Sync develop from internal

.github/workflows/linting.yml

@@ -2,15 +2,68 @@ name: Linting
 
 on:
   push:
-    branches: 
-    - develop
-    - main
+    branches:
+      - develop
+      - main
   pull_request:
-    branches: 
-    - develop
-    - main
+    branches:
+      - develop
+      - main
+
+permissions:
+  contents: read
 
 jobs:
-  call-workflow-passing-data:
-    name: Documentation
-    uses: ROCm/rocm-docs-core/.github/workflows/linting.yml@develop
+  markdown:
+    name: Documentation / Markdown
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - name: Fetch config
+        shell: sh
+        run: |
+          test -f .markdownlint.yaml && echo "Using local config file" || curl --silent --show-error --fail --location https://raw.githubusercontent.com/ROCm/rocm-docs-core/develop/.markdownlint.yaml -O
+      - name: Set up Node.js
+        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
+        with:
+          node-version: 24
+      - name: Run markdownlint
+        run: npx --yes markdownlint-cli2 "**/*.md"
+
+  spelling:
+    name: Documentation / Spelling
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+      - name: Fetch config
+        shell: sh
+        run: |
+          curl --silent --show-error --fail --location https://raw.githubusercontent.com/ROCm/rocm-docs-core/develop/.github/workflows/yaml_merger.py -o .github/workflows/yaml_merger.py
+          curl --silent --show-error --fail --location https://raw.githubusercontent.com/ROCm/rocm-docs-core/develop/.spellcheck.yaml -O
+          curl --silent --show-error --fail --location https://raw.githubusercontent.com/ROCm/rocm-docs-core/develop/.wordlist.txt >> .wordlist.txt
+      - name: Check local spelling file
+        id: check_local_spelling
+        run: |
+          if [ -f .spellcheck.local.yaml ]; then
+            echo "check_result=true" >> $GITHUB_OUTPUT
+          else
+            echo "check_result=false" >> $GITHUB_OUTPUT
+          fi
+      - name: Merge local and main YAML files
+        if: steps.check_local_spelling.outputs.check_result == 'true'
+        shell: sh
+        run: |
+          python3 .github/workflows/yaml_merger.py .spellcheck.yaml .spellcheck.local.yaml .spellcheck.yaml
+      - name: Install spellcheck dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends aspell aspell-en
+          python3 -m pip install pyspelling==2.12.1
+      - name: Run spellcheck
+        run: python3 -m pyspelling --config .spellcheck.yaml
+      - name: On fail
+        if: failure()
+        run: |
+          echo "Please check for spelling mistakes or add them to '.wordlist.txt' in either the root of this project or in rocm-docs-core."

.wordlist.txt

@@ -6,6 +6,7 @@ ACS
 AccVGPR
 AccVGPRs
 AER
+AIS
 allreduce
 ALU
 AMD
@@ -20,6 +21,7 @@ APBDIS
 APIC
 APIs
 APU
+APUs
 ASIC
 ASICs
 ASan
@@ -114,6 +116,7 @@ EPYC
 ESXi
 EoS
 FBGEMM
+FCLK
 FFT
 FFTs
 FFmpeg
@@ -136,6 +139,7 @@ GDB
 GDDR
 GDR
 GDS
+GPUDirect
 GEMM
 GEMMs
 GFortran
@@ -144,6 +148,7 @@ GIM
 GL
 GLXT
 Gloo
+GMC
 GMI
 GPG
 GPR
@@ -157,6 +162,7 @@ GenZ
 GitHub
 Gitpod
 HBM
+HipFile
 HCA
 HGX
 HIPCC
@@ -221,6 +227,7 @@ LLVM
 LM
 LSAN
 LSan
+LSDMA
 LTS
 LoRA
 MCP
@@ -235,6 +242,7 @@ MIOpen's
 MIVisionX
 MLM
 MMA
+MMHUB
 MMIO
 MMIOH
 MMU
@@ -276,6 +284,10 @@ NVCC
 NVIDIA
 NVPTX
 NaN
+NFS
+NFSoRDMA
+NVMe
+NVMeoF
 Nano
 Navi
 Noncoherently
@@ -306,6 +318,7 @@ OpenXLA
 Oversubscription
 PagedAttention
 Pallas
+PASID
 PCC
 PCI
 PCIe
@@ -317,6 +330,7 @@ PLDM
 POR
 PRNG
 PRs
+PSP
 PaLM
 Pageable
 PeerDirect
@@ -359,6 +373,7 @@ ROCmValidationSuite
 ROCprofiler
 ROCr
 RPP
+RSL
 RST
 RW
 Radeon
@@ -389,6 +404,7 @@ SLES
 SMEM
 SMI
 SMT
+SMU
 SPI
 SQs
 SRAM
@@ -448,6 +464,7 @@ UTCL
 UTIL
 Uncached
 Unittests
+UniRAS
 Unhandled
 VALU
 VBIOS
@@ -571,6 +588,7 @@ detections
 dev
 devicelibs
 devsel
+dGPU
 dimensionality
 disambiguates
 distro
@@ -631,6 +649,7 @@ hlist
 hotspotting
 hpc
 hpp
+html
 hsa
 hsakmt
 hyperparameter
@@ -681,13 +700,15 @@ mkdir
 mlirmiopen
 mtypes
 mutex
+myst
 mvffr
 namespace
 namespaces
 nanoGPT
 num
 numref
 ocl
+oF
 ol
 opencl
 opencv
@@ -811,11 +832,13 @@ subfolder
 subfolders
 submodule
 submodules
+suboptimal
 supercomputing
 symlink
 symlinks
 sys
 td
+teardown
 tensorfloat
 th
 tokenization
@@ -904,6 +927,7 @@ amd
 amdsmi
 celerator
 chiplets
+vLLM
 vllm
 misconfigurations
 integrators
@@ -918,4 +942,5 @@ addressability
 datacenter
 programmability
 uptime
+userq
 TPX

