From: John Hubbard <jhubbard@nvidia.com>
To: Danilo Krummrich <dakr@kernel.org>,
Alexandre Courbot <acourbot@nvidia.com>
Cc: "Joel Fernandes" <joelagnelf@nvidia.com>,
"Timur Tabi" <ttabi@nvidia.com>,
"Alistair Popple" <apopple@nvidia.com>,
"Eliot Courtney" <ecourtney@nvidia.com>,
"Shashank Sharma" <shashanks@nvidia.com>,
"Zhi Wang" <zhiw@nvidia.com>, "David Airlie" <airlied@gmail.com>,
"Simona Vetter" <simona@ffwll.ch>,
"Bjorn Helgaas" <bhelgaas@google.com>,
"Miguel Ojeda" <ojeda@kernel.org>,
"Alex Gaynor" <alex.gaynor@gmail.com>,
"Boqun Feng" <boqun.feng@gmail.com>,
"Gary Guo" <gary@garyguo.net>,
"Björn Roy Baron" <bjorn3_gh@protonmail.com>,
"Benno Lossin" <lossin@kernel.org>,
"Andreas Hindborg" <a.hindborg@kernel.org>,
"Alice Ryhl" <aliceryhl@google.com>,
"Trevor Gross" <tmgross@umich.edu>,
rust-for-linux@vger.kernel.org,
LKML <linux-kernel@vger.kernel.org>,
"John Hubbard" <jhubbard@nvidia.com>
Subject: [PATCH v6 30/34] gpu: nova-core: Hopper/Blackwell: larger WPR2 (GSP) heap
Date: Mon, 9 Mar 2026 19:11:20 -0700 [thread overview]
Message-ID: <20260310021125.117855-31-jhubbard@nvidia.com> (raw)
In-Reply-To: <20260310021125.117855-1-jhubbard@nvidia.com>
Hopper, Blackwell and later GPUs require a larger heap for WPR2.
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
drivers/gpu/nova-core/fb.rs | 2 +-
drivers/gpu/nova-core/gsp/fw.rs | 74 ++++++++++++++++++++++++---------
2 files changed, 55 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/nova-core/fb.rs b/drivers/gpu/nova-core/fb.rs
index c12705f5f742..5943db2b619b 100644
--- a/drivers/gpu/nova-core/fb.rs
+++ b/drivers/gpu/nova-core/fb.rs
@@ -247,7 +247,7 @@ pub(crate) fn new(chipset: Chipset, bar: &Bar0, gsp_fw: &GspFirmware) -> Result<
let wpr2_heap = {
const WPR2_HEAP_DOWN_ALIGN: Alignment = Alignment::new::<SZ_1M>();
let wpr2_heap_size =
- gsp::LibosParams::from_chipset(chipset).wpr_heap_size(chipset, fb.end);
+ gsp::LibosParams::from_chipset(chipset).wpr_heap_size(chipset, fb.end)?;
let wpr2_heap_addr = (elf.start - wpr2_heap_size).align_down(WPR2_HEAP_DOWN_ALIGN);
FbRange(wpr2_heap_addr..(elf.start).align_down(WPR2_HEAP_DOWN_ALIGN))
diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs
index c1f76659dfba..7834efc9095a 100644
--- a/drivers/gpu/nova-core/gsp/fw.rs
+++ b/drivers/gpu/nova-core/gsp/fw.rs
@@ -48,32 +48,52 @@ enum GspFwHeapParams {}
/// Minimum required alignment for the GSP heap.
const GSP_HEAP_ALIGNMENT: Alignment = Alignment::new::<{ 1 << 20 }>();
+// These constants override the generated bindings for architecture-specific heap sizing.
+// See Open RM: kgspCalculateGspFwHeapSize and related functions.
+//
+// 14MB for Hopper/Blackwell+.
+const GSP_FW_HEAP_PARAM_BASE_RM_SIZE_GH100: u64 = 14 * num::usize_as_u64(SZ_1M);
+// 142MB client alloc for ~188MB total.
+const GSP_FW_HEAP_PARAM_CLIENT_ALLOC_SIZE_GH100: u64 = 142 * num::usize_as_u64(SZ_1M);
+// Hopper/Blackwell+ minimum heap size: 170MB (88 + 12 + 70).
