public inbox for rust-for-linux@vger.kernel.org
 help / color / mirror / Atom feed
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>,
	"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>,
	nouveau@lists.freedesktop.org, rust-for-linux@vger.kernel.org,
	LKML <linux-kernel@vger.kernel.org>,
	"John Hubbard" <jhubbard@nvidia.com>
Subject: [PATCH v5 32/38] gpu: nova-core: Hopper/Blackwell: larger WPR2 (GSP) heap
Date: Fri, 20 Feb 2026 18:09:46 -0800	[thread overview]
Message-ID: <20260221020952.412352-33-jhubbard@nvidia.com> (raw)
In-Reply-To: <20260221020952.412352-1-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 8b3ba9c9f464..08e6dd815352 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 086153edfa86..7fa9d3b1a592 100644
--- a/drivers/gpu/nova-core/gsp/fw.rs
+++ b/drivers/gpu/nova-core/gsp/fw.rs
@@ -49,32 +49,52 @@ 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)
     }
 }
 
@@ -106,29 +126,43 @@ 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


  parent reply	other threads:[~2026-02-21  2:11 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-21  2:09 [PATCH v5 00/38] gpu: nova-core: firmware: Hopper/Blackwell support John Hubbard
2026-02-21  2:09 ` [PATCH v5 01/38] gpu: nova-core: fix aux device registration for multi-GPU systems John Hubbard
2026-02-24 14:47   ` Danilo Krummrich
2026-02-27 15:37     ` Gary Guo
2026-02-27 15:41       ` Gary Guo
2026-02-27 16:05         ` Danilo Krummrich
2026-02-27 16:29           ` John Hubbard
2026-02-21  2:09 ` [PATCH v5 02/38] gpu: nova-core: pass pdev directly to dev_* logging macros John Hubbard
2026-02-21  2:09 ` [PATCH v5 03/38] gpu: nova-core: print FB sizes, along with ranges John Hubbard
2026-02-21  2:09 ` [PATCH v5 04/38] gpu: nova-core: add FbRange.len() and use it in boot.rs John Hubbard
2026-02-21  2:09 ` [PATCH v5 05/38] gpu: nova-core: Hopper/Blackwell: basic GPU identification John Hubbard
2026-02-21  2:09 ` [PATCH v5 06/38] gpu: nova-core: factor .fwsignature* selection into a new find_gsp_sigs_section() John Hubbard
2026-02-21  2:09 ` [PATCH v5 07/38] gpu: nova-core: use GPU Architecture to simplify HAL selections John Hubbard
2026-02-21  2:09 ` [PATCH v5 08/38] gpu: nova-core: apply the one "use" item per line policy to commands.rs John Hubbard
2026-02-21  2:09 ` [PATCH v5 09/38] gpu: nova-core: move GPU init and DMA mask setup into Gpu::new() John Hubbard
2026-02-21  2:09 ` [PATCH v5 10/38] gpu: nova-core: set DMA mask width based on GPU architecture John Hubbard
2026-02-21  2:09 ` [PATCH v5 11/38] gpu: nova-core: Hopper/Blackwell: skip GFW boot waiting John Hubbard
2026-02-21  2:09 ` [PATCH v5 12/38] gpu: nova-core: move firmware image parsing code to firmware.rs John Hubbard
2026-02-21  2:09 ` [PATCH v5 13/38] gpu: nova-core: factor out an elf_str() function John Hubbard
2026-02-21  2:09 ` [PATCH v5 14/38] gpu: nova-core: don't assume 64-bit firmware images John Hubbard
2026-02-21  2:09 ` [PATCH v5 15/38] gpu: nova-core: add support for 32-bit " John Hubbard
2026-02-21  2:09 ` [PATCH v5 16/38] gpu: nova-core: add auto-detection of 32-bit, 64-bit " John Hubbard
2026-02-21  2:09 ` [PATCH v5 17/38] gpu: nova-core: Hopper/Blackwell: add FMC firmware image, in support of FSP John Hubbard
2026-02-21  2:09 ` [PATCH v5 18/38] gpu: nova-core: Hopper/Blackwell: add FSP falcon engine stub John Hubbard
2026-02-21  2:09 ` [PATCH v5 19/38] gpu: nova-core: Hopper/Blackwell: add FSP falcon EMEM operations John Hubbard
