GPU needs to be reset to proceed\n"
);
return Err(EBUSY);
}
let fwsec_frts = FwsecFirmware::new(
dev,
falcon,
bar,
bios,
FwsecCommand::Frts {
frts_addr: fb_layout.frts.start,
frts_size: fb_layout.frts.end - fb_layout.frts.start,
},
)?;
// Run FWSEC-FRTS to create the WPR2 region.
fwsec_frts.run(dev, falcon, bar)?;
// SCRATCH_E contains the error code for FWSEC-FRTS.
let frts_status = regs::NV_PBUS_SW_SCRATCH_0E::read(bar).frts_err_code();
if frts_status != 0 {
dev_err!(
dev,
"FWSEC-FRTS returned with error code {:#x}",
frts_status
);
return Err(EIO);
}
// Check that the WPR2 region has been created as we requested.
let (wpr2_lo, wpr2_hi) = (
regs::NV_PFB_PRI_MMU_WPR2_ADDR_LO::read(bar).lower_bound(),
regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound(),
);
match (wpr2_lo, wpr2_hi) {
(_, 0) => {
dev_err!(dev, "WPR2 region not created after running FWSEC-FRTS\n");
Err(EIO)
}
(wpr2_lo, _) if wpr2_lo != fb_layout.frts.start => {
dev_err!(
dev,
"WPR2 region created at unexpected address {:#x}; expected {:#x}\n",
wpr2_lo,
fb_layout.frts.start,
);
Err(EIO)
}
(wpr2_lo, wpr2_hi) => {
dev_dbg!(dev, "WPR2: {:#x}-{:#x}\n", wpr2_lo, wpr2_hi);
dev_dbg!(dev, "GPU instance built\n");
Ok(())
}
}
}
pub(crate) fn new(
pdev: &pci::Device<device::Bound>,
devres_bar: Arc<Devres<Bar0>>,
) -> Result<impl PinInit<Self>> {
let bar = devres_bar.access(pdev.as_ref())?;
let spec = Spec::new(bar)?;
let fw = Firmware::new(pdev.as_ref(), spec.chipset, FIRMWARE_VERSION)?;
dev_info!(
pdev.as_ref(),
"NVIDIA (Chipset: {}, Architecture: {:?}, Revision: {})\n",
spec.chipset,
spec.chipset.arch(),
spec.revision
);
// We must wait for GFW_BOOT completion before doing any significant setup on the GPU.
gfw::wait_gfw_boot_completion(bar)
.inspect_err(|_| dev_err!(pdev.as_ref(), "GFW boot did not complete"))?;
let sysmem_flush = SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?;
let gsp_falcon = Falcon::<Gsp>::new(
pdev.as_ref(),
spec.chipset,
bar,
spec.chipset > Chipset::GA100,
)?;
gsp_falcon.clear_swgen0_intr(bar);
let _sec2_falcon = Falcon::<Sec2>::new(pdev.as_ref(), spec.chipset, bar, true)?;
let fb_layout = FbLayout::new(spec.chipset, bar)?;
dev_dbg!(pdev.as_ref(), "{:#x?}\n", fb_layout);
let bios = Vbios::new(pdev, bar)?;
Self::run_fwsec_frts(pdev.as_ref(), &gsp_falcon, bar, &bios, &fb_layout)?;
Ok(pin_init!(Self {
spec,
bar: devres_bar,
fw,
sysmem_flush,
}))
}
}