+// See Open RM: GSP_FW_HEAP_SIZE_OVERRIDE_LIBOS3_BAREMETAL_MIN_MB for the base 88MB,
+// plus Hopper+ additions in kgspCalculateGspFwHeapSize_GH100.
+const GSP_FW_HEAP_SIZE_OVERRIDE_LIBOS3_BAREMETAL_MIN_MB_HOPPER: u64 = 170;
+
impl GspFwHeapParams {
/// Returns the amount of GSP-RM heap memory used during GSP-RM boot and initialization (up to
/// and including the first client subdevice allocation).
- fn base_rm_size(_chipset: Chipset) -> u64 {
- // TODO: this needs to be updated to return the correct value for Hopper+ once support for
- // them is added:
- // u64::from(bindings::GSP_FW_HEAP_PARAM_BASE_RM_SIZE_GH100)
- u64::from(bindings::GSP_FW_HEAP_PARAM_BASE_RM_SIZE_TU10X)
+ fn base_rm_size(chipset: Chipset) -> u64 {
+ use crate::gpu::Architecture;
+ match chipset.arch() {
+ Architecture::Hopper | Architecture::Blackwell => {
+ GSP_FW_HEAP_PARAM_BASE_RM_SIZE_GH100
+ }
+ _ => u64::from(bindings::GSP_FW_HEAP_PARAM_BASE_RM_SIZE_TU10X),
+ }
}
/// Returns the amount of heap memory required to support a single channel allocation.
- fn client_alloc_size() -> u64 {
- u64::from(bindings::GSP_FW_HEAP_PARAM_CLIENT_ALLOC_SIZE)
- .align_up(GSP_HEAP_ALIGNMENT)
- .unwrap_or(u64::MAX)
+ fn client_alloc_size(chipset: Chipset) -> Result<u64> {
+ use crate::gpu::Architecture;
+ let size = match chipset.arch() {
+ Architecture::Hopper | Architecture::Blackwell => {
+ GSP_FW_HEAP_PARAM_CLIENT_ALLOC_SIZE_GH100
+ }
+ _ => u64::from(bindings::GSP_FW_HEAP_PARAM_CLIENT_ALLOC_SIZE),
+ };
+ size.align_up(GSP_HEAP_ALIGNMENT).ok_or(EINVAL)
}
/// Returns the amount of memory to reserve for management purposes for a framebuffer of size
/// `fb_size`.
- fn management_overhead(fb_size: u64) -> u64 {
+ fn management_overhead(fb_size: u64) -> Result<u64> {
let fb_size_gb = fb_size.div_ceil(u64::from_safe_cast(kernel::sizes::SZ_1G));
u64::from(bindings::GSP_FW_HEAP_PARAM_SIZE_PER_GB_FB)
.saturating_mul(fb_size_gb)
.align_up(GSP_HEAP_ALIGNMENT)
- .unwrap_or(u64::MAX)
+ .ok_or(EINVAL)
}
}
@@ -105,29 +125,43 @@ impl LibosParams {
* num::usize_as_u64(SZ_1M),
};
+ /// Hopper/Blackwell+ GPUs need a larger minimum heap size than the bindings specify.
+ /// The r570 bindings set LIBOS3_BAREMETAL_MIN_MB to 88MB, but Hopper/Blackwell+ actually
+ /// requires 170MB (88 + 12 + 70).
+ const LIBOS_HOPPER: LibosParams = LibosParams {
+ carveout_size: num::u32_as_u64(bindings::GSP_FW_HEAP_PARAM_OS_SIZE_LIBOS3_BAREMETAL),
+ allowed_heap_size: GSP_FW_HEAP_SIZE_OVERRIDE_LIBOS3_BAREMETAL_MIN_MB_HOPPER
+ * num::usize_as_u64(SZ_1M)
+ ..num::u32_as_u64(bindings::GSP_FW_HEAP_SIZE_OVERRIDE_LIBOS3_BAREMETAL_MAX_MB)
+ * num::usize_as_u64(SZ_1M),
+ };
+
/// Returns the libos parameters corresponding to `chipset`.
pub(crate) fn from_chipset(chipset: Chipset) -> &'static LibosParams {
- if chipset < Chipset::GA102 {
- &Self::LIBOS2
- } else {
- &Self::LIBOS3
+ use crate::gpu::Architecture;
+ match chipset.arch() {
+ Architecture::Turing => &Self::LIBOS2,
+ Architecture::Ampere if chipset == Chipset::GA100 => &Self::LIBOS2,
+ Architecture::Ampere | Architecture::Ada => &Self::LIBOS3,
+ Architecture::Hopper | Architecture::Blackwell => &Self::LIBOS_HOPPER,
}
}
/// Returns the amount of memory (in bytes) to allocate for the WPR heap for a framebuffer size
/// of `fb_size` (in bytes) for `chipset`.