2026-02-21  2:09 ` [PATCH v5 20/38] gpu: nova-core: Hopper/Blackwell: add FSP message infrastructure John Hubbard
2026-02-21  2:09 ` [PATCH v5 21/38] rust: ptr: add const_align_up() and enable inline_const feature John Hubbard
2026-02-21 20:50   ` Miguel Ojeda
2026-02-22 19:03     ` John Hubbard
2026-02-22 19:08       ` Miguel Ojeda
2026-02-23  3:36         ` Alexandre Courbot
2026-02-22  7:46   ` Gary Guo
2026-02-22 19:04     ` John Hubbard
2026-02-23 11:07       ` Danilo Krummrich
2026-02-23 14:16         ` Gary Guo
2026-02-23 14:20           ` Danilo Krummrich
2026-03-04  3:47             ` John Hubbard
2026-03-04 11:18               ` Gary Guo
2026-03-04 18:53                 ` John Hubbard
2026-03-04 19:04                   ` Gary Guo
2026-03-04 19:14                     ` John Hubbard
2026-03-05  1:23                       ` Alexandre Courbot
2026-03-05  1:31                         ` John Hubbard
2026-03-05  7:07                           ` Alexandre Courbot
2026-03-05 12:28                             ` Gary Guo
2026-03-05 12:36                               ` Danilo Krummrich
2026-03-05 12:59                                 ` Gary Guo
2026-03-05 13:59                               ` Alexandre Courbot
2026-03-05 14:05                                 ` Gary Guo
2026-03-05 15:17                                   ` Alexandre Courbot
2026-02-23 11:23   ` Alice Ryhl
2026-02-21  2:09 ` [PATCH v5 22/38] gpu: nova-core: Hopper/Blackwell: calculate reserved FB heap size John Hubbard
2026-02-21  2:09 ` [PATCH v5 23/38] gpu: nova-core: add MCTP/NVDM protocol types for firmware communication John Hubbard
2026-02-21  2:09 ` [PATCH v5 24/38] gpu: nova-core: Hopper/Blackwell: add FSP secure boot completion waiting John Hubbard
2026-02-21  2:09 ` [PATCH v5 25/38] gpu: nova-core: Hopper/Blackwell: add FSP message structures John Hubbard
2026-02-21  2:09 ` [PATCH v5 26/38] gpu: nova-core: Hopper/Blackwell: add FMC signature extraction John Hubbard
2026-02-21  2:09 ` [PATCH v5 27/38] gpu: nova-core: Hopper/Blackwell: add FSP send/receive messaging John Hubbard
2026-02-21  2:09 ` [PATCH v5 28/38] gpu: nova-core: Hopper/Blackwell: add FspCotVersion type John Hubbard
2026-02-21  2:09 ` [PATCH v5 29/38] gpu: nova-core: Hopper/Blackwell: larger non-WPR heap John Hubbard
2026-02-21  2:09 ` [PATCH v5 30/38] gpu: nova-core: Hopper/Blackwell: add FSP Chain of Trust boot John Hubbard
2026-02-21  2:09 ` [PATCH v5 31/38] gpu: nova-core: Blackwell: use correct sysmem flush registers John Hubbard
2026-02-21  2:09 ` John Hubbard [this message]
2026-02-21  2:09 ` [PATCH v5 33/38] gpu: nova-core: refactor SEC2 booter loading into BooterFirmware::run() John Hubbard
2026-02-21  2:09 ` [PATCH v5 34/38] gpu: nova-core: Hopper/Blackwell: add GSP lockdown release polling John Hubbard
2026-02-21  2:09 ` [PATCH v5 35/38] gpu: nova-core: Hopper/Blackwell: new location for PCI config mirror John Hubbard
2026-02-21  2:09 ` [PATCH v5 36/38] gpu: nova-core: Hopper/Blackwell: integrate FSP boot path into boot() John Hubbard
2026-02-21  2:09 ` [PATCH v5 37/38] rust: sizes: add u64 variants of SZ_* constants John Hubbard
2026-02-21  2:09 ` [PATCH v5 38/38] gpu: nova-core: use SZ_*_U64 constants from kernel::sizes 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=20260221020952.412352-33-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=nouveau@lists.freedesktop.org \
    --cc=ojeda@kernel.org \
    --cc=rust-for-linux@vger.kernel.org \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox