aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
AgeCommit message (Collapse)AuthorFilesLines
2024-04-26drm/amdgpu: add protype for print ip stateSunil Khatri1-0/+1
Add the protoype for print ip state to be used to print the registers in devcoredump during a gpu reset. Signed-off-by: Sunil Khatri <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-04-26drm/amdgpu: add prototype for ip dumpSunil Khatri1-0/+1
Add the prototype to dump ip registers for all ips of different asics and set them to NULL for now. Based on the requirement add a function pointer for each of them. Signed-off-by: Sunil Khatri <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-01-31drm/amdgpu: Reset IH OVERFLOW_CLEAR bitFriedrich Vock1-0/+6
Allows us to detect subsequent IH ring buffer overflows as well. Cc: Joshua Ashton <[email protected]> Cc: Alex Deucher <[email protected]> Cc: Christian König <[email protected]> Cc: [email protected] Signed-off-by: Friedrich Vock <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-01-15drm/amdgpu: Clean up errors in navi10_ih.cchenxuebing1-2/+1
Fix the following errors reported by checkpatch: ERROR: that open brace { should be on the previous line Signed-off-by: chenxuebing <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-10-05drm/amdgpu: Drop unnecessary return statementsSrinivasan Shanmugam1-4/+0
There is no reason to call return at the end of function that returns void. Fixes the below: WARNING: void function return statements are not generally useful Thus remove such a statement in the affected functions. Cc: Christian König <[email protected]> Cc: Alex Deucher <[email protected]> Cc: "Pan, Xinhui" <[email protected]> Signed-off-by: Srinivasan Shanmugam <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-09-20drm/amdgpu: Use function for IP version checkLijo Lazar1-2/+2
Use an inline function for version check. Gives more flexibility to handle any format changes. Signed-off-by: Lijo Lazar <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2023-07-12drm/amdgpu: Increase soft IH ring sizePhilip Yang1-2/+2
Retry faults are delegated to soft IH ring and then processed by deferred worker. Current soft IH ring size PAGE_SIZE can store 128 entries, which may overflow and drop retry faults, causes HW stucks because the retry fault is not recovered. Increase soft IH ring size to 8KB, enough to store 256 CAM entries because we clear the CAM entry after handling the retry fault from soft ring. Define macro IH_RING_SIZE and IH_SW_RING_SIZE to remove duplicate constant. Show warning message if soft IH ring overflows with CAM enabled because this should not happen. Signed-off-by: Philip Yang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-08-16drm/amdgpu: Fix interrupt handling on ih_soft ringMukul Joshi1-1/+6
There are no backing hardware registers for ih_soft ring. As a result, don't try to access hardware registers for read and write pointers when processing interrupts on the IH soft ring. Signed-off-by: Mukul Joshi <[email protected]> Acked-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-05-04drm/amdgpu: simplify the return expression of navi10_ih_hw_init()Minghao Chi1-6/+1
Simplify the return expression. Reported-by: Zeal Robot <[email protected]> Signed-off-by: Minghao Chi <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2022-04-08drm/amdgpu: expand cg_flags from u32 to u64Evan Quan1-1/+1
With this, we can support more CG flags. Signed-off-by: Evan Quan <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-12-01drm/amdgpu: handle IH ring1 overflowPhilip Yang1-0/+1
IH ring1 is used to process GPU retry fault, overflow is enabled to drain retry fault because we want receive other interrupts while handling retry fault to recover range. There is no overflow flag set when wptr pass rptr. Use timestamp of rptr and wptr to handle overflow and drain retry fault. If fault timestamp goes backward, the fault is filtered and should not be processed. Drain fault is finished if processed_timestamp is equal to or larger than checkpoint timestamp. Add amdgpu_ih_functions interface decode_iv_ts for different chips to get timestamp from IV entry with different iv size and timestamp offset. amdgpu_ih_decode_iv_ts_helper is used for vega10, vega20, navi10. Signed-off-by: Philip Yang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-11-24drm/amdgpu: enable Navi retry fault wptr overflowPhilip Yang1-21/+12