- pub(crate) fn wpr_heap_size(&self, chipset: Chipset, fb_size: u64) -> u64 {
+ pub(crate) fn wpr_heap_size(&self, chipset: Chipset, fb_size: u64) -> Result<u64> {
// The WPR heap will contain the following:
// LIBOS carveout,
- self.carveout_size
+ Ok(self
+ .carveout_size
// RM boot working memory,
.saturating_add(GspFwHeapParams::base_rm_size(chipset))
// One RM client,
- .saturating_add(GspFwHeapParams::client_alloc_size())
+ .saturating_add(GspFwHeapParams::client_alloc_size(chipset)?)
// Overhead for memory management.
- .saturating_add(GspFwHeapParams::management_overhead(fb_size))
+ .saturating_add(GspFwHeapParams::management_overhead(fb_size)?)
// Clamp to the supported heap sizes.
- .clamp(self.allowed_heap_size.start, self.allowed_heap_size.end - 1)
+ .clamp(self.allowed_heap_size.start, self.allowed_heap_size.end - 1))
}
}
--
2.53.0
next prev parent reply other threads:[~2026-03-10 2:12 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-10 2:10 [PATCH v6 00/34] gpu: nova-core: firmware: Hopper/Blackwell support John Hubbard
2026-03-10 2:10 ` [PATCH v6 01/34] gpu: nova-core: print FB sizes, along with ranges John Hubbard
2026-03-10 11:21 ` Alexandre Courbot
2026-03-10 2:10 ` [PATCH v6 02/34] gpu: nova-core: add FbRange.len() and use it in boot.rs John Hubbard
2026-03-10 11:21 ` Alexandre Courbot
2026-03-10 2:10 ` [PATCH v6 03/34] gpu: nova-core: Hopper/Blackwell: basic GPU identification John Hubbard
2026-03-10 8:06 ` Alexandre Courbot
2026-03-10 16:54 ` John Hubbard
2026-03-10 2:10 ` [PATCH v6 04/34] gpu: nova-core: factor .fwsignature* selection into a new find_gsp_sigs_section() John Hubbard
2026-03-10 2:10 ` [PATCH v6 05/34] gpu: nova-core: use GPU Architecture to simplify HAL selections John Hubbard
2026-03-10 2:10 ` [PATCH v6 06/34] gpu: nova-core: apply the one "use" item per line policy to commands.rs John Hubbard
2026-03-10 11:21 ` Alexandre Courbot
2026-03-10 2:10 ` [PATCH v6 07/34] gpu: nova-core: move GPU init and DMA mask setup into Gpu::new() John Hubbard
2026-03-10 8:23 ` Alexandre Courbot
2026-03-10 2:10 ` [PATCH v6 08/34] gpu: nova-core: set DMA mask width based on GPU architecture John Hubbard
2026-03-10 2:10 ` [PATCH v6 09/34] gpu: nova-core: Hopper/Blackwell: skip GFW boot waiting John Hubbard
2026-03-10 10:23 ` Alexandre Courbot
2026-03-10 2:11 ` [PATCH v6 10/34] gpu: nova-core: move firmware image parsing code to firmware.rs John Hubbard
2026-03-10 10:28 ` Alexandre Courbot
2026-03-10 2:11 ` [PATCH v6 11/34] gpu: nova-core: factor out an elf_str() function John Hubbard
2026-03-10 2:11 ` [PATCH v6 12/34] gpu: nova-core: don't assume 64-bit firmware images John Hubbard
2026-03-10 10:38 ` Alexandre Courbot
2026-03-10 2:11 ` [PATCH v6 13/34] gpu: nova-core: add support for 32-bit " John Hubbard
2026-03-10 2:11 ` [PATCH v6 14/34] gpu: nova-core: add auto-detection of 32-bit, 64-bit " John Hubbard
2026-03-10 2:11 ` [PATCH v6 15/34] gpu: nova-core: Hopper/Blackwell: add FMC firmware image, in support of FSP John Hubbard
2026-03-10 2:11 ` [PATCH v6 16/34] gpu: nova-core: Hopper/Blackwell: add FSP falcon engine stub John Hubbard
