The LOGINIT, LOGINTR, LOGRM, and LOGPMU buffers are circular buffers
that have printf-like logs from GSP-RM and PMU encoded in them.
LOGINIT, LOGINTR, and LOGRM are allocated by Nouveau and their DMA
addresses are passed to GSP-RM during initialization. The buffers are
required for GSP-RM to initialize properly.
LOGPMU is also allocated by Nouveau, but its contents are updated
when Nouveau receives an NV_VGPU_MSG_EVENT_UCODE_LIBOS_PRINT RPC from
GSP-RM. Nouveau then copies the RPC to the buffer.
The messages are encoded as an array of variable-length structures that
contain the parameters to an NV_PRINTF call. The format string and
parameter count are stored in a special ELF image that contains only
logging strings. This image is not currently shipped with the Nvidia
driver.
There are two methods to extract the logs.
OpenRM tries to load the logging ELF, and if present, parses the log
buffers in real time and outputs the strings to the kernel console.
Alternatively, and this is the method used by this patch, the buffers
can be exposed to user space, and a user-space tool (along with the
logging ELF image) can parse the buffer and dump the logs.
This method has the advantage that it allows the buffers to be parsed
even when the logging ELF file is not available to the user. However,
it has the disadvantage the debugfs entries need to remain until the
driver is unloaded.
The buffers are exposed via debugfs. If GSP-RM fails to initialize, then
Nouveau immediately shuts down the GSP interface. This would normally
also deallocate the logging buffers, thereby preventing the user from
capturing the debug logs.
To avoid this, introduce the keep-gsp-logging command line parameter. If
specified, and if at least one logging buffer has content, then Nouveau
will migrate these buffers into new debugfs entries that are retained
until the driver unloads.
An end-user can capture the logs using the following commands:
cp /sys/kernel/debug/nouveau/<path>/loginit loginit
cp /sys/kernel/debug/nouveau/<path>/logrm logrm
cp /sys/kernel/debug/nouveau/<path>/logintr logintr
cp /sys/kernel/debug/nouveau/<path>/logpmu logpmu
where (for a PCI device) <path> is the PCI ID of the GPU (e.g.
0000:65:00.0).
Since LOGPMU is not needed for normal GSP-RM operation, it is only
created if debugfs is available. Otherwise, the
NV_VGPU_MSG_EVENT_UCODE_LIBOS_PRINT RPCs are ignored.
A simple way to test the buffer migration feature is to have
nvkm_gsp_init() return an error code.
Tested-by: Ben Skeggs <bskeggs@nvidia.com>
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20241030202952.694055-2-ttabi@nvidia.com
Currently we allocate all 3 levels of radix3 page tables using
nvkm_gsp_mem_ctor(), which uses dma_alloc_coherent() for allocating all of
the relevant memory. This can end up failing in scenarios where the system
has very high memory fragmentation, and we can't find enough contiguous
memory to allocate level 2 of the page table.
Currently, this can result in runtime PM issues on systems where memory
fragmentation is high - as we'll fail to allocate the page table for our
suspend/resume buffer:
kworker/10:2: page allocation failure: order:7, mode:0xcc0(GFP_KERNEL),
nodemask=(null),cpuset=/,mems_allowed=0
CPU: 10 PID: 479809 Comm: kworker/10:2 Not tainted
6.8.6-201.ChopperV6.fc39.x86_64 #1
Hardware name: SLIMBOOK Executive/Executive, BIOS N.1.10GRU06 02/02/2024
Workqueue: pm pm_runtime_work
Call Trace:
<TASK>
dump_stack_lvl+0x64/0x80
warn_alloc+0x165/0x1e0
? __alloc_pages_direct_compact+0xb3/0x2b0
__alloc_pages_slowpath.constprop.0+0xd7d/0xde0
__alloc_pages+0x32d/0x350
__dma_direct_alloc_pages.isra.0+0x16a/0x2b0
dma_direct_alloc+0x70/0x270
nvkm_gsp_radix3_sg+0x5e/0x130 [nouveau]
r535_gsp_fini+0x1d4/0x350 [nouveau]
nvkm_subdev_fini+0x67/0x150 [nouveau]
nvkm_device_fini+0x95/0x1e0 [nouveau]
nvkm_udevice_fini+0x53/0x70 [nouveau]
nvkm_object_fini+0xb9/0x240 [nouveau]
nvkm_object_fini+0x75/0x240 [nouveau]
nouveau_do_suspend+0xf5/0x280 [nouveau]
nouveau_pmops_runtime_suspend+0x3e/0xb0 [nouveau]
pci_pm_runtime_suspend+0x67/0x1e0
? __pfx_pci_pm_runtime_suspend+0x10/0x10
__rpm_callback+0x41/0x170
? __pfx_pci_pm_runtime_suspend+0x10/0x10
rpm_callback+0x5d/0x70
? __pfx_pci_pm_runtime_suspend+0x10/0x10
rpm_suspend+0x120/0x6a0
pm_runtime_work+0x98/0xb0
process_one_work+0x171/0x340
worker_thread+0x27b/0x3a0
? __pfx_worker_thread+0x10/0x10
kthread+0xe5/0x120
? __pfx_kthread+0x10/0x10
ret_from_fork+0x31/0x50
? __pfx_kthread+0x10/0x10
ret_from_fork_asm+0x1b/0x30
Luckily, we don't actually need to allocate coherent memory for the page
table thanks to being able to pass the GPU a radix3 page table for
suspend/resume data. So, let's rewrite nvkm_gsp_radix3_sg() to use the sg
allocator for level 2. We continue using coherent allocations for lvl0 and
1, since they only take a single page.
V2:
* Don't forget to actually jump to the next scatterlist when we reach the
end of the scatterlist we're currently on when writing out the page table
for level 2
Signed-off-by: Lyude Paul <lyude@redhat.com>
Cc: stable@vger.kernel.org
Reviewed-by: Ben Skeggs <bskeggs@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240429182318.189668-2-lyude@redhat.com
Add the NVreg_RegistryDwords command line parameter, which allows
specifying additional registry keys to be sent to GSP-RM. This
allows additional configuration, debugging, and experimentation
with GSP-RM, which uses these keys to alter its behavior.
Note that these keys are passed as-is to GSP-RM, and Nouveau does
not parse them. This is in contrast to the Nvidia driver, which may
parse some of the keys to configure some functionality in concert with
GSP-RM. Therefore, any keys which also require action by the driver
may not function correctly when passed by Nouveau. Caveat emptor.
The name and format of NVreg_RegistryDwords is the same as used by
the Nvidia driver, to maintain compatibility.
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240417215317.3490856-1-ttabi@nvidia.com
Using the end of rpc->entries[] for addressing runs into both compile-time
and run-time detection of accessing beyond the end of the array. Use the
base pointer instead, since was allocated with the additional bytes for
storing the strings. Avoids the following warning in future GCC releases
with support for __counted_by:
In function 'fortify_memcpy_chk',
inlined from 'r535_gsp_rpc_set_registry' at ../drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c:1123:3:
../include/linux/fortify-string.h:553:25: error: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror=attribute-warning]
553 | __write_overflow_field(p_size_field, size);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
for this code:
strings = (char *)&rpc->entries[NV_GSP_REG_NUM_ENTRIES];
...
memcpy(strings, r535_registry_entries[i].name, name_len);
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240330141159.work.063-kees@kernel.org
Pull drm fixes from Dave Airlie:
"Fixes from the last week (or 3 weeks in amdgpu case), after amdgpu,
it's xe and nouveau then a few scattered core fixes.
