gpu: nova-core: Hopper/Blackwell: larger non-WPR heap

Hopper and Blackwell need a larger non-WPR heap than the 1 MiB that
earlier architectures use. Hopper and Blackwell GB10x need 2 MiB, while
Blackwell GB20x needs 2 MiB + 128 KiB. These sizes diverge by family,
so give Hopper and each Blackwell family its own framebuffer HAL and
select the non-WPR heap size per chipset family.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Eliot Courtney <ecourtney@nvidia.com>
Link: https://patch.msgid.link/20260602032111.224790-5-jhubbard@nvidia.com
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>

diff --git a/drivers/gpu/nova-core/fb.rs b/drivers/gpu/nova-core/fb.rs
index d7a4dc944131ed74ff9d79abc6be82624e340ce3..0aaee718c2c3311185c99dbf38c0999a64ac33e2 100644 (file)
--- a/drivers/gpu/nova-core/fb.rs
+++ b/drivers/gpu/nova-core/fb.rs
@@ -252,9 +252,8 @@ impl FbLayout {
         };
 
         let heap = {
-            const HEAP_SIZE: u64 = u64::SZ_1M;
-
-            FbRange(wpr2.start - HEAP_SIZE..wpr2.start)
+            let heap_size = u64::from(hal.non_wpr_heap_size());
+            FbRange(wpr2.start - heap_size..wpr2.start)
         };
 
         Ok(Self {

diff --git a/drivers/gpu/nova-core/fb/hal.rs b/drivers/gpu/nova-core/fb/hal.rs
index b45784ad5f2e38f035545e340bdb28acc7ee3eec..be9e75f990f012a711183157418622493131c899 100644 (file)
--- a/drivers/gpu/nova-core/fb/hal.rs
+++ b/drivers/gpu/nova-core/fb/hal.rs
@@ -14,6 +14,8 @@ use crate::{
 mod ga100;
 mod ga102;
 mod gb100;
+mod gb202;
+mod gh100;
 mod tu102;
 
 pub(crate) trait FbHal {
@@ -34,6 +36,9 @@ pub(crate) trait FbHal {
     /// Returns the amount of VRAM to reserve for the PMU.
     fn pmu_reserved_size(&self) -> u32;
 
+    /// Returns the non-WPR heap size for this chipset, in bytes.
+    fn non_wpr_heap_size(&self) -> u32;
+
     /// Returns the FRTS size, in bytes.
     fn frts_size(&self) -> u64;
 }
@@ -43,7 +48,9 @@ pub(super) fn fb_hal(chipset: Chipset) -> &'static dyn FbHal {
     match chipset.arch() {
         Architecture::Turing => tu102::TU102_HAL,
         Architecture::Ampere if chipset == Chipset::GA100 => ga100::GA100_HAL,
-        Architecture::Ampere | Architecture::Ada | Architecture::Hopper => ga102::GA102_HAL,
-        Architecture::BlackwellGB10x | Architecture::BlackwellGB20x => gb100::GB100_HAL,
+        Architecture::Ampere | Architecture::Ada => ga102::GA102_HAL,
+        Architecture::Hopper => gh100::GH100_HAL,
+        Architecture::BlackwellGB10x => gb100::GB100_HAL,
+        Architecture::BlackwellGB20x => gb202::GB202_HAL,
     }
 }

diff --git a/drivers/gpu/nova-core/fb/hal/ga100.rs b/drivers/gpu/nova-core/fb/hal/ga100.rs
index 0f5132aa9c31d9a3e6c06cc9ee19226a2c677640..af95f1bdd2735b309d0f387ff1e666b0e75ec05d 100644 (file)
--- a/drivers/gpu/nova-core/fb/hal/ga100.rs
+++ b/drivers/gpu/nova-core/fb/hal/ga100.rs
@@ -72,6 +72,10 @@ impl FbHal for Ga100 {
         super::tu102::pmu_reserved_size_tu102()
     }
 
+    fn non_wpr_heap_size(&self) -> u32 {
+        super::tu102::non_wpr_heap_size_tu102()
+    }
+
     // GA100 is a special case where its FRTS region exists, but is empty.  We
     // return a size of 0 because we still need to record where the region starts.
     fn frts_size(&self) -> u64 {

diff --git a/drivers/gpu/nova-core/fb/hal/ga102.rs b/drivers/gpu/nova-core/fb/hal/ga102.rs
index 17a2fef1ad44b5234f43b710a06e9288d4ab5dbe..e06dbb08349e56873fcbf560391a54848cd57560 100644 (file)
--- a/drivers/gpu/nova-core/fb/hal/ga102.rs
+++ b/drivers/gpu/nova-core/fb/hal/ga102.rs
@@ -41,6 +41,10 @@ impl FbHal for Ga102 {
         super::tu102::pmu_reserved_size_tu102()
     }
 
+    fn non_wpr_heap_size(&self) -> u32 {
+        super::tu102::non_wpr_heap_size_tu102()
+    }
+
     fn frts_size(&self) -> u64 {
         super::tu102::frts_size_tu102()
     }

diff --git a/drivers/gpu/nova-core/fb/hal/gb100.rs b/drivers/gpu/nova-core/fb/hal/gb100.rs
index c78027c26a9ec2634ef32d031a885ea04c21ab8e..8d63350abf8aa0d2d724ed2a0eebee5a5f516c31 100644 (file)
--- a/drivers/gpu/nova-core/fb/hal/gb100.rs
+++ b/drivers/gpu/nova-core/fb/hal/gb100.rs
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 
-//! Blackwell framebuffer HAL.
+//! Blackwell GB10x framebuffer HAL.
 
 use kernel::{
     prelude::*,
@@ -20,7 +20,7 @@ use crate::{
 
 struct Gb100;
 
