fkie_cve-2025-22013
Vulnerability from fkie_nvd
Published
2025-04-08 09:15
Modified
2025-05-02 07:15
Severity ?
Summary
In the Linux kernel, the following vulnerability has been resolved: KVM: arm64: Unconditionally save+flush host FPSIMD/SVE/SME state There are several problems with the way hyp code lazily saves the host's FPSIMD/SVE state, including: * Host SVE being discarded unexpectedly due to inconsistent configuration of TIF_SVE and CPACR_ELx.ZEN. This has been seen to result in QEMU crashes where SVE is used by memmove(), as reported by Eric Auger: https://issues.redhat.com/browse/RHEL-68997 * Host SVE state is discarded *after* modification by ptrace, which was an unintentional ptrace ABI change introduced with lazy discarding of SVE state. * The host FPMR value can be discarded when running a non-protected VM, where FPMR support is not exposed to a VM, and that VM uses FPSIMD/SVE. In these cases the hyp code does not save the host's FPMR before unbinding the host's FPSIMD/SVE/SME state, leaving a stale value in memory. Avoid these by eagerly saving and "flushing" the host's FPSIMD/SVE/SME state when loading a vCPU such that KVM does not need to save any of the host's FPSIMD/SVE/SME state. For clarity, fpsimd_kvm_prepare() is removed and the necessary call to fpsimd_save_and_flush_cpu_state() is placed in kvm_arch_vcpu_load_fp(). As 'fpsimd_state' and 'fpmr_ptr' should not be used, they are set to NULL; all uses of these will be removed in subsequent patches. Historical problems go back at least as far as v5.17, e.g. erroneous assumptions about TIF_SVE being clear in commit: 8383741ab2e773a9 ("KVM: arm64: Get rid of host SVE tracking/saving") ... and so this eager save+flush probably needs to be backported to ALL stable trees.
References
416baaa9-dc9f-4396-8d5f-8c081fb06d67https://git.kernel.org/stable/c/04c50cc23a492c4d43fdaefc7c1ecc0ff6f7b82e
416baaa9-dc9f-4396-8d5f-8c081fb06d67https://git.kernel.org/stable/c/5289ac43b69c61a49c75720921f2008005a31c43
416baaa9-dc9f-4396-8d5f-8c081fb06d67https://git.kernel.org/stable/c/79e140bba70bcacc5fe15bf8c0b958793fd7d56f
416baaa9-dc9f-4396-8d5f-8c081fb06d67https://git.kernel.org/stable/c/806d5c1e1d2e5502175a24bf70f251648d99c36a
416baaa9-dc9f-4396-8d5f-8c081fb06d67https://git.kernel.org/stable/c/900b444be493b7f404898c785d6605b177a093d0
416baaa9-dc9f-4396-8d5f-8c081fb06d67https://git.kernel.org/stable/c/fbc7e61195e23f744814e78524b73b59faa54ab4
Impacted products
Vendor Product Version