docs/compatibility/compatibility-matrix.rst

@@ -6,17 +6,17 @@
 Compatibility matrix
 **************************************************************************************
 
-The AMD GPU Driver (amdgpu) 30.30.4 is compatible with ROCm 7.2.x, 7.1.x, 7.0.x, 6.4.x, and 6.3.x. For more information, see `AMD GPU Driver (amdgpu) support matrix
-<https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`__.
+The AMD GPU Driver (amdgpu) 31.40.0 is compatible with ROCm 7.14.0 and Radeon™ Software for Linux (RSL) 26.13. For more information, see `ROCm 7.14.0 compatibility matrix
+<https://rocm.docs.amd.com/en/docs-7.14.0/compatibility/compatibility-matrix.html>`__.
 
-======================================
+====================================
 Operating system and kernel version
-======================================
+====================================
 
-See `Supported operating systems <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html#supported-operating-systems>`_ for ROCm supported operating systems and their kernel versions.
+See `Operating system support <https://rocm.docs.amd.com/en/docs-7.14.0/about/release-notes.html#operating-system-support>`_ for ROCm supported operating systems and their kernel versions.
 
-=============
+============
 GPU support
-=============
+============
 
-See `Supported GPUs <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html#supported-gpus>`_ for the list of supported AMD Instinct™, Radeon™ PRO, and Radeon GPUs.
+See `Hardware support <https://rocm.docs.amd.com/en/docs-7.14.0/about/release-notes.html#amd-hardware-support>`_ for the list of supported AMD Instinct™, Radeon™ PRO, Radeon, and Ryzen™ AI GPUs.

docs/conf.py

@@ -7,22 +7,22 @@
     html_context["READTHEDOCS"] = True
 project = "AMD GPU Driver (amdgpu)"
 
-version = "30.30.4"
-rocm_version = '7.2.4'
-rocm_directory_version = '7.2.4' # in 6.0 rocm was located in /opt/rocm-6.0.0
-amdgpu_version = '30.30.4' # directory in https://repo.radeon.com/rocm/apt/ and https://repo.radeon.com/amdgpu-install/
-amdgpu_url_version = '30.30.4'
+version = "31.40.0"
+rocm_version = '7.14'
+rocm_directory_version = '7.14.0' # in 6.0 rocm was located in /opt/rocm-6.0.0
+amdgpu_version = '31.40' # directory in https://repo.radeon.com/rocm/apt/ and https://repo.radeon.com/amdgpu-install/
+amdgpu_url_version = '31.40'
 release = version
 html_title = f"AMD GPU Driver (amdgpu) {version}"
 author = "Advanced Micro Devices, Inc."
 copyright = "Copyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved."
 
 # Supported linux version numbers
-ubuntu_version_numbers = [('24.04', 'noble'), ('22.04', 'jammy')]
+ubuntu_version_numbers = [('26.04', 'resolute'), ('24.04', 'noble'), ('22.04', 'jammy')]
 debian_version_numbers = [('13', 'noble'), ('12', 'jammy')]
 rhel_release_version_numbers = ['10', '9', '8']
-rhel_version_numbers = ['10.1', '10.0', '9.7', '9.6', '9.4', '8.10']
-sles_version_numbers = ['15.7']
+rhel_version_numbers = ['10.2', '10.0', '9.8', '9.6', '9.4', '8.10']
+sles_version_numbers = ['16.0', '15.7']
 ol_release_version_numbers = ['10', '9', '8']
 ol_version_numbers = ['10.1', '9.7', '8.10']
 rl_version_numbers = ['9.7']
@@ -43,7 +43,6 @@
 html_theme = "rocm_docs_theme"
 html_theme_options = {
     "flavor": "amdgpu",
-    "announcement": f"<a id='rocm-banner' href='https://instinct.docs.amd.com/projects/amdgpu-docs/en/31.30.0-preview/'>AMD GPU Driver 31.30.0</a> is a technology preview intended for use only with <a id='rocm-banner' href='https://rocm.docs.amd.com/en/7.13.0-preview/index.html'>AMD ROCm 7.13.0 technology preview</a>. For production use, continue to use AMD GPU Driver {version} documentation.",
     "link_main_doc": True,
     # Add any additional theme options here
 }
@@ -60,7 +59,6 @@
 