-const fn pmu_reserved_size_gb100() -> u32 {
+pub(super) const fn pmu_reserved_size_gb100() -> u32 {
     usize_into_u32::<{ const_align_up(SZ_8M + SZ_16M + SZ_4K, Alignment::new::<SZ_128K>()).unwrap() }>(
     )
 }
@@ -48,6 +48,11 @@ impl FbHal for Gb100 {
         pmu_reserved_size_gb100()
     }
 
+    fn non_wpr_heap_size(&self) -> u32 {
+        // Non-WPR heap for GB10x (see Open RM: kgspGetNonWprHeapSize, GB100/GB102).
+        u32::SZ_2M
+    }
+
     fn frts_size(&self) -> u64 {
         super::tu102::frts_size_tu102()
     }

diff --git a/drivers/gpu/nova-core/fb/hal/gb202.rs b/drivers/gpu/nova-core/fb/hal/gb202.rs
new file mode 100644 (file)
index 0000000..542c1d7
--- /dev/null
+++ b/drivers/gpu/nova-core/fb/hal/gb202.rs
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+// SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+//! Blackwell GB20x framebuffer HAL.
+
+use kernel::{
+    prelude::*,
+    sizes::SizeConstants, //
+};
+
+use crate::{
+    driver::Bar0,
+    fb::hal::FbHal, //
+};
+
+struct Gb202;
+
+impl FbHal for Gb202 {
+    fn read_sysmem_flush_page(&self, bar: &Bar0) -> u64 {
+        super::ga100::read_sysmem_flush_page_ga100(bar)
+    }
+
+    fn write_sysmem_flush_page(&self, bar: &Bar0, addr: u64) -> Result {
+        super::ga100::write_sysmem_flush_page_ga100(bar, addr);
+
+        Ok(())
+    }
+
+    fn supports_display(&self, bar: &Bar0) -> bool {
+        super::ga100::display_enabled_ga100(bar)
+    }
+
+    fn vidmem_size(&self, bar: &Bar0) -> u64 {
+        super::ga102::vidmem_size_ga102(bar)
+    }
+
+    fn pmu_reserved_size(&self) -> u32 {
+        super::gb100::pmu_reserved_size_gb100()
+    }
+
+    fn non_wpr_heap_size(&self) -> u32 {
+        // Non-WPR heap for GB20x (see Open RM: kgspGetNonWprHeapSize, GB202+).
+        u32::SZ_2M + u32::SZ_128K
+    }
+
+    fn frts_size(&self) -> u64 {
+        super::tu102::frts_size_tu102()
+    }
+}
+
+const GB202: Gb202 = Gb202;
+pub(super) const GB202_HAL: &dyn FbHal = &GB202;

diff --git a/drivers/gpu/nova-core/fb/hal/gh100.rs b/drivers/gpu/nova-core/fb/hal/gh100.rs
new file mode 100644 (file)
index 0000000..8f79c72
--- /dev/null
+++ b/drivers/gpu/nova-core/fb/hal/gh100.rs
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+// SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+use kernel::{
+    prelude::*,
+    sizes::SizeConstants, //
+};
+
+use crate::{
+    driver::Bar0,
+    fb::hal::FbHal, //
+};
+
+struct Gh100;
+
+impl FbHal for Gh100 {
+    fn read_sysmem_flush_page(&self, bar: &Bar0) -> u64 {
+        super::ga100::read_sysmem_flush_page_ga100(bar)
+    }
+
+    fn write_sysmem_flush_page(&self, bar: &Bar0, addr: u64) -> Result {
+        super::ga100::write_sysmem_flush_page_ga100(bar, addr);
+
+        Ok(())
+    }
+
+    fn supports_display(&self, bar: &Bar0) -> bool {
+        super::ga100::display_enabled_ga100(bar)
+    }
+
+    fn vidmem_size(&self, bar: &Bar0) -> u64 {
+        super::ga102::vidmem_size_ga102(bar)
+    }
+
+    fn pmu_reserved_size(&self) -> u32 {
+        super::tu102::pmu_reserved_size_tu102()
+    }
+
+    fn non_wpr_heap_size(&self) -> u32 {
+        // Non-WPR heap for Hopper (see Open RM: kgspCalculateFbLayout_GH100).
+        u32::SZ_2M
+    }
+
+    fn frts_size(&self) -> u64 {
+        super::tu102::frts_size_tu102()
+    }
+}
+
+const GH100: Gh100 = Gh100;
+pub(super) const GH100_HAL: &dyn FbHal = &GH100;

diff --git a/drivers/gpu/nova-core/fb/hal/tu102.rs b/drivers/gpu/nova-core/fb/hal/tu102.rs
index 1755bbc278661b38d93b997cd551350f2217afcb..62d9357987f73c15938695f19cd1f0848a3b81ec 100644 (file)
--- a/drivers/gpu/nova-core/fb/hal/tu102.rs
+++ b/drivers/gpu/nova-core/fb/hal/tu102.rs
@@ -44,6 +44,10 @@ pub(super) const fn pmu_reserved_size_tu102() -> u32 {
     0
 }
 
+pub(super) const fn non_wpr_heap_size_tu102() -> u32 {
+    u32::SZ_1M
+}
+
 pub(super) const fn frts_size_tu102() -> u64 {
     u64::SZ_1M
 }
@@ -71,6 +75,10 @@ impl FbHal for Tu102 {
         pmu_reserved_size_tu102()
     }
 
+    fn non_wpr_heap_size(&self) -> u32 {
+        non_wpr_heap_size_tu102()
+    }
+
     fn frts_size(&self) -> u64 {
         frts_size_tu102()
     }