If xnack is on, VM retry fault interrupt send to IH ring1, and ring1 will be full quickly. IH cannot receive other interrupts, this causes deadlock if migrating buffer using sdma and waiting for sdma done while handling retry fault. Remove VMC from IH storm client, enable ring1 write pointer overflow, then IH will drop retry fault interrupts and be able to receive other interrupts while driver is handling retry fault. IH ring1 write pointer doesn't writeback to memory by IH, and ring1 write pointer recorded by self-irq is not updated, so always read the latest ring1 write pointer from register. Signed-off-by: Philip Yang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-11-24drm/amdgpu: enable Navi 48-bit IH timestamp counterPhilip Yang1-0/+1
By default this timestamp is 32 bit counter. It gets overflowed in around 10 minutes. Signed-off-by: Philip Yang <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu: convert IP version array to include instancesAlex Deucher1-2/+2
Allow us to query instances versions more cleanly. Instancing support is not consistent unfortunately. SDMA is a good example. Sienna cichlid has 4 total SDMA instances, each enumerated separately (HWIDs 42, 43, 68, 69). Arcturus has 8 total SDMA instances, but they are enumerated as multiple instances of the same HWIDs (4x HWID 42, 4x HWID 43). UMC is another example. On most chips there are multiple instances with the same HWID. This allows us to support both forms. v2: rebase v3: clarify instancing support Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-10-04drm/amdgpu/navi10_ih: convert to IP version checkingAlex Deucher1-8/+5
Use IP versions rather than asic_type to differentiate IP version specific features. Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-06-08drm/amdgpu: Use PSP to program IH_RB_CNTL_RING1/2 on SRIOVRohit Khaire1-5/+15
This is similar to IH_RB_CNTL programming in navi10_ih_toggle_ring_interrupts Signed-off-by: Rohit Khaire <[email protected]> Acked-by: Christian König <[email protected]> Reviewed-by: Horace Chen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-06-04drm/amdgpu: add yellow carp support for ih blockAaron Liu1-0/+1
This patch adds the support for yellow carp ih block. Signed-off-by: Aaron Liu <[email protected]> Reviewed-by: Huang Rui <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-05-22Merge drm/drm-next into drm-misc-nextThomas Zimmermann1-2/+19
Backmerging from drm/drm-next to the patches for AMD devices for v5.14. Signed-off-by: Thomas Zimmermann <[email protected]>
2021-05-19drm/amdgpu: Handle IOMMU enabled case.Andrey Grodzovsky1-4/+0
Problem: Handle all DMA IOMMU group related dependencies before the group is removed. Those manifest themself in that when IOMMU enabled DMA map/unmap is dependent on the presence of IOMMU group the device belongs to but, this group is released once the device is removed from PCI topology. Fix: Expedite all such unmap operations to pci remove driver callback. v5: Drop IOMMU notifier and switch to lockless call to ttm_tt_unpopulate v6: Drop the BO unamp list v7: Drop amdgpu_gart_fini In amdgpu_ih_ring_fini do uncinditional check (!ih->ring) to avoid freeing uniniitalized rings. Call amdgpu_ih_ring_fini unconditionally. v8: Add deatiled explanation Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2021-05-19drm/amdgpu: Split amdgpu_device_fini into early and lateAndrey Grodzovsky1-1/+1
Some of the stuff in amdgpu_device_fini such as HW interrupts disable and pending fences finilization must be done right away on pci_remove while most of the stuff which relates to finilizing and releasing driver data structures can be kept until drm_driver.release hook is called, i.e. when the last device reference is dropped. v4: Change functions prefix early->hw and late->sw Signed-off-by: Andrey Grodzovsky <[email protected]> Acked-by: Christian König <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2021-05-19drm/amd/amdgpu: psp program IH_RB_CTRL on sienna_cichlidYuBiao Wang1-2/+18
[Why] IH_RB_CNTL is blocked by PSP so we need to ask psp to help config it. [How] Move psp ip block before ih, and use psp to program IH_RB_CNTL under sriov. Reviewed-by: Chen, Horace <[email protected]> Signed-off-by: YuBiao Wang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2021-05-19drm/amd/amdgpu: add ih ip block for beige_gobyChengming Gui1-0/+1
Enable ih block for beige_goby, same as dimgrey_cavefish Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Tao Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: drop psp ih programming for sriov guest on naviHawking Zhang1-16/+2
the psp access ih path is not needed in navi Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Alex Deucher <[email protected]> Reviewed-by: Jane Jian <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: de-initialize software ih ringHawking Zhang1-0/+1
tear down software ih ring and its state. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: set ih soft ring enabled flag for vega and naviHawking Zhang1-0/+3
