gdrdrv_remap_gpu_mem:error -22, in remap_pfn_range()

Open
#199 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
25/100
Issue type
Bug
Clarity
Needs clarification
Activity status
Stale
Tech stack
c, linux

Research direction

Start by tracing gdrdrv_mmap and gdrdrv_remap_gpu_mem at the remap_pfn_range() call, using the logged non-contiguous page addresses and -22 return as the reproduction clue. Done should include a confirmed cause for the mapping failure and a documented validation path; the payload names no test or reproduction command.

Written by the indexing model from the issue text.

Description

bug
[14916.488532] gdrdrv:gdrdrv_pin_buffer:invoking nvidia_p2p_get_pages(va=0x7fba65a20000 len=262144 p2p_tok=0 va_tok=0)
[14916.489847] gdrdrv:gdrdrv_pin_buffer:page table entries: 4
[14916.489850] gdrdrv:gdrdrv_pin_buffer:page[0]=0x000003b000c20000
[14916.489852] gdrdrv:gdrdrv_pin_buffer:page[1]=0x000003b000c30000
[14916.489853] gdrdrv:gdrdrv_pin_buffer:page[2]=0x000003b000c40000
[14916.489854] gdrdrv:gdrdrv_pin_buffer:page[3]=0x000003b006050000
[14916.489863] gdrdrv:gdrdrv_mmap:mmap filp=0xffff9025aabe0600 vma=0xffff8fe965ef3290 vm_file=0xffff9025aabe0600 start=0x7fb9a5169000 size=262144 off=0x2240
[14916.489865] gdrdrv:gdrdrv_mmap:range start with p=0 vaddr=7fb9a5169000 page_paddr=3b000c20000
[14916.489866] gdrdrv:gdrdrv_mmap:non-contig p=3 prev_page_paddr=3b000c40000 cur_page_paddr=3b006050000
[14916.489868] gdrdrv:gdrdrv_mmap:mapping p=3 entries=3 offset=0 len=196608 vaddr=7fb9a5169000 paddr=3b000c20000 is_wcomb=1
[14916.489873] gdrdrv:gdrdrv_remap_gpu_mem:error -22,  in remap_pfn_range()
[14916.489875] gdrdrv:gdrdrv_mmap:error -22 in gdrdrv_remap_gpu_mem(vaddr=7fb9a5169000, len=196608
[15081.321727] gdrdrv:gdrdrv_pin_buffer:invoking nvidia_p2p_get_pages(va=0x7fba65a20000 len=196608 p2p_tok=0 va_tok=0)
Dominant language
C
Stars
1.4k
Forks
198
PR merge metrics
No merged PRs in 30d

Getting set up

This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from NVIDIA/gdrcopy

All issues in NVIDIA/gdrcopy

Similar issues

More C issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.