CVE-2026-93237 (GCVE-0-2026-93237)
Vulnerability from cvelistv5
Published
2026-09-24 15:33
Modified
2026-10-19 09:07
Summary
In the Linux kernel, the following vulnerability has been resolved: LoongArch: Add DIRECT_MAP_PHYSMEM_END definition get_free_mem_region() and mhp_get_pluggable_range() bound their search to DIRECT_MAP_PHYSMEM_END. LoongArch does not define it, so the fallback in include/linux/mm.h applies: under CONFIG_SPARSEMEM_VMEMMAP it is (1ULL << MAX_PHYSMEM_BITS) - 1, a compile-time constant that does not adapt to the CPU's physical address space bits (cpu_pabits, probed from CPUCFG1). The vmemmap window only covers physical space below 2^(cpu_pabits+1) (i.e. VMEMMAP_SIZE), so on CPUs with fewer physical address bits than MAX_PHYSMEM_BITS the fallback allows get_free_mem_region() to return a ZONE_DEVICE region outside the vmemmap window; vmemmap_populate() then wraps the memmap range around and maps it into low memory, silently corrupting the page tables. The same search also picked the top-of- address-space region that crashed memmap_init_zone_device() with amdkfd on Loongson-3C6000 in 6.16 [1]; the commit 2969b42c8f99 ("LoongArch/mm: align vmemmap to maximal folio size") keeps that region in bounds on current Loongson-3C6000 configs, but CPUs with smaller cpu_pabits (e.g. the Loongson-2K series) are still affected. Define DIRECT_MAP_PHYSMEM_END as the vmemmap-covered physical range, (1ULL << (cpu_pabits + 1)) - 1, capped at (1ULL << MAX_PHYSMEM_BITS) - 1 under CONFIG_SPARSEMEM, similar to the commit f3336b48cf9d ("riscv: mm: Define DIRECT_MAP_PHYSMEM_END"). [1] https://lore.kernel.org/amd-gfx/20250814032153.227285-1-jeffbai@aosc.io/
Impacted products
Vendor Product Version
Linux Linux Version: 7b09f5af01ede480cbe7abcb281cf17550a46ff5
Version: 7b09f5af01ede480cbe7abcb281cf17550a46ff5
Version: 7b09f5af01ede480cbe7abcb281cf17550a46ff5
Create a notification for this product.
Show details on NVD website


