Title: cuda.core: a fast-path VMM grow leaves its extension unfreeable · Issue #2887 · NVIDIA/cuda-python · GitHub
Open Graph Title: cuda.core: a fast-path VMM grow leaves its extension unfreeable · Issue #2887 · NVIDIA/cuda-python
X Title: cuda.core: a fast-path VMM grow leaves its extension unfreeable · Issue #2887 · NVIDIA/cuda-python
Description: Summary _grow_allocation_fast_path maps a new chunk into a second, adjacent VA reservation and updates buf._size in place. The Buffer's deleter captured the original size when the buffer was created, so close() calls deallocate(ptr, orig...
Open Graph Description: Summary _grow_allocation_fast_path maps a new chunk into a second, adjacent VA reservation and updates buf._size in place. The Buffer's deleter captured the original size when the buffer was create...
X Description: Summary _grow_allocation_fast_path maps a new chunk into a second, adjacent VA reservation and updates buf._size in place. The Buffer's deleter captured the original size when the buffer was cr...
Opengraph URL: https://github.com/NVIDIA/cuda-python/issues/2887
X: @github
Domain: github.com
{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"cuda.core: a fast-path VMM grow leaves its extension unfreeable","articleBody":"## Summary\n\n`_grow_allocation_fast_path` maps a new chunk into a second, adjacent VA reservation and updates `buf._size` in place. The Buffer's deleter captured the original size when the buffer was created, so `close()` calls `deallocate(ptr, original_size)` and frees only the first reservation. The extension's reservation, mapping, and physical memory leak with no warning.\n\nNo `deallocate(ptr, size)` call can fix this: `cuMemAddressFree` frees a reservation only when `ptr` and `size` match exactly one reservation, so a range that spans two reservations cannot be freed in one call. The buffer needs to own each reservation and mapping it consists of.\n\n## Status\n\nToday the fast path is unreachable (#2388 defect 2). #2237 and #2407 make it live and would expose this leak, so they should wait for this fix. The existing fast-path test mocks the driver and cannot catch it.\n\nRefs: #2388, #2237, #2407, #2882.\n","author":{"url":"https://github.com/Andy-Jost","@type":"Person","name":"Andy-Jost"},"datePublished":"2026-09-16T21:30:35Z","url":"https://github.com/NVIDIA/cuda-python/issues/2887"}
| react-profiling | 0 |
| react-import-map | react,react-dom,react-dom/client,react-dom/profiling,react-is,react-reconciler,react/compiler-runtime,react/jsx-dev-runtime,react/jsx-runtime,scheduler@d5750093facf |
| route-pattern | /_view_fragments/issues/show/:user_id/:repository/:id/issue_layout(.:format) |
| route-controller | voltron_issues_fragments |
| route-action | issue_layout |
| fetch-nonce | v2:8f83769d-0520-e205-51b0-d5b0382576b2 |
| current-catalog-service-hash | 81bb79d38c15960b92d99bca9288a9108c7a47b18f2423d0f6438c5b7bcd2114 |
| request-id | 8E56:8ECA6:2F8E37:41EB0B:6AF836B1 |
| html-safe-nonce | 26fa482a4afd6a1899534a633645e0a14e887975d0382095cfdb9acf2a6f5543 |
| visitor-payload | eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiI4RTU2OjhFQ0E2OjJGOEUzNzo0MUVCMEI6NkFGODM2QjEiLCJ2aXNpdG9yX2lkIjoiNzcwMzU0NjM0NzEyMjA3OTQwOSIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9 |
| visitor-hmac | 0770d0ad90c3a75267f4b9074bfb1a4f603de00d68b69100da64d3b3f83da7c0 |
| hovercard-subject-tag | issue:5480150992 |
| github-keyboard-shortcuts | repository,issues,copilot |
| google-site-verification | Apib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I |
| octolytics-url | https://collector.github.com/github/collect |
| analytics-location | / |
| fb:app_id | 1401488693436528 |
| apple-itunes-app | app-id=1477376905, app-argument=https://github.com/_view_fragments/issues/show/NVIDIA/cuda-python/2887/issue_layout |
| twitter:image | https://opengraph.githubassets.com/ecadfaa16e74cf83dd5e6eb73150f7f7c45c45fab73ed12d517bd29305bf16dd/NVIDIA/cuda-python/issues/2887 |
| twitter:card | summary_large_image |
| og:image | https://opengraph.githubassets.com/ecadfaa16e74cf83dd5e6eb73150f7f7c45c45fab73ed12d517bd29305bf16dd/NVIDIA/cuda-python/issues/2887 |
| og:image:alt | Summary _grow_allocation_fast_path maps a new chunk into a second, adjacent VA reservation and updates buf._size in place. The Buffer's deleter captured the original size when the buffer was create... |
| og:image:width | 1200 |
| og:image:height | 600 |
| og:site_name | GitHub |
| og:type | object |
| og:author:username | Andy-Jost |
| hostname | github.com |
| expected-hostname | github.com |
| None | 5713ecd83001b2f55c3509fb7a292bf7d66d0f167c7ae87a9f7eaec5a52bf8db |
| turbo-cache-control | no-preview |
| go-import | github.com/NVIDIA/cuda-python git https://github.com/NVIDIA/cuda-python.git |
| octolytics-dimension-user_id | 1728152 |
| octolytics-dimension-user_login | NVIDIA |
| octolytics-dimension-repository_id | 381173759 |
| octolytics-dimension-repository_nwo | NVIDIA/cuda-python |
| octolytics-dimension-repository_public | true |
| octolytics-dimension-repository_is_fork | false |
| octolytics-dimension-repository_network_root_id | 381173759 |
| octolytics-dimension-repository_network_root_nwo | NVIDIA/cuda-python |
| turbo-body-classes | logged-out env-production page-responsive |
| disable-turbo | false |
| browser-stats-url | https://api.github.com/_private/browser/stats |
| browser-errors-url | https://api.github.com/_private/browser/errors |
| release | 653be32ff5c755082a4db662491bfbbcfc9112c1 |
| ui-target | full |
| theme-color | #1e2327 |
| color-scheme | light dark |
| react-app-name | issues |
Links:
Viewport: width=device-width