software ih ring is enabled in vega10 and navi ih block by default. Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: retire the vega20 code path from navi10 ih blockHawking Zhang1-38/+2
already switched to vega20 ih block for vega20 and arcturus. no need to add vega20 support in navi10 ih block Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: switch to common decode iv helperHawking Zhang1-46/+1
The iv format is the same for all the soc15 adpater and onwards and can share a common function to decode iv. Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: use cached ih rb control reg offsets for navi10Hawking Zhang1-38/+14
all the ih rb control register offsets are cached at the beginning of navi10 ih_sw_init. Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: switch to ih_enable_ring for navi10Hawking Zhang1-90/+12
use navi10_ih_enable_ring to enable all the available ring buffers for navi1x and onwards Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: switch to ih_toggle_interrupts for navi10Hawking Zhang1-133/+33
replace ih_enable_interrupts and ih_disable_interrupts with ih_toggle_interrupts Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: switch to ih_init_register_offset for navi10Hawking Zhang1-0/+3
Initialize ih control registers offset through helper function navi10_ih_init_register_offset. Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: add helper to toggle ih ring interrupts for navi10Hawking Zhang1-0/+45
navi10_ih_toggle_ring_interrupts will be used to enable/disable an ih ring interrupts for navi1x and onwards Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: add helper to enable an ih ring for navi10Hawking Zhang1-0/+52
navi10_ih_enable_ring will be used to enable an ih ring for navi1x and onwards Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-23drm/amdgpu: add helper to init ih ring regs for navi10Hawking Zhang1-0/+47
navi10_ih_init_register_offset will be used to init register offset for all the available ih rings Signed-off-by: Hawking Zhang <[email protected]> Acked-by: Christian König <[email protected]> Acked-by: Felix Kuehling <[email protected]> Reviewed-by: Dennis Li <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-12-01drm/amd/amdgpu/navi10_ih: Add descriptions for 'ih' and 'entry'Lee Jones1-0/+5
Fixes the following W=1 kernel build warning(s): drivers/gpu/drm/amd/amdgpu/navi10_ih.c:453: warning: Function parameter or member 'ih' not described in 'navi10_ih_get_wptr' drivers/gpu/drm/amd/amdgpu/navi10_ih.c:512: warning: Function parameter or member 'ih' not described in 'navi10_ih_decode_iv' drivers/gpu/drm/amd/amdgpu/navi10_ih.c:512: warning: Function parameter or member 'entry' not described in 'navi10_ih_decode_iv' drivers/gpu/drm/amd/amdgpu/navi10_ih.c:552: warning: Function parameter or member 'ih' not described in 'navi10_ih_irq_rearm' drivers/gpu/drm/amd/amdgpu/navi10_ih.c:585: warning: Function parameter or member 'ih' not described in 'navi10_ih_set_rptr' Cc: Alex Deucher <[email protected]> Cc: "Christian König" <[email protected]> Cc: David Airlie <[email protected]> Cc: Daniel Vetter <[email protected]> Cc: Alex Sierra <[email protected]> Cc: [email protected] Cc: [email protected] Signed-off-by: Lee Jones <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-11-24drm/amdgpu: enabled software IH ring for NaviChristian König1-0/+7
Felix pointed out that we need this for Navi as well. Signed-off-by: Christian König <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-10-12drm/amdgpu: add ih ip block for dimgrey_cavefishTao Zhou1-0/+1
Enable ih block for dimgrey_cavefish, same as navy_flounder. Signed-off-by: Tao Zhou <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Reviewed-by: Jiansong Chen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-10-05drm/amdgpu: use gpu virtual address for interrupt packet write space for vangoghHuang Rui1-2/+5
The interrupts are not stable while uses guest physical address (GPA) for interrupt packet write space even on direct loading case. v2: make condition more readable Signed-off-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-10-05drm/amdgpu: add van gogh support for ih blockHuang Rui1-0/+1
This patch adds the support for van gogh ih block. Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-09-03drm/amdgpu: enable ih1 ih2 for Arcturus onlyAlex Sierra1-11/+19
Enable multi-ring ih1 and ih2 for Arcturus only. For Navi10 family multi-ring has been disabled. Apparently, having multi-ring enabled in Navi was causing continus page fault interrupts. Further investigation is needed to get to the root cause. Related issue link: https://gitlab.freedesktop.org/drm/amd/-/issues/1279 Signed-off-by: Alex Sierra <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-07-21drm/amdgpu: add timeout flush mechanism to update wptr for self interrupