[ Upstream commit 74fa02c4a5ea1ade5156a6ce494d3ea83881c2d8 ]
Cache the PCI state before bus master is disabled. The saved state is
later used for other cases like restoring config space after mode-2
reset.
Fixes: 5c03e5843e6b ("drm/amdgpu:add smu mode1/2 support for aldebaran")
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 47fc644f801e4414753a9b7e87ed41f991cd68c3 ]
Fix following checkpatch style errors in amdgpu_drv.c &
amdgpu_device.c
ERROR: exactly one space required after that #ifdef
ERROR: spaces required around that '+=' (ctx:WxV)
ERROR: space required before the open brace '{'
ERROR: spaces required around that '||' (ctx:VxE)
ERROR: space prohibited before that close parenthesis ')'
ERROR: space required before the open parenthesis '('
ERROR: space required before the open brace '{'
ERROR: code indent should use tabs where possible
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Stable-dep-of: 74fa02c4a5ea ("drm/amdgpu: Fix pci state save during mode-1 reset")
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 03c6284df179de3a4a6e0684764b1c71d2a405e2 upstream.
This patch causes the following iounmap erorr and calltrace
iounmap: bad address 00000000d0b3631f
The original patch was unjustified because amdgpu_device_fini_sw() will
always cleanup the rmmio mapping.
This reverts commit eb4f139888f636614dab3bcce97ff61cefc4b3a7.
Signed-off-by: Ma Jun <Jun.Ma2@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit eb4f139888f636614dab3bcce97ff61cefc4b3a7 ]
This ensures that the memory mapped by ioremap for adev->rmmio, is
properly handled in amdgpu_device_init(). If the function exits early
due to an error, the memory is unmapped. If the function completes
successfully, the memory remains mapped.
Reported by smatch:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:4337 amdgpu_device_init() warn: 'adev->rmmio' from ioremap() not released on lines: 4035,4045,4051,4058,4068,4337
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit cb11ca3233aa3303dc11dca25977d2e7f24be00f ]
If any IP blocks allocate memory during their hw_fini() sequence
this can cause the suspend to fail under memory pressure. Introduce
a new phase that IP blocks can use to allocate memory before suspend
starts so that it can potentially be evicted into swap instead.
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Stable-dep-of: ca299b4512d4 ("drm/amd: Flush GFXOFF requests in prepare stage")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5095d5418193eb2748c7d8553c7150b8f1c44696 ]
Linux PM core has a prepare() callback run before suspend.
If the system is under high memory pressure, the resources may need
to be evicted into swap instead. If the storage backing for swap
is offlined during the suspend() step then such a call may fail.
So move this step into prepare() to move evict majority of
resources and update all non-pmops callers to call the same callback.
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2362
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Stable-dep-of: ca299b4512d4 ("drm/amd: Flush GFXOFF requests in prepare stage")
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 916361685319098f696b798ef1560f69ed96e934 upstream.
commit ab4750332dbe ("drm/amdgpu/sdma5.2: add begin/end_use ring
callbacks") caused GFXOFF control to be used more heavily and the
codepath that was removed from commit 0dee72639533 ("drm/amd: flush any
delayed gfxoff on suspend entry") now can be exercised at suspend again.
Users report that by using GNOME to suspend the lockscreen trigger will
cause SDMA traffic and the system can deadlock.
This reverts commit 0dee726395333fea833eaaf838bc80962df886c8.
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Fixes: ab4750332dbe ("drm/amdgpu/sdma5.2: add begin/end_use ring callbacks")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 8a44fdd3cf91debbd09b43bd2519ad2b2486ccf4 ]
In function 'amdgpu_device_need_post(struct amdgpu_device *adev)' -
'adev->pm.fw' may not be released before return.
Using the function release_firmware() to release adev->pm.fw.
Thus fixing the below:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1571 amdgpu_device_need_post() warn: 'adev->pm.fw' from request_firmware() not released on lines: 1554.
Cc: Monk Liu <Monk.Liu@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 7b1c6263eaf4fd64ffe1cafdc504a42ee4bfbb33 upstream.
It's only valid on Intel systems with the Intel VSEC.