{
  "containers": {
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "product": "Linux",
          "programFiles": [
            "arch/loongarch/include/asm/pgtable.h"
          ],
          "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git",
          "vendor": "Linux",
          "versions": [
            {
              "lessThan": "ab275a23b4d9f04ca6c2f5f6a3246194e045a761",
              "status": "affected",
              "version": "7b09f5af01ede480cbe7abcb281cf17550a46ff5",
              "versionType": "git"
            },
            {
              "lessThan": "55e18311c705cceef6c34d522ea387b1f0069bab",
              "status": "affected",
              "version": "7b09f5af01ede480cbe7abcb281cf17550a46ff5",
              "versionType": "git"
            },
            {
              "lessThan": "2677f97a67fdbc62a82ce1faa67791f54451d36f",
              "status": "affected",
              "version": "7b09f5af01ede480cbe7abcb281cf17550a46ff5",
              "versionType": "git"
            }
          ]
        },
        {
          "defaultStatus": "affected",
          "product": "Linux",
          "programFiles": [
            "arch/loongarch/include/asm/pgtable.h"
          ],
          "repo": "https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git",
          "vendor": "Linux",
          "versions": [
            {
              "status": "affected",
              "version": "6.2"
            },
            {
              "lessThan": "6.2",
              "status": "unaffected",
              "version": "0",
              "versionType": "semver"
            },
            {
              "lessThanOrEqual": "6.18.*",
              "status": "unaffected",
              "version": "6.18.51",
              "versionType": "semver"
            },
            {
              "lessThanOrEqual": "7.2.*",
              "status": "unaffected",
              "version": "7.2.5",
              "versionType": "semver"
            },
            {
              "lessThanOrEqual": "*",
              "status": "unaffected",
              "version": "7.3",
              "versionType": "original_commit_for_fix"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "6.18.51",
                  "versionStartIncluding": "6.2",
                  "vulnerable": true
                },
                {
                  "criteria": "cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "7.2.5",
                  "versionStartIncluding": "6.2",
                  "vulnerable": true
                },
                {
                  "criteria": "cpe:2.3:o:linux:linux_kernel:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "7.3",
                  "versionStartIncluding": "6.2",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "In the Linux kernel, the following vulnerability has been resolved:\n\nLoongArch: Add DIRECT_MAP_PHYSMEM_END definition\n\nget_free_mem_region() and mhp_get_pluggable_range() bound their search\nto DIRECT_MAP_PHYSMEM_END. LoongArch does not define it, so the fallback\nin include/linux/mm.h applies: under CONFIG_SPARSEMEM_VMEMMAP it is\n(1ULL \u003c\u003c MAX_PHYSMEM_BITS) - 1, a compile-time constant that does not\nadapt to the CPU\u0027s physical address space bits (cpu_pabits, probed from\nCPUCFG1).\n\nThe vmemmap window only covers physical space below 2^(cpu_pabits+1)\n(i.e. VMEMMAP_SIZE), so on CPUs with fewer physical address bits than\nMAX_PHYSMEM_BITS the fallback allows get_free_mem_region() to return\na ZONE_DEVICE region outside the vmemmap window; vmemmap_populate() then\nwraps the memmap range around and maps it into low memory, silently\ncorrupting the page tables. The same search also picked the top-of-\naddress-space region that crashed memmap_init_zone_device() with amdkfd\non Loongson-3C6000 in 6.16 [1]; the commit 2969b42c8f99 (\"LoongArch/mm:\nalign vmemmap to maximal folio size\") keeps that region in bounds on\ncurrent Loongson-3C6000 configs, but CPUs with smaller cpu_pabits (e.g.\nthe Loongson-2K series) are still affected.\n\nDefine DIRECT_MAP_PHYSMEM_END as the vmemmap-covered physical range,\n(1ULL \u003c\u003c (cpu_pabits + 1)) - 1, capped at (1ULL \u003c\u003c MAX_PHYSMEM_BITS) - 1\nunder CONFIG_SPARSEMEM, similar to the commit f3336b48cf9d (\"riscv: mm:\nDefine DIRECT_MAP_PHYSMEM_END\").\n\n[1] https://lore.kernel.org/amd-gfx/20250814032153.227285-1-jeffbai@aosc.io/"
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "baseScore": 7.8,
            "baseSeverity": "HIGH",
            "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.1"
          },
          "scenarios": [
            {
              "lang": "en",
              "value": "AV:L - The missing DIRECT_MAP_PHYSMEM_END is consumed by gfr_start() inside get_free_mem_region() when kgd2kfd_init_zone_device() calls devm_request_free_mem_region(\u0026iomem_resource) from amdgpu device init (HSA_AMD depends on LOONGARCH \u0026\u0026 64BIT); that is local PCI-probe HMM setup, not a remote protocol message.\nAC:L - With GFR_DESCENDING, gfr_start() always starts at min(iomem_resource.end, the mm.h fallback (1ULL\u003c\u003cMAX_PHYSMEM_BITS)-1) minus size, so on a CPU with cpu_pabits+1 below 48 the first ZONE_DEVICE slot is above VMEMMAP_SIZE and vmemmap_populate() wraps with no race or victim-owned device fault.\nPR:L - amdgpu PCI probe runs kgd2kfd_init_zone_device()\u2192devm_memremap_pages() with no capable() check from userspace; after that wrap the unprivileged local account on a typical ROCm/desktop LoongArch host (render group, /dev/kfd with kfd_open() likewise ungated) shares the corrupted init_mm without init-namespace root.\nUI:N - amdgpu_device init itself calls kgd2kfd_init_zone_device() and then pagemap_range()\u2192add_pages()\u2192vmemmap_populate() on PCI bind; no victim must mount media, open a file, or click, and any NOUVEAU_SVM_BIND the attacker issues is on their own DRM fd.\nS:U - LoongArch vmemmap_populate() (vmemmap_set_pmd/vmemmap_populate_hugepages) writes PTEs via pgd_offset_k() into init_mm for the wrapped pfn_to_page() VA, which is host kernel MM corruption, not a KVM guest-to-host escape or IOMMU/DMA bypass.\nC:H - __populate_section_memmap() sets start to (unsigned long)pfn_to_page() of the out-of-window ZONE_DEVICE PFN, so vmemmap_populate() maps struct-page backing over low kernel VAs; memmap_init_zone_device() then stores page-\u003epgmap and flags through that alias, disclosing kernel pointers and data those VAs previously mapped.\nI:H - vmemmap_set_pmd() installs PAGE_KERNEL PMDs at the wrapped address and memmap_init_zone_device() writes struct-page fields through pfn_to_page() into that alias, an unconstrained kernel page-table and metadata write rather than a bounded data tweak.\nA:H - The same top-of-address-space region already crashed memmap_init_zone_device() with amdkfd on Loongson-3C6000, and on smaller cpu_pabits the wrap leaves init_mm PTEs pointing at the wrong physical pages so later pfn_to_page() walks oops or panic the host."
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-19T09:07:48.863Z",
        "orgId": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
        "shortName": "Linux"
      },
      "references": [
        {
          "url": "https://git.kernel.org/stable/c/ab275a23b4d9f04ca6c2f5f6a3246194e045a761"
        },
        {
          "url": "https://git.kernel.org/stable/c/55e18311c705cceef6c34d522ea387b1f0069bab"
        },
        {
          "url": "https://git.kernel.org/stable/c/2677f97a67fdbc62a82ce1faa67791f54451d36f"
        }
      ],
      "title": "LoongArch: Add DIRECT_MAP_PHYSMEM_END definition",
      "x_generator": {
        "engine": "bippy-1.2.0"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
    "assignerShortName": "Linux",
    "cveId": "CVE-2026-93237",
    "datePublished": "2026-09-24T15:33:51.702Z",
    "dateReserved": "2026-09-17T16:02:15.095Z",
    "dateUpdated": "2026-10-19T09:07:48.863Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.


Loading…

Loading…