linux-stable.git/drivers/gpu/drm/amd, branch linux-5.14.y

drm/amd/display: Look at firmware version to determine using dmub on dcn21

2021-11-17T10:04:51+00:00

commit 91adec9e07097e538691daed5d934e7886dd1dc3 upstream.

commit 652de07addd2 ("drm/amd/display: Fully switch to dmub for all dcn21
asics") switched over to using dmub on Renoir to fix Gitlab 1735, but this
implied a new dependency on newer firmware which might not be met on older
kernel versions.

Since sw_init runs before hw_init, there is an opportunity to determine
whether or not the firmware version is new to adjust the behavior.

Cc: Roman.Li@amd.com
BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1772
BugLink: https://gitlab.freedesktop.org/drm/amd/-/issues/1735
Fixes: 652de07addd2 ("drm/amd/display: Fully switch to dmub for all dcn21 asics")
Signed-off-by: Mario Limonciello 
Acked-by: Alex Deucher 
Reviewed-by: Roman Li 
Signed-off-by: Alex Deucher 
Signed-off-by: Greg Kroah-Hartman

drm/ttm: remove ttm_bo_vm_insert_huge()

2021-11-17T10:04:39+00:00

[ Upstream commit 0d979509539ed1df883a30d442177ca7be609565 ]

The huge page functionality in TTM does not work safely because PUD and
PMD entries do not have a special bit.

get_user_pages_fast() considers any page that passed pmd_huge() as
usable:

	if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) ||
		     pmd_devmap(pmd))) {

And vmf_insert_pfn_pmd_prot() unconditionally sets

	entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));

eg on x86 the page will be _PAGE_PRESENT | PAGE_PSE.

As such gup_huge_pmd() will try to deref a struct page:

	head = try_grab_compound_head(pmd_page(orig), refs, flags);

and thus crash.

Thomas further notices that the drivers are not expecting the struct page
to be used by anything - in particular the refcount incr above will cause
them to malfunction.

Thus everything about this is not able to fully work correctly considering
GUP_fast. Delete it entirely. It can return someday along with a proper
PMD/PUD_SPECIAL bit in the page table itself to gate GUP_fast.

Fixes: 314b6580adc5 ("drm/ttm, drm/vmwgfx: Support huge TTM pagefaults")
Signed-off-by: Jason Gunthorpe 
Reviewed-by: Thomas Hellström 
Reviewed-by: Christian König 
[danvet: Update subject per Thomas' &Christian's review]
Signed-off-by: Daniel Vetter 
Link: https://patchwork.freedesktop.org/patch/msgid/0-v2-a44694790652+4ac-ttm_pmd_jgg@nvidia.com
Signed-off-by: Sasha Levin

drm/amdgpu/gmc6: fix DMA mask from 44 to 40 bits

2021-11-17T10:04:17+00:00

[ Upstream commit 403475be6d8b122c3e6b8a47e075926d7299e5ef ]

The DMA mask on SI parts is 40 bits not 44.  Copy
paste typo.

Fixes: 244511f386ccb9 ("drm/amdgpu: simplify and cleanup setting the dma mask")
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1762
Acked-by: Christian König 
Tested-by: Paul Menzel 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdgpu: fix a potential memory leak in amdgpu_device_fini_sw()

2021-11-17T10:04:17+00:00

[ Upstream commit a5c5d8d50ecf5874be90a76e1557279ff8a30c9e ]

amdgpu_fence_driver_sw_fini() should be executed before
amdgpu_device_ip_fini(), otherwise fence driver resource
won't be properly freed as adev->rings have been tore down.

Fixes: 72c8c97b1522 ("drm/amdgpu: Split amdgpu_device_fini into early and late")

Signed-off-by: Lang Yu 
Reviewed-by: Andrey Grodzovsky 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: Fix an inappropriate error handling in allloc memory of gpu

2021-11-17T10:04:08+00:00

[ Upstream commit 5aeeac6fa38fca450faed9770f75b1470c0e2073 ]

We should unreference a gem object instead of an amdgpu bo here.

Fixes: fd9a9f8801de ("drm/amdgpu: Use GEM obj reference for KFD BOs")

Signed-off-by: Lang Yu 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdgpu: fix warning for overflow check

2021-11-17T10:04:01+00:00

[ Upstream commit 335aea75b0d95518951cad7c4c676e6f1c02c150 ]

The overflow check in amdgpu_bo_list_create() causes a warning with
clang-14 on 64-bit architectures, since the limit can never be
exceeded.

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c:74:18: error: result of comparison of constant 256204778801521549 with expression of type 'unsigned int' is always false [-Werror,-Wtautological-constant-out-of-range-compare]
        if (num_entries > (SIZE_MAX - sizeof(struct amdgpu_bo_list))
            ~~~~~~~~~~~ ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The check remains useful for 32-bit architectures, so just avoid the
warning by using size_t as the type for the count.

Fixes: 920990cb080a ("drm/amdgpu: allocate the bo_list array after the list")
Reviewed-by: Christian König 
Signed-off-by: Arnd Bergmann 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdgpu: move amdgpu_virt_release_full_gpu to fini_early stage

2021-11-17T10:03:59+00:00

[ Upstream commit 6effad8abe0ba4db3d9c58ed585127858a990f35 ]

adev->rmmio is set to be NULL in amdgpu_device_unmap_mmio to prevent
access after pci_remove, however, in SRIOV case, amdgpu_virt_release_full_gpu
will still use adev->rmmio for access after amdgpu_device_unmap_mmio.
The patch is to move such SRIOV calling earlier to fini_early stage.

Fixes: 07775fc13878 ("drm/amdgpu: Unmap all MMIO mappings")
Cc: Andrey Grodzovsky 
Signed-off-by: Leslie Shi 
Signed-off-by: Guchun Chen 
Reviewed-by: Andrey Grodzovsky 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amd/display: dcn20_resource_construct reduce scope of FPU enabled

2021-11-17T10:03:56+00:00

[ Upstream commit bc39a69a2ac484e6575a958567c162ef56c9f278 ]

Limit when FPU is enabled to only functions that does FPU operations for
dcn20_resource_construct, which gets called during driver
initialization.

Enabling FPU operation disables preemption.  Sleeping functions(mutex
(un)lock, memory allocation using GFP_KERNEL, etc.) should not be called
when preemption is disabled.

Fixes the following case caught by enabling
CONFIG_DEBUG_ATOMIC_SLEEP in kernel config
[    1.338434] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:281
[    1.347395] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 197, name: systemd-udevd
[    1.356356] CPU: 7 PID: 197 Comm: systemd-udevd Not tainted 5.13.0+ #3
[    1.356358] Hardware name: System manufacturer System Product Name/PRIME X570-PRO, BIOS 3405 02/01/2021
[    1.356360] Call Trace:
[    1.356361]  dump_stack+0x6b/0x86
[    1.356366]  ___might_sleep.cold+0x87/0x98
[    1.356370]  __might_sleep+0x4b/0x80
[    1.356372]  mutex_lock+0x21/0x50
[    1.356376]  smu_get_uclk_dpm_states+0x3f/0x80 [amdgpu]
[    1.356538]  pp_nv_get_uclk_dpm_states+0x35/0x50 [amdgpu]
[    1.356711]  init_soc_bounding_box+0xf9/0x210 [amdgpu]
[    1.356892]  ? create_object+0x20d/0x340
[    1.356897]  ? dcn20_resource_construct+0x46f/0xd30 [amdgpu]
[    1.357077]  dcn20_resource_construct+0x4b1/0xd30 [amdgpu]
...

Tested on: 5700XT (NAVI10 0x1002:0x731F 0x1DA2:0xE410 0xC1)

Cc: Christian König 
Cc: Hersen Wu 
Cc: Anson Jacob 
Cc: Harry Wentland 

Reviewed-by: Rodrigo Siqueira 
Tested-by: Daniel Wheeler 
Acked-by: Agustin Gutierrez 
Signed-off-by: Anson Jacob 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdgpu/pm: properly handle sclk for profiling modes on vangogh

2021-11-17T10:03:53+00:00

[ Upstream commit 68e3871dcd6e547f6c47454492bc452356cb9eac ]

When selecting between levels in the force performance levels interface
sclk (gfxclk) was not set correctly for all levels.  Select the proper
sclk settings for all levels.

Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1726
Reviewed-by: Evan Quan 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin

drm/amdkfd: fix resume error when iommu disabled in Picasso

2021-11-17T10:03:50+00:00

[ Upstream commit 6f4b590aae217da16cfa44039a2abcfb209137ab ]

When IOMMU disabled in sbios and kfd in iommuv2 path,
IOMMU resume failure blocks system resume. Don't allow kfd to
use iommu v2 when iommu is disabled.

Reported-by: youling 
Tested-by: youling 
Signed-off-by: Yifan Zhang 
Reviewed-by: James Zhu 
Signed-off-by: Alex Deucher 
Signed-off-by: Sasha Levin