Use dev_is_removable() instead. This should do the right
thing regardless of the platform.
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2925
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 80285ae1ec8717b597b20de38866c29d84d321a1 ]
The amdgpu_ras_get_context may return NULL if device
not support ras feature, so add check before using.
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 134b8c5d8674e7cde380f82e9aedfd46dcdd16f7 upstream.
On some systems with Navi3x dGPU will attempt to use BACO for runtime
PM but fails to resume properly. This is because on these systems
the root port goes into D3cold which is incompatible with BACO.
This happens because in this case dGPU is connected to a bridge between
root port which causes BOCO detection logic to fail. Fix the intent of
the logic by looking at root port, not the immediate upstream bridge for
_PR3.
Cc: stable@vger.kernel.org
Suggested-by: Jun Ma <Jun.Ma2@amd.com>
Tested-by: David Perry <David.Perry@amd.com>
Fixes: b10c1c5b3a4e ("drm/amdgpu: add check for ACPI power resources")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 169ed4ece8373f02f10642eae5240e3d1ef5c038 upstream.
This reverts commit 70e64c4d522b732e31c6475a3be2349de337d321.
Since, we now have an actual fix for this issue, we can get rid of this
workaround as it can cause pin failures if enough VRAM isn't carved out
by the BIOS.
Cc: stable@vger.kernel.org # 6.1+
Acked-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 822130b5e8834ab30ad410cf19a582e5014b9a85 ]
On 32-bit architectures comparing a resource against a value larger than
U32_MAX can cause a warning:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1344:18: error: result of comparison of constant 4294967296 with expression of type 'resource_size_t' (aka 'unsigned int') is always false [-Werror,-Wtautological-constant-out-of-range-compare]
res->start > 0x100000000ull)
~~~~~~~~~~ ^ ~~~~~~~~~~~~~~
As gcc does not warn about this in dead code, add an IS_ENABLED() check at
the start of the function. This will always return success but not actually resize
the BAR on 32-bit architectures without high memory, which is exactly what
we want here, as the driver can fall back to bank switching the VRAM
access.
Fixes: 31b8adab3247 ("drm/amdgpu: require a root bus window above 4GB for BAR resize")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit a7b7d9e8aee4f71b4c7151702fd74237b8cef989 upstream.
DCN 3.1.4 is reported to hang on s2idle entry if graphics activity
is happening during entry. This is because GFXOFF was scheduled as
delayed but RLC gets disabled in s2idle entry sequence which will
hang GFX IP if not already in GFXOFF.
To help this problem, flush any delayed work for GFXOFF early in
s2idle entry sequence to ensure that it's off when RLC is changed.
commit 4b31b92b143f ("drm/amdgpu: complete gfxoff allow signal during
suspend without delay") modified power gating flow so that if called
in s0ix that it ensured that GFXOFF wasn't put in work queue but
instead processed immediately.
This is dead code due to commit 10cb67eb8a1b ("drm/amdgpu: skip
CG/PG for gfx during S0ix") because GFXOFF will now not be explicitly
called as part of the suspend entry code. Remove that dead code.
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Tim Huang <tim.huang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 08fffa74d9772d9538338be3f304006c94dde6f0 upstream.
Users report a white flickering screen on multiple systems that
is tied to having 64GB or more memory. When S/G is enabled pages
will get pinned to both VRAM carve out and system RAM leading to
this.
Until it can be fixed properly, disable S/G when 64GB of memory or
more is detected. This will force pages to be pinned into VRAM.
This should fix white screen flickers but if VRAM pressure is
encountered may lead to black screens. It's a trade-off for now.
Fixes: 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)")
Cc: Hamza Mahfooz <Hamza.Mahfooz@amd.com>
Cc: Roman Li <roman.li@amd.com>
Cc: <stable@vger.kernel.org> # 6.1.y: bf0207e172703 ("drm/amdgpu: add S/G display parameter")
Cc: <stable@vger.kernel.org> # 6.4.y
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2735
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2354
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 188623076d0f1a500583d392b6187056bf7cc71a upstream.
This helper is used for checking if the connected host supports
the feature, it can be moved into generic code to be used by other
smu implementations as well.
