Re: [PATCH] IMA: allow/fix UML builds

[Randy Dunlap]

On 3/14/23 11:28, Mimi Zohar wrote:
> On Thu, 2023-02-23 at 19:27 -0800, Randy Dunlap wrote:
>> UML supports HAS_IOMEM since 0bbadafdc49d (um: allow disabling
>> NO_IOMEM).
>>
>> Current IMA build on UML fails on allmodconfig (with TCG_TPM=m):
>>
>> ld: security/integrity/ima/ima_queue.o: in function `ima_add_template_entry':
>> ima_queue.c:(.text+0x2d9): undefined reference to `tpm_pcr_extend'
>> ld: security/integrity/ima/ima_init.o: in function `ima_init':
>> ima_init.c:(.init.text+0x43f): undefined reference to `tpm_default_chip'
>> ld: security/integrity/ima/ima_crypto.o: in function `ima_calc_boot_aggregate_tfm':
>> ima_crypto.c:(.text+0x1044): undefined reference to `tpm_pcr_read'
>> ld: ima_crypto.c:(.text+0x10d8): undefined reference to `tpm_pcr_read'
>>
>> Modify the IMA Kconfig entry so that it selects TCG_TPM if HAS_IOMEM
>> is set, regardless of the UML Kconfig setting.
>> This updates TCG_TPM from =m to =y and fixes the linker errors.
>>
>> Fixes: f4a0391dfa91 ("ima: fix Kconfig dependencies")
>> Signed-off-by: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
> 
> Indicating this resolves a commit which was upstreamed in linux-3.4,
> while the fix for that commit 0bbadafdc49d ("um: allow disabling
> NO_IOMEM") was upstreamed only in linux-5.14, leaves out an important
> detail.
> 
> Is the proper way of indicating this disconnect by adding to the fixes
> line the kernel?
> Fixes: f4a0391dfa91 ("ima: fix Kconfig dependencies") # v5.14+

Yes, that is acceptable AFAIK. Also
Cc: stable@xxxxxxxxxxxxxxx

or AUTOSEL would probably take care of this as it is.

-- 
~Randy