core:
- fix rounding in drm_fixp2int_round()
bridge:
- fix documentation for DRM_BRIDGE_OP_EDID
sun4i:
- fix 64-bit division on 32-bit architectures
tests:
- fix dependency on DRM_KMS_HELPER
probe-helper:
- never return negative values from .get_modes() plus driver fixes
xe:
- invalidate userptr vma on page pin fault
- fail early on sysfs file creation error
- skip VMA pinning on xe_exec if no batches
nouveau:
- clear bo resource bus after eviction
- documentation fixes
- don't check devinit disable on GSP
amdgpu:
- Freesync fixes
- UAF IOCTL fixes
- Fix mmhub client ID mapping
- IH 7.0 fix
- DML2 fixes
- VCN 4.0.6 fix
- GART bind fix
- GPU reset fix
- SR-IOV fix
- OD table handling fixes
- Fix TA handling on boards without display hardware
- DML1 fix
- ABM fix
- eDP panel fix
- DPPCLK fix
- HDCP fix
- Revert incorrect error case handling in ioremap
- VPE fix
- HDMI fixes
- SDMA 4.4.2 fix
- Other misc fixes
amdkfd:
- Fix duplicate BO handling in process restore"
* tag 'drm-next-2024-03-22' of https://gitlab.freedesktop.org/drm/kernel: (50 commits)
drm/amdgpu/pm: Don't use OD table on Arcturus
drm/amdgpu: drop setting buffer funcs in sdma442
drm/amd/display: Fix noise issue on HDMI AV mute
drm/amd/display: Revert Remove pixle rate limit for subvp
Revert "drm/amdgpu/vpe: don't emit cond exec command under collaborate mode"
Revert "drm/amd/amdgpu: Fix potential ioremap() memory leaks in amdgpu_device_init()"
drm/amd/display: Add a dc_state NULL check in dc_state_release
drm/amd/display: Return the correct HDCP error code
drm/amd/display: Implement wait_for_odm_update_pending_complete
drm/amd/display: Lock all enabled otg pipes even with no planes
drm/amd/display: Amend coasting vtotal for replay low hz
drm/amd/display: Fix idle check for shared firmware state
drm/amd/display: Update odm when ODM combine is changed on an otg master pipe with no plane
drm/amd/display: Init DPPCLK from SMU on dcn32
drm/amd/display: Add monitor patch for specific eDP
drm/amd/display: Allow dirty rects to be sent to dmub when abm is active
drm/amd/display: Override min required DCFCLK in dml1_validate
drm/amdgpu: Bypass display ta if display hw is not available
drm/amdgpu: correct the KGQ fallback message
drm/amdgpu/pm: Check the validity of overdiver power limit
...
Nouveau deallocates a few buffers post GPU init which are required for GPU suspend/resume to function correctly.
This is likely not as big an issue on systems where the NVGPU is the only GPU, but on multi-GPU set ups it leads to a regression where the kernel module errors and results in a system-wide rendering freeze.
This commit addresses that regression by moving the two buffers required for suspend and resume to be deallocated at driver unload instead of post init.
Fixes: 042b5f8384 ("drm/nouveau: fix several DMA buffer leaks")
Signed-off-by: Sid Pranjale <sidpranjale127@protonmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Nouveau manages GSP-RM DMA buffers with nvkm_gsp_mem objects. Several of
these buffers are never dealloced. Some of them can be deallocated
right after GSP-RM is initialized, but the rest need to stay until the
driver unloads.
Also futher bullet-proof these objects by poisoning the buffer and
clearing the nvkm_gsp_mem object when it is deallocated. Poisoning
the buffer should trigger an error (or crash) from GSP-RM if it tries
to access the buffer after we've deallocated it, because we were wrong
about when it is safe to deallocate.
Finally, change the mem->size field to a size_t because that's the same
type that dma_alloc_coherent expects.
Cc: <stable@vger.kernel.org> # v6.7
Fixes: 176fdcbddf ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202230608.1981026-1-ttabi@nvidia.com
Pull drm fixes from Dave Airlie:
"This is just a wrap up of fixes from the last few days. It has the
proper fix to the i915/xe collision, we can clean up what you did
later once rc1 lands.