2026-03-10 2:11 ` [PATCH v6 17/34] gpu: nova-core: Hopper/Blackwell: add FSP falcon EMEM operations John Hubbard
2026-03-10 2:11 ` [PATCH v6 18/34] gpu: nova-core: Hopper/Blackwell: add FSP message infrastructure John Hubbard
2026-03-10 10:57 ` Alexandre Courbot
2026-03-11 17:53 ` Timur Tabi
2026-03-10 2:11 ` [PATCH v6 19/34] rust: ptr: add const_align_up() John Hubbard
2026-03-10 2:11 ` [PATCH v6 20/34] gpu: nova-core: Hopper/Blackwell: calculate reserved FB heap size John Hubbard
2026-03-10 2:11 ` [PATCH v6 21/34] gpu: nova-core: add MCTP/NVDM protocol types for firmware communication John Hubbard
2026-03-10 10:53 ` Alexandre Courbot
2026-03-10 2:11 ` [PATCH v6 22/34] gpu: nova-core: Hopper/Blackwell: add FSP secure boot completion waiting John Hubbard
2026-03-10 2:11 ` [PATCH v6 23/34] gpu: nova-core: Hopper/Blackwell: add FSP message structures John Hubbard
2026-03-10 11:01 ` Alexandre Courbot
2026-03-10 2:11 ` [PATCH v6 24/34] gpu: nova-core: Hopper/Blackwell: add FMC signature extraction John Hubbard
2026-03-10 2:11 ` [PATCH v6 25/34] gpu: nova-core: Hopper/Blackwell: add FSP send/receive messaging John Hubbard
2026-03-10 2:11 ` [PATCH v6 26/34] gpu: nova-core: Hopper/Blackwell: add FspCotVersion type John Hubbard
2026-03-10 2:11 ` [PATCH v6 27/34] gpu: nova-core: Hopper/Blackwell: larger non-WPR heap John Hubbard
2026-03-10 2:11 ` [PATCH v6 28/34] gpu: nova-core: Hopper/Blackwell: add FSP Chain of Trust boot John Hubbard
2026-03-17 8:20 ` Alexandre Courbot
2026-03-10 2:11 ` [PATCH v6 29/34] gpu: nova-core: Blackwell: use correct sysmem flush registers John Hubbard
2026-03-10 2:11 ` John Hubbard [this message]
2026-03-17 8:25 ` [PATCH v6 30/34] gpu: nova-core: Hopper/Blackwell: larger WPR2 (GSP) heap Alexandre Courbot
2026-03-10 2:11 ` [PATCH v6 31/34] gpu: nova-core: refactor SEC2 booter loading into BooterFirmware::run() John Hubbard
2026-03-10 2:11 ` [PATCH v6 32/34] gpu: nova-core: Hopper/Blackwell: add GSP lockdown release polling John Hubbard
2026-03-10 2:11 ` [PATCH v6 33/34] gpu: nova-core: Hopper/Blackwell: new location for PCI config mirror John Hubbard
2026-03-17 8:27 ` Alexandre Courbot
2026-03-17 22:17 ` John Hubbard
2026-03-10 2:11 ` [PATCH v6 34/34] gpu: nova-core: Hopper/Blackwell: integrate FSP boot path into boot() John Hubbard
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260310021125.117855-31-jhubbard@nvidia.com \
--to=jhubbard@nvidia.com \
--cc=a.hindborg@kernel.org \
--cc=acourbot@nvidia.com \
--cc=airlied@gmail.com \
--cc=alex.gaynor@gmail.com \
--cc=aliceryhl@google.com \
--cc=apopple@nvidia.com \
--cc=bhelgaas@google.com \
--cc=bjorn3_gh@protonmail.com \
--cc=boqun.feng@gmail.com \
--cc=dakr@kernel.org \
--cc=ecourtney@nvidia.com \
--cc=gary@garyguo.net \
--cc=joelagnelf@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lossin@kernel.org \
--cc=ojeda@kernel.org \
--cc=rust-for-linux@vger.kernel.org \
--cc=shashanks@nvidia.com \
--cc=simona@ffwll.ch \
--cc=tmgross@umich.edu \
--cc=ttabi@nvidia.com \
--cc=zhiw@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.