[PATCH v9 01/31] gpu: nova-core: Hopper/Blackwell: basic GPU identification

John Hubbard posted 31 patches 1 week ago
[PATCH v9 01/31] gpu: nova-core: Hopper/Blackwell: basic GPU identification
Posted by John Hubbard 1 week ago
Hopper (GH100) and Blackwell identification, including ELF
.fwsignature_* items.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 drivers/gpu/nova-core/falcon/hal.rs   |  3 ++-
 drivers/gpu/nova-core/fb/hal.rs       |  5 ++---
 drivers/gpu/nova-core/firmware/gsp.rs |  6 ++++--
 drivers/gpu/nova-core/gpu.rs          | 21 +++++++++++++++++++++
 4 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/nova-core/falcon/hal.rs b/drivers/gpu/nova-core/falcon/hal.rs
index a7e5ea8d0272..c7f12f2a7a35 100644
--- a/drivers/gpu/nova-core/falcon/hal.rs
+++ b/drivers/gpu/nova-core/falcon/hal.rs
@@ -80,7 +80,8 @@ pub(super) fn falcon_hal<E: FalconEngine + 'static>(
         TU102 | TU104 | TU106 | TU116 | TU117 => {
             KBox::new(tu102::Tu102::<E>::new(), GFP_KERNEL)? as KBox<dyn FalconHal<E>>
         }
-        GA102 | GA103 | GA104 | GA106 | GA107 | AD102 | AD103 | AD104 | AD106 | AD107 => {
+        GA102 | GA103 | GA104 | GA106 | GA107 | AD102 | AD103 | AD104 | AD106 | AD107 | GH100
+        | GB100 | GB102 | GB202 | GB203 | GB205 | GB206 | GB207 => {
             KBox::new(ga102::Ga102::<E>::new(), GFP_KERNEL)? as KBox<dyn FalconHal<E>>
         }
         _ => return Err(ENOTSUPP),
diff --git a/drivers/gpu/nova-core/fb/hal.rs b/drivers/gpu/nova-core/fb/hal.rs
index aba0abd8ee00..e709affaa7e8 100644
--- a/drivers/gpu/nova-core/fb/hal.rs
+++ b/drivers/gpu/nova-core/fb/hal.rs
@@ -34,8 +34,7 @@ pub(super) fn fb_hal(chipset: Chipset) -> &'static dyn FbHal {
     match chipset {
         TU102 | TU104 | TU106 | TU117 | TU116 => tu102::TU102_HAL,
         GA100 => ga100::GA100_HAL,
-        GA102 | GA103 | GA104 | GA106 | GA107 | AD102 | AD103 | AD104 | AD106 | AD107 => {
-            ga102::GA102_HAL
-        }
+        GA102 | GA103 | GA104 | GA106 | GA107 | AD102 | AD103 | AD104 | AD106 | AD107 | GH100
+        | GB100 | GB102 | GB202 | GB203 | GB205 | GB206 | GB207 => ga102::GA102_HAL,
     }
 }
diff --git a/drivers/gpu/nova-core/firmware/gsp.rs b/drivers/gpu/nova-core/firmware/gsp.rs
index 9488a626352f..2bbea1db0238 100644
--- a/drivers/gpu/nova-core/firmware/gsp.rs
+++ b/drivers/gpu/nova-core/firmware/gsp.rs
@@ -213,8 +213,7 @@ pub(crate) fn new<'a>(
                 signatures: {
                     let sigs_section = match chipset.arch() {
                         Architecture::Turing
-                            if matches!(chipset, Chipset::TU116 | Chipset::TU117) =>
-                        {
+                            if matches!(chipset, Chipset::TU116 | Chipset::TU117) => {
                             ".fwsignature_tu11x"
                         }
                         Architecture::Turing => ".fwsignature_tu10x",
@@ -222,6 +221,9 @@ pub(crate) fn new<'a>(
                         Architecture::Ampere if chipset == Chipset::GA100 => ".fwsignature_tu10x",
                         Architecture::Ampere => ".fwsignature_ga10x",
                         Architecture::Ada => ".fwsignature_ad10x",
+                        Architecture::Hopper => ".fwsignature_gh10x",
+                        Architecture::BlackwellGB10x => ".fwsignature_gb10x",
+                        Architecture::BlackwellGB20x => ".fwsignature_gb20x",
                     };
 
                     elf::elf64_section(firmware.data(), sigs_section)
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 8579d632e717..0c68bca7bf65 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -83,12 +83,22 @@ fn try_from(value: u32) -> Result<Self, Self::Error> {
     GA104 = 0x174,
     GA106 = 0x176,
     GA107 = 0x177,
+    // Hopper
+    GH100 = 0x180,
     // Ada
     AD102 = 0x192,
     AD103 = 0x193,
     AD104 = 0x194,
     AD106 = 0x196,
     AD107 = 0x197,
+    // Blackwell
+    GB100 = 0x1a0,
+    GB102 = 0x1a2,
+    GB202 = 0x1b2,
+    GB203 = 0x1b3,
+    GB205 = 0x1b5,
+    GB206 = 0x1b6,
+    GB207 = 0x1b7,
 });
 
 impl Chipset {
@@ -100,9 +110,14 @@ pub(crate) const fn arch(self) -> Architecture {
             Self::GA100 | Self::GA102 | Self::GA103 | Self::GA104 | Self::GA106 | Self::GA107 => {
                 Architecture::Ampere
             }
+            Self::GH100 => Architecture::Hopper,
             Self::AD102 | Self::AD103 | Self::AD104 | Self::AD106 | Self::AD107 => {
                 Architecture::Ada
             }
+            Self::GB100 | Self::GB102 => Architecture::BlackwellGB10x,
+            Self::GB202 | Self::GB203 | Self::GB205 | Self::GB206 | Self::GB207 => {
+                Architecture::BlackwellGB20x
+            }
         }
     }
 
@@ -139,7 +154,10 @@ pub(crate) enum Architecture {
     #[default]
     Turing = 0x16,
     Ampere = 0x17,
+    Hopper = 0x18,
     Ada = 0x19,
+    BlackwellGB10x = 0x1a,
+    BlackwellGB20x = 0x1b,
 }
 
 impl TryFrom<u8> for Architecture {
@@ -149,7 +167,10 @@ fn try_from(value: u8) -> Result<Self> {
         match value {
             0x16 => Ok(Self::Turing),
             0x17 => Ok(Self::Ampere),
+            0x18 => Ok(Self::Hopper),
             0x19 => Ok(Self::Ada),
+            0x1a => Ok(Self::BlackwellGB10x),
+            0x1b => Ok(Self::BlackwellGB20x),
             _ => Err(ENODEV),
         }
     }
-- 
2.53.0