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 38eecbe086a4e52f54b2bbda8feba65d44addbef ]
[WHY]
Function "amdgpu_irq_update()" called by "amdgpu_device_ip_late_init()" is an atomic context.
We shouldn't access registers through KIQ since "msleep()" may be called in "amdgpu_kiq_rreg()".
[HOW]
Move function "amdgpu_virt_release_full_gpu()" after function "amdgpu_device_ip_late_init()",
to ensure that registers be accessed through RLCG instead of KIQ.
Call Trace:
<TASK>
show_stack+0x52/0x69
dump_stack_lvl+0x49/0x6d
dump_stack+0x10/0x18
__schedule_bug.cold+0x4f/0x6b
__schedule+0x473/0x5d0
? __wake_up_klogd.part.0+0x40/0x70
? vprintk_emit+0xbe/0x1f0
schedule+0x68/0x110
schedule_timeout+0x87/0x160
? timer_migration_handler+0xa0/0xa0
msleep+0x2d/0x50
amdgpu_kiq_rreg+0x18d/0x1f0 [amdgpu]
amdgpu_device_rreg.part.0+0x59/0xd0 [amdgpu]
amdgpu_device_rreg+0x3a/0x50 [amdgpu]
amdgpu_sriov_rreg+0x3c/0xb0 [amdgpu]
gfx_v10_0_set_gfx_eop_interrupt_state.constprop.0+0x16c/0x190 [amdgpu]
gfx_v10_0_set_eop_interrupt_state+0xa5/0xb0 [amdgpu]
amdgpu_irq_update+0x53/0x80 [amdgpu]
amdgpu_irq_get+0x7c/0xb0 [amdgpu]
amdgpu_fence_driver_hw_init+0x58/0x90 [amdgpu]
amdgpu_device_init.cold+0x16b7/0x2022 [amdgpu]
Signed-off-by: Chong Li <chongli2@amd.com>
Reviewed-by: JingWen.Chen2@amd.com
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 6c032c37ac3ef3b7df30937c785ecc4da428edc0 upstream.
v1: Vmbo->shadow is used to back vram bo up when vram lost. So that we
should set shadow as vmbo->shadow to recover vmbo->bo
v2: Modify if(vmbo->shadow) shadow = vmbo->shadow as if(!vmbo->shadow)
continue;
Fixes: e18aaea733da ("drm/amdgpu: move shadow_list to amdgpu_bo_vm")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Lin.Cao <lincao12@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit d37a3929ca0363ed1dce02b2772cd5bc547ca66d ]
Commit 3840c5bcc245 ("drm/amdgpu: disentangle runtime pm and
vga_switcheroo") made amdgpu only register a vga_switcheroo client for
GPU's with PX, however AMD GPUs in dual gpu Apple Macbooks do need to
register, but don't have PX. Instead of AMD's PX, they use apple-gmux.
Use apple_gmux_detect() to identify these gpus, and
pci_is_thunderbolt_attached() to ensure eGPUs connected to Dual GPU
Macbooks don't register with vga_switcheroo.
Fixes: 3840c5bcc245 ("drm/amdgpu: disentangle runtime pm and vga_switcheroo")
Link: https://lore.kernel.org/amd-gfx/20230210044826.9834-10-orlandoch.dev@gmail.com/
Signed-off-by: Orlando Chamberlain <orlandoch.dev@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit e11c775030c5585370fda43035204bb5fa23b139 upstream.
The psp suspend & resume should be skipped to avoid destroy
the TMR and reload FWs again for IMU enabled APU ASICs.
Signed-off-by: Tim Huang <tim.huang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2a7798ea7390fd78f191c9e9bf68f5581d3b4a02 upstream.
SDMA 5.x is part of the GFX block so it's controlled via
GFXOFF. Skip suspend as it should be handled the same
as GFX.
v2: drop SDMA 4.x. That requires special handling.
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: "Limonciello, Mario" <Mario.Limonciello@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2b072442f4962231a8516485012bb2d2551ef2fe upstream.
S2idle resume freeze can be observed on Intel ADL + AMD WX5500. This is
caused by commit 0064b0ce85bb ("drm/amd/pm: enable ASPM by default").
The root cause is still not clear for now.
So extend and apply the ASPM quirk from commit e02fe3bc7aba
("drm/amdgpu: vi: disable ASPM on Intel Alder Lake based systems"), to
workaround the issue on Navi cards too.
Fixes: 0064b0ce85bb ("drm/amd/pm: enable ASPM by default")
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2458
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 39934d3ed5725c5e3570ed1b67f612f1ea60ce03 ]
This reverts commit fac53471d0ea9693d314aa2df08d62b2e7e3a0f8.
The following change: move the drm_dev_unplug call after
amdgpu_driver_unload_kms in amdgpu_pci_remove. The reason is
the following: amdgpu_pci_remove calls drm_dev_unregister
and it should be called first to ensure userspace can't access the
device instance anymore. If we call drm_dev_unplug after
amdgpu_driver_unload_kms then we observe IGT PCI software unplug
test failure (kernel hung) for all ASICs. This is how this
regression was found.
After this revert, the following commands do work not, but it would
be fixed in the next commit:
- sudo modprobe -r amdgpu
- sudo modprobe amdgpu
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 8f32378986218812083b127da5ba42d48297d7c4 upstream.
Freeing memory was warned during suspend.
Move the self test out of suspend.
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2151825
Cc: jfalempe@redhat.com
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-and-tested-by: Evan Quan <evan.quan@amd.com>
Tested-by: Jocelyn Falempe <jfalempe@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 1923bc5a56daeeabd7e9093bad2febcd6af2416a upstream.
Removing the firmware framebuffer from the driver means that even
if the driver doesn't support the IP blocks in a GPU it will no
longer be functional after the driver fails to initialize.
This change will ensure that unsupported IP blocks at least cause
the driver to work with the EFI framebuffer.
Cc: stable@vger.kernel.org
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit afa6646b1c5d3affd541f76bd7476e4b835a9174 upstream.
It's also part of gfxoff.
Cc: stable@vger.kernel.org # 6.0, 6.1
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit dfd0287bd3920e132a8dae2a0ec3d92eaff5f2dd ]
In amdgpu_get_xgmi_hive(), we should not call kfree() after
kobject_put() as the PUT will call kfree().
In amdgpu_device_ip_init(), we need to check the returned *hive*
which can be NULL before we dereference it.
Signed-off-by: Liang He <windhl@126.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit b85e285e3d6352b02947fc1b72303673dfacb0aa ]
As comment of pci_get_domain_bus_and_slot() says, it returns
a pci device with refcount increment, when finish using it,
the caller must decrement the reference count by calling
pci_dev_put().
So before returning from amdgpu_device_resume|suspend_display_audio(),
pci_dev_put() is called to avoid refcount leak.
Fixes: 3f12acc8d6d4 ("drm/amdgpu: put the audio codec into suspend state before gpu reset V3")
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
If we enable virtual display functionality on parts with
no display hardware we can end up trying to check for and
reserve the vbios FB area on devices where it doesn't exist.
Check if display hardware is actually present on the hardware
before trying to reserve the memory.
v2: move the check into common code
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
If a system does not have swap and memory is under 100% usage,
amdgpu will fail to evict resources. Currently the suspend
carries on proceeding to reset the GPU:
```
[drm] evicting device resources failed
[drm:amdgpu_device_ip_suspend_phase2 [amdgpu]] *ERROR* suspend of IP block <vcn_v3_0> failed -12
[drm] free PSP TMR buffer
[TTM] Failed allocating page table
[drm] evicting device resources failed
amdgpu 0000:03:00.0: amdgpu: MODE1 reset
amdgpu 0000:03:00.0: amdgpu: GPU mode1 reset
amdgpu 0000:03:00.0: amdgpu: GPU smu mode1 reset
```
At this point if the suspend actually succeeded I think that amdgpu
would have recovered because the GPU would have power cut off and
restored. However the kernel fails to continue the suspend from the
memory pressure and amdgpu fails to run the "resume" from the aborted
suspend.