 # Add the following replacements to every RST file.
 rst_prolog = f"""
-.. |version| replace:: {version}
 .. |rocm_version| replace:: {rocm_version}
 .. |amdgpu_version| replace:: {amdgpu_version}
 .. |amdgpu_url_version| replace:: {amdgpu_url_version}

docs/documentation/release-notes.md

@@ -1,13 +1,65 @@
-# AMD GPU Driver (amdgpu) 30.30.4 release notes
+# AMD GPU Driver (amdgpu) 31.40.0 release notes
 
-The release notes provide release highlights since the previous AMD GPU Driver release (30.30.3).
+The release notes provide release highlights and resolved issues since the previous AMD GPU Driver release (31.30.0, a preview release).
 
 ## Release highlights
 
-Added support for ROCm 7.2.4.
+The AMD GPU Driver 31.40.0 builds on 31.30.0 with a wide range of enhancements in compute performance, power management, and overall reliability. It is compatible with ROCm 7.14.0 and Radeon™ Software for Linux (RSL) 26.13.
 
-## Operating system and hardware support changes
-
-This release doesn’t introduce operating system or hardware support changes.
+This release introduces more resilient handling of AI and compute workloads, expanded monitoring capabilities, and numerous stability improvements to reduce hangs, crashes, and memory-related issues. It also includes targeted improvements for Instinct MI300-series platforms and newer compute GPUs.
 
 For compatibility between AMD GPU Driver, ROCm, GPUs, and operating systems, see the [Compatibility matrix](../compatibility/compatibility-matrix.rst).
+
+The following are notable new features and improvements in AMD GPU Driver 31.40.0.
+
+### Compute and Instinct improvements
+
+- **Improved compute trap-handler memory placement:** Compute trap-handler data is now stored in GPU device memory instead of system memory on supported Instinct platforms. This enhancement improves reliability for AI and HPC workloads that depend on stable compute error handling.
+
+- **Finer-grained queue recovery:** Added compute user queue reset and pipe reset for AMD Radeon™ RX 7000 and RX 9000 Series GPUs. This enables recovery from compute-related faults without requiring a full GPU reset, improving overall stability and fault tolerance.
+
+- **Enhanced user-mode queue handling:** Additional validation, hang detection, and reset logic for user-mode queues reduces the risk of stalled AI/ML jobs and prevents resource leaks under heavy submissions.
+
+- **Expanded HBM queue descriptor support:** Optimized placement and management of compute queue metadata on high-memory Instinct platforms.
+
+- **AMD Infinity Storage (AIS) enablement:** Introduces AMD Infinity Storage (AIS) enablement together with HipFile support, enabling direct data transfers between AMD GPUs and storage. AIS allows data to move directly between GPU VRAM and storage devices, including local NVMe, NVMe-oF RDMA, and NFSoRDMA, without staging data through host memory and delivers high-bandwidth, low-overhead storage I/O for GPU compute workloads.
+
+### Power, thermal, and telemetry
+
+- **SMU 15.0.5 support:** Introduces updated power management features for upcoming platforms.
+
+- **Enhanced SMU v15 metrics:** Adds support for monitoring memory temperature, partition-level metrics, and thermal alerts, offering improved data-center monitoring and diagnostics capabilities.
+
+- **Improved driver unload on APU platforms:** Refines power management processes when the driver is removed or during system shutdown on SMU v15 APUs.
+
+### Reliability, serviceability, and RAS
+
+- **Enhanced UniRAS and bad-page management:** Adds EEPROM-backed reliability data, poison-error handling, and improved bad-page tracking, enabling easier serviceability and diagnostics.
+
+- **System stability improvements:** Implements extensive memory safety, locking, and validation enhancements across device setup, GPU memory management, user queues, and error-reporting paths.
+
+## Resolved issues
+
+The following previously known issues have been resolved in this release:
+
+### Driver security
+
+- Resolved multiple memory safety vulnerabilities, including null-pointer access, use-after-free, buffer overflows, and out-of-bounds access, which could lead to system instability under fault or stress conditions.
+
+- Resolved incorrect video memory mapping behavior on systems using non-4 KB memory page sizes.
+
+- Resolved issues with user-mode queue creation, waiting, and path reset operations that could cause system hangs or resource leaks.
+
+- Resolved module unload issues to ensure pending cleanup processes complete reliably when the driver is removed.
+
+### Compute and power
+
+- Resolved issues with compute scheduling and reset paths on newer GPU generations, including MES queue removal and pipe reset handling.
+
+- Resolved power-management reporting and overdrive table handling on select SMU v14/v15 platforms, addressing memory leaks and incorrect limit calculations.
+
+- Resolved incorrect SDMA queue counter reporting affected platforms.
+
+### Reliability and RAS
+
+Resolved RAS reservation and EEPROM synchronization issues that caused incorrect reporting of available bad-page capacity.