Otherwise it's a few other i915, a v3d, rockchip and a nouveau fix to
make GSP load on some original Turing GPUs.
i915:
- Fixes for kernel-doc warnings enforced in linux-next
- Another build warning fix for string formatting of intel_wakeref_t
- Display fixes for DP DSC BPC and C20 PLL state verification
v3d:
- register readout fix
rockchip:
- two build warning fixes
nouveau:
- fix GSP loading on Turing with different nvdec configuration"
* tag 'drm-next-2024-01-15-1' of git://anongit.freedesktop.org/drm/drm:
nouveau/gsp: handle engines in runl without nonstall interrupts.
drm/i915/perf: reconcile Excess struct member kernel-doc warnings
drm/i915/guc: reconcile Excess struct member kernel-doc warnings
drm/i915/gt: reconcile Excess struct member kernel-doc warnings
drm/i915/gem: reconcile Excess struct member kernel-doc warnings
drm/i915/dp: Fix the max DSC bpc supported by source
drm/i915: don't make assumptions about intel_wakeref_t type
drm/i915/dp: Fix the PSR debugfs entries wrt. MST connectors
drm/i915/display: Fix C20 pll selection for state verification
drm/v3d: Fix support for register debugging on the RPi 4
drm/rockchip: vop2: Drop unused if_dclk_rate variable
drm/rockchip: vop2: Drop superfluous include
Currently we get an error from ACPI because both of these arguments expect
a single argument, and we don't provide one. I'm not totally clear on what
that argument does, but we're able to find the missing value from
_acpiCacheMethodData() in src/kernel/platform/acpi_common.c in nvidia's
driver. So, let's add that - which doesn't get eDP displays to power on
quite yet, but gets rid of the argument warning at least.
Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231222043308.3090089-7-airlied@gmail.com
Fake flexible arrays (zero-length and one-element arrays) are deprecated,
and should be replaced by flexible-array members. So, replace
zero-length array with a flexible-array member in `struct
PACKED_REGISTRY_TABLE`.
Also annotate array `entries` with `__counted_by()` to prepare for the
coming implementation by GCC and Clang of the `__counted_by` attribute.
Flexible array members annotated with `__counted_by` can have their
accesses bounds-checked at run-time via `CONFIG_UBSAN_BOUNDS` (for array
indexing) and `CONFIG_FORTIFY_SOURCE` (for strcpy/memcpy-family functions).
This fixes multiple -Warray-bounds warnings:
drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c:1069:29: warning: array subscript 0 is outside array bounds of 'PACKED_REGISTRY_ENTRY[0]' [-Warray-bounds=]
drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c:1070:29: warning: array subscript 0 is outside array bounds of 'PACKED_REGISTRY_ENTRY[0]' [-Warray-bounds=]
drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c:1071:29: warning: array subscript 0 is outside array bounds of 'PACKED_REGISTRY_ENTRY[0]' [-Warray-bounds=]
drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c:1072:29: warning: array subscript 0 is outside array bounds of 'PACKED_REGISTRY_ENTRY[0]' [-Warray-bounds=]
While there, also make use of the struct_size() helper, and address
checkpatch.pl warning:
WARNING: please, no spaces at the start of a line
This results in no differences in binary output.
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZVZbX7C5suLMiBf+@work
The nvidia driver sets these two basic registry entries always,
so copy it.
Reviewed-by: Danilo Krummrich <dakr@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This original one was backwards, compared to traces from nvidia driver.
Reviewed-by: Danilo Krummrich <dakr@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This moves the initial effort to the latest 535 firmware.
The gsp msg structs have changed, and the message passing also.
The wpr also seems to have some struct changes.
This version of the firmware will be what we are stuck on for a while,
until we can refactor the driver and work out a better path forward.
Reviewed-by: Danilo Krummrich <dakr@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This commit adds the initial code needed to boot the GSP-RM firmware
provided by NVIDIA, bringing with it the beginnings of Ada support.
Until it's had more testing and time to bake, support is disabled by
default (except on Ada). GSP-RM usage can be enabled by passing the
"config=NvGspRm=1" module option.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230918202149.4343-33-skeggsb@gmail.com