```
ACPI: PM: Preparing to enter system sleep state S3
SLUB: Unable to allocate memory on node -1, gfp=0xdc0(GFP_KERNEL|__GFP_ZERO)
cache: Acpi-State, object size: 80, buffer size: 80, default order: 0, min order: 0
node 0: slabs: 22, objs: 1122, free: 0
ACPI Error: AE_NO_MEMORY, Could not update object reference count (20210730/utdelete-651)
[drm:psp_hw_start [amdgpu]] *ERROR* PSP load kdb failed!
[drm:psp_resume [amdgpu]] *ERROR* PSP resume failed
[drm:amdgpu_device_fw_loading [amdgpu]] *ERROR* resume of IP block <psp> failed -62
amdgpu 0000:03:00.0: amdgpu: amdgpu_device_ip_resume failed (-62).
PM: dpm_run_callback(): pci_pm_resume+0x0/0x100 returns -62
amdgpu 0000:03:00.0: PM: failed to resume async: error -62
```
To avoid this series of unfortunate events, fail amdgpu's suspend
when the memory eviction fails. This will let the system gracefully
recover and the user can try suspend again when the memory pressure
is relieved.
Reported-by: post@davidak.de
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2223
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In the S2idle suspend/resume phase the gfxoff is keeping functional so
some IP blocks will be likely to reinitialize at gfxoff entry and that
will result in failing to program GC registers.Therefore, let disallow
gfxoff until AMDGPU IPs reinitialized completely.
Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 5.15.x
Suggested by PMFW team and same as what did for gfxoff feature.
This can address some Mode1Reset failures observed on SMU13.0.0.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.0.x
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts commit dac6b80818ac2353631c5a33d140d8d5508e2957.
This commit reverted the AMDGPU_SKIP_MODE2_RESET as it conflicts with
the original design of reset handler. Will redesign it.
Fixes: dac6b80818ac23 ("drm/amdgpu: let mode2 reset fallback to default when failure")
Signed-off-by: Victor Zhao <Victor.Zhao@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
- Under SRIOV, we need to send REQ_GPU_FINI to the hypervisor
during the suspend time. Furthermore, we cannot request a
mode 1 reset under SRIOV as VF. Therefore, we will skip it
as it is called in suspend_noirq() function.
- In the resume code path, we need to send REQ_GPU_INIT to the
hypervisor and also resume PSP IP block under SRIOV.
Signed-off-by: Bokun Zhang <Bokun.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Use the simpified API that calculates distance between two devices.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Disable verbose while getting p2p distance. With verbose, it shows
warning if ACS redirect is set between the devices. Adds noise
to dmesg logs when a few GPU devices are on the same platform.
Example log:
amdgpu 0000:34:00.0: ACS redirect is set between the client and provider (0000:31:00.0)
amdgpu 0000:34:00.0: to disable ACS redirect for this path, add the kernel parameter:
pci=disable_acs_redir=0000:30:00.0;0000:2e:00.0;0000:33:00.0;0000:2e:10.0
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Allows submitting jobs as gang which needs to run on multiple
engines at the same time.
Basic idea is that we have a global gang submit fence representing when the
gang leader is finally pushed to run on the hardware last.
Jobs submitted as gang are never re-submitted in case of a GPU reset since this
won't work and will just deadlock the hardware immediately again.
v2: fix logic inversion, improve documentation, fix rcu
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
V3:
Fixed psp fence and memory issues for the asic
using smu v13_0_2 when removing amdgpu device.
[Why]:
1. psp_suspend->psp_free_shared_bufs->
psp_ta_free_shared_buf->
amdgpu_bo_free_kernel->
...->amdgpu_bo_release_notify->
amdgpu_fill_buffer
psp will free vram memory used by psp when psp_suspend
is called. But for the asic using smu v13_0_2, because
psp_suspend is called before adev->shutdown is set to
true when removing the first hive device, amdgpu fill_buffer
will be called, which will cause fence issues when evicting
all vram resources in amdgpu vram mgr_fini.
2. Since psp_hw_fini is not called after calling psp_suspend
and psp_suspend only calls psp_ring_stop, the psp ring memory
will not be released when amdgpu device is removed.
[How]:
1. Set shutdown to true before calling amdgpu_device_gpu_recover,
then amdgpu_fill_buffer will not be called when psp_suspend is
called.
2. Free psp ring memory in psp_sw_fini.
Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Adjust removal control flow for smu v13_0_2:
During amdgpu uninstallation, when removing the first
device, the kernel needs to first send a mode1reset message
to all gpu devices. Otherwise, smu initialization will fail
the next time amdgpu is installed.
V2:
1. Update commit comments.
2. Remove the global variable amdgpu_device_remove_cnt
and add a variable to the structure amdgpu_hive_info.
3. Use hive to detect the first removed device instead of
a global variable.
V3:
1. Update commit comments.
2. Split a patch into multiple patches.
3. The current patch does:
a. Add a work mode of AMDGPU_RESET_FOR_DEVICE_REMOVE into
the existing gpu recover path, which make all devices
in hive list only have HW reset but no resume (except
the base IP).
b. Call AMDGPU_RESET_FOR_DEVICE_REMOVE and
AMDGPU_NEED_FULL_RESET mode of amdgpu_device_gpu_recover
in amdgpu_pci_remove when removing the first device in
hive list.
c. When removing the first device, the IP blocks keyword
function call sequence is as follows:
.suspend->mode1reset->.resume(basic ip)->.hw_fini->.early_fini->.sw_fini.
^ |
|-<----------<---------<----|
The first three sequences are because of a call to
amdgpu_device_gpu_recover. The three sequences will be
executed in a loop until all devices in the hive list
are iterated.
The sequences starting from .hw_fini only apply to the
first device. Since .suspend has been called before,
except the resumed phase1 basic ip blocks, all other ip
blocks .hw_fini of current device will do nothing.
d. When removing other devices, the calling sequences is the
same as legacy:
.hw_fini -> .early_fini -> .sw_fini.
Since .suspend has been called when removing the first device,
except the resumed phase1 basic ip blocks, all of other ip
blocks .hw_fini of current device will do nothing.
Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Move common IP init before GMC init so that HDP gets
remapped before GMC init which uses it.
This fixes the Unsupported Request error reported through
AER during driver load. The error happens as a write happens
to the remap offset before real remapping is done.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216373
The error was unnoticed before and got visible because of the commit
referenced below. This doesn't fix anything in the commit below, rather
fixes the issue in amdgpu exposed by the commit. The reference is only
to associate this commit with below one so that both go together.
Fixes: 8795e182b02d ("PCI/portdrv: Don't disable AER reporting in get_port_device_capability()")
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
both get_xgmi_hive and put_xgmi_hive can be skipped since the
reset domain is not necessary for VF
Signed-off-by: Vignesh Chander <Vignesh.Chander@amd.com>
Reviewed-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For SRIOV configuration, host driver control the reset method(either FLR or
heavier chain reset). The host will notify the guest individually with FLR
message if individual GPU within the hive need to be reset. So for guest
side, no need to use hive->reset_domain to replace the original per
device reset_domain
Signed-off-by: shaoyunl <shaoyun.liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
V1:
The psp_cmd_submit_buf function is called by psp_hw_fini to send
TA unload messages to psp to terminate ras, asd and tmr. But when
amdgpu is uninstalled, drm_dev_unplug is called earlier than
psp_hw_fini in amdgpu_pci_remove, the calling order as follows:
static void amdgpu_pci_remove(struct pci_dev *pdev) {
drm_dev_unplug
......
amdgpu_driver_unload_kms->amdgpu_device_fini_hw->...
->.hw_fini->psp_hw_fini->...
->psp_ta_unload->psp_cmd_submit_buf
......
}
The program will return when calling drm_dev_enter in psp_cmd_submit_buf.
So the call to drm_dev_enter in psp_cmd_submit_buf should be
removed, so that the TA unload messages can be sent to the psp
when amdgpu is uninstalled.
V2:
1. Restore psp_cmd_submit_buf to its original code.
2. Move drm_dev_unplug call after amdgpu_driver_unload_kms in
amdgpu_pci_remove.
3. Since amdgpu_device_fini_hw is called by amdgpu_driver_unload_kms,
remove the unplug check to release device mmio resource in
amdgpu_device_fini_hw before calling drm_dev_unplug.
Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why] Devices with CPU XGMI iolink do not support PCIe peer access.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