To clipboard 

{
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "In the Linux kernel, the following vulnerability has been resolved:\n\nKVM: arm64: Unconditionally save+flush host FPSIMD/SVE/SME state\n\nThere are several problems with the way hyp code lazily saves the host\u0027s\nFPSIMD/SVE state, including:\n\n* Host SVE being discarded unexpectedly due to inconsistent\n  configuration of TIF_SVE and CPACR_ELx.ZEN. This has been seen to\n  result in QEMU crashes where SVE is used by memmove(), as reported by\n  Eric Auger:\n\n  https://issues.redhat.com/browse/RHEL-68997\n\n* Host SVE state is discarded *after* modification by ptrace, which was an\n  unintentional ptrace ABI change introduced with lazy discarding of SVE state.\n\n* The host FPMR value can be discarded when running a non-protected VM,\n  where FPMR support is not exposed to a VM, and that VM uses\n  FPSIMD/SVE. In these cases the hyp code does not save the host\u0027s FPMR\n  before unbinding the host\u0027s FPSIMD/SVE/SME state, leaving a stale\n  value in memory.\n\nAvoid these by eagerly saving and \"flushing\" the host\u0027s FPSIMD/SVE/SME\nstate when loading a vCPU such that KVM does not need to save any of the\nhost\u0027s FPSIMD/SVE/SME state. For clarity, fpsimd_kvm_prepare() is\nremoved and the necessary call to fpsimd_save_and_flush_cpu_state() is\nplaced in kvm_arch_vcpu_load_fp(). As \u0027fpsimd_state\u0027 and \u0027fpmr_ptr\u0027\nshould not be used, they are set to NULL; all uses of these will be\nremoved in subsequent patches.\n\nHistorical problems go back at least as far as v5.17, e.g. erroneous\nassumptions about TIF_SVE being clear in commit:\n\n  8383741ab2e773a9 (\"KVM: arm64: Get rid of host SVE tracking/saving\")\n\n... and so this eager save+flush probably needs to be backported to ALL\nstable trees."
    },
    {
      "lang": "es",
      "value": "En el kernel de Linux, se ha resuelto la siguiente vulnerabilidad: KVM: arm64: Guardar y vaciar incondicionalmente el estado FPSIMD/SVE/SME del host Hay varios problemas con la forma en que el c\u00f3digo hyp guarda de forma diferida el estado FPSIMD/SVE del host, incluidos: * El SVE del host se descarta inesperadamente debido a una configuraci\u00f3n inconsistente de TIF_SVE y CPACR_ELx.ZEN. Se ha visto que esto da como resultado fallos de QEMU donde memmove() usa SVE, como lo inform\u00f3 Eric Auger: https://issues.redhat.com/browse/RHEL-68997 * El estado SVE del host se descarta *despu\u00e9s* de la modificaci\u00f3n por ptrace, que fue un cambio de ABI de ptrace no intencionado introducido con el descarte diferido del estado SVE. * El valor FPMR del host se puede descartar cuando se ejecuta una VM no protegida, donde la compatibilidad con FPMR no est\u00e1 expuesta a una VM y esa VM usa FPSIMD/SVE. En estos casos, el c\u00f3digo hyp no guarda el FPMR del host antes de desvincular su estado FPSIMD/SVE/SME, lo que deja un valor obsoleto en memoria. Para evitar esto, guarde y vac\u00ede el estado FPSIMD/SVE/SME del host al cargar una vCPU, de modo que KVM no tenga que guardar ninguno de sus estados. Para mayor claridad, se ha eliminado fpsimd_kvm_prepare() y la llamada necesaria a fpsimd_save_and_flush_cpu_state() se ha ubicado en kvm_arch_vcpu_load_fp(). Dado que \u0027fpsimd_state\u0027 y \u0027fpmr_ptr\u0027 no deben usarse, se establecen en NULL; todos sus usos se eliminar\u00e1n en parches posteriores. Los problemas hist\u00f3ricos se remontan al menos a la versi\u00f3n v5.17, por ejemplo, suposiciones err\u00f3neas acerca de que TIF_SVE est\u00e1 claro en el commit: 8383741ab2e773a9 (\"KVM: arm64: deshacerse del seguimiento/guardado de SVE del host\")... y por eso, este ansioso guardado y vaciado probablemente deba ser retrotra\u00eddo a TODOS los \u00e1rboles estables."
    }
  ],
  "id": "CVE-2025-22013",
  "lastModified": "2025-05-02T07:15:59.113",
  "metrics": {},
  "published": "2025-04-08T09:15:25.643",
  "references": [
    {
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
      "url": "https://git.kernel.org/stable/c/04c50cc23a492c4d43fdaefc7c1ecc0ff6f7b82e"
    },
    {
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
      "url": "https://git.kernel.org/stable/c/5289ac43b69c61a49c75720921f2008005a31c43"
    },
    {
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
      "url": "https://git.kernel.org/stable/c/79e140bba70bcacc5fe15bf8c0b958793fd7d56f"
    },
    {
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
      "url": "https://git.kernel.org/stable/c/806d5c1e1d2e5502175a24bf70f251648d99c36a"
    },
    {
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
      "url": "https://git.kernel.org/stable/c/900b444be493b7f404898c785d6605b177a093d0"
    },
    {
      "source": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
      "url": "https://git.kernel.org/stable/c/fbc7e61195e23f744814e78524b73b59faa54ab4"
    }
  ],
  "sourceIdentifier": "416baaa9-dc9f-4396-8d5f-8c081fb06d67",
  "vulnStatus": "Awaiting Analysis"
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




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.
  • 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.