For some GPUs with more CUs, the original sibling_map[32]
in struct crat_subtype_cache is not enough
to save the cache information when create the VCRAT table,
so skip filling the struct crat_subtype_cache info instead
fill struct kfd_cache_properties directly to fix this problem.
Signed-off-by: Ma Jun <email address hidden>
Reviewed-by: Felix Kuehling <email address hidden>
Signed-off-by: Alex Deucher <email address hidden>
(backported from commit c0cc999f3c32e65a7c88fb323893ddf897b24488)
[vicamo: fix conflict in kfd_get_gpu_cache_info]
Signed-off-by: You-Sheng Yang (vicamo) <email address hidden>
kfd_topology_device->cache_count is not used by
other fucntions, so remove it.
Signed-off-by: Ma Jun <email address hidden>
Reviewed-by: Felix Kuehling <email address hidden>
Signed-off-by: Alex Deucher <email address hidden>
(cherry picked from commit ee22f63b1085fd5cf1649e8915b1e2617cd33ca0)
Signed-off-by: You-Sheng Yang (vicamo) <email address hidden>
As there will be more USB4 devices that support NVM firmware upgrade from
various vendors, it makes sense to split out the Intel specific NVM
image handling from the generic code. This moves the Intel specific NVM
handling into a new structure that will be matched by the device type
and the vendor ID. Do this for both routers and retimers.
This makes it easier to extend the NVM support to cover new vendors and
NVM image formats in the future.
Signed-off-by: Szuying Chen <email address hidden>
Signed-off-by: Mika Westerberg <email address hidden>
(cherry picked from commit aef9c693e7e550954fc526b919342cc7d8047ed1 linux-next)
Signed-off-by: You-Sheng Yang (vicamo) <email address hidden>
26a2fc6...
by
Mika Westerberg <email address hidden>
thunderbolt: Provide tb_retimer_nvm_read() analogous to tb_switch_nvm_read()
As we are moving the NVM vendor specifics into nvm.c we need to deal
witht he retimer NVM formats too. For this reason provide retimer
specific function that can be used to read the contents of the NVM and
rename the internal ones accordingly analogous to what we do with
routers.
Signed-off-by: Mika Westerberg <email address hidden>
(backported from commit 8b02b2da77c89d9b9031f522e50af9eb2270585a linux-next)
[vicamo: fix conflict due to the lack of commit 7f333ace02578]
Signed-off-by: You-Sheng Yang (vicamo) <email address hidden>
In order to support non-Intel NVM formats the vendor specific NVM
validation code that will live in nvm.c needs to be able to read various
parts of the NVM so make the function available outside of switch.c and
rename it accordingly.
Signed-off-by: Szuying Chen <email address hidden>
Signed-off-by: Mika Westerberg <email address hidden>
(cherry picked from commit 7bfafaa5185be3088e57f046956d6db0155ddc17 linux-next)
Signed-off-by: You-Sheng Yang (vicamo) <email address hidden>