ghsa-4gg5-g35c-mghx
Vulnerability from github
In the Linux kernel, the following vulnerability has been resolved:
LoongArch: Define the __io_aw() hook as mmiowb()
Commit fb24ea52f78e0d595852e ("drivers: Remove explicit invocations of mmiowb()") remove all mmiowb() in drivers, but it says:
"NOTE: mmiowb() has only ever guaranteed ordering in conjunction with spin_unlock(). However, pairing each mmiowb() removal in this patch with the corresponding call to spin_unlock() is not at all trivial, so there is a small chance that this change may regress any drivers incorrectly relying on mmiowb() to order MMIO writes between CPUs using lock-free synchronisation."
The mmio in radeon_ring_commit() is protected by a mutex rather than a spinlock, but in the mutex fastpath it behaves similar to spinlock. We can add mmiowb() calls in the radeon driver but the maintainer says he doesn't like such a workaround, and radeon is not the only example of mutex protected mmio.
So we should extend the mmiowb tracking system from spinlock to mutex, and maybe other locking primitives. This is not easy and error prone, so we solve it in the architectural code, by simply defining the __io_aw() hook as mmiowb(). And we no longer need to override queued_spin_unlock() so use the generic definition.
Without this, we get such an error when run 'glxgears' on weak ordering architectures such as LoongArch:
radeon 0000:04:00.0: ring 0 stalled for more than 10324msec radeon 0000:04:00.0: ring 3 stalled for more than 10240msec radeon 0000:04:00.0: GPU lockup (current fence id 0x000000000001f412 last fence id 0x000000000001f414 on ring 3) radeon 0000:04:00.0: GPU lockup (current fence id 0x000000000000f940 last fence id 0x000000000000f941 on ring 0) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] ERROR Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] ERROR Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] ERROR Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] ERROR Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] ERROR Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] ERROR Couldn't update BO_VA (-35) radeon 0000:04:00.0: scheduling IB failed (-35). [drm:radeon_gem_va_ioctl [radeon]] ERROR Couldn't update BO_VA (-35)
{
"affected": [],
"aliases": [
"CVE-2024-35818"
],
"database_specific": {
"cwe_ids": [],
"github_reviewed": false,
"github_reviewed_at": null,
"nvd_published_at": "2024-05-17T14:15:16Z",
"severity": null
},
"details": "In the Linux kernel, the following vulnerability has been resolved:\n\nLoongArch: Define the __io_aw() hook as mmiowb()\n\nCommit fb24ea52f78e0d595852e (\"drivers: Remove explicit invocations of\nmmiowb()\") remove all mmiowb() in drivers, but it says:\n\n\"NOTE: mmiowb() has only ever guaranteed ordering in conjunction with\nspin_unlock(). However, pairing each mmiowb() removal in this patch with\nthe corresponding call to spin_unlock() is not at all trivial, so there\nis a small chance that this change may regress any drivers incorrectly\nrelying on mmiowb() to order MMIO writes between CPUs using lock-free\nsynchronisation.\"\n\nThe mmio in radeon_ring_commit() is protected by a mutex rather than a\nspinlock, but in the mutex fastpath it behaves similar to spinlock. We\ncan add mmiowb() calls in the radeon driver but the maintainer says he\ndoesn\u0027t like such a workaround, and radeon is not the only example of\nmutex protected mmio.\n\nSo we should extend the mmiowb tracking system from spinlock to mutex,\nand maybe other locking primitives. This is not easy and error prone, so\nwe solve it in the architectural code, by simply defining the __io_aw()\nhook as mmiowb(). And we no longer need to override queued_spin_unlock()\nso use the generic definition.\n\nWithout this, we get such an error when run \u0027glxgears\u0027 on weak ordering\narchitectures such as LoongArch:\n\nradeon 0000:04:00.0: ring 0 stalled for more than 10324msec\nradeon 0000:04:00.0: ring 3 stalled for more than 10240msec\nradeon 0000:04:00.0: GPU lockup (current fence id 0x000000000001f412 last fence id 0x000000000001f414 on ring 3)\nradeon 0000:04:00.0: GPU lockup (current fence id 0x000000000000f940 last fence id 0x000000000000f941 on ring 0)\nradeon 0000:04:00.0: scheduling IB failed (-35).\n[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn\u0027t update BO_VA (-35)\nradeon 0000:04:00.0: scheduling IB failed (-35).\n[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn\u0027t update BO_VA (-35)\nradeon 0000:04:00.0: scheduling IB failed (-35).\n[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn\u0027t update BO_VA (-35)\nradeon 0000:04:00.0: scheduling IB failed (-35).\n[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn\u0027t update BO_VA (-35)\nradeon 0000:04:00.0: scheduling IB failed (-35).\n[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn\u0027t update BO_VA (-35)\nradeon 0000:04:00.0: scheduling IB failed (-35).\n[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn\u0027t update BO_VA (-35)\nradeon 0000:04:00.0: scheduling IB failed (-35).\n[drm:radeon_gem_va_ioctl [radeon]] *ERROR* Couldn\u0027t update BO_VA (-35)",
"id": "GHSA-4gg5-g35c-mghx",
"modified": "2024-05-17T15:31:10Z",
"published": "2024-05-17T15:31:10Z",
"references": [
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2024-35818"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/0b61a7dc6712b78799b3949997e8a5e94db5c4b0"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/97cd43ba824aec764f5ea2790d0c0a318f885167"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/9adec248bba33b1503252caf8e59d81febfc5ceb"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/9c68ece8b2a5c5ff9b2fcaea923dd73efeb174cd"
},
{
"type": "WEB",
"url": "https://git.kernel.org/stable/c/d7d7c6cdea875be3b241d7d39873bb431db7154d"
}
],
"schema_version": "1.4.0",
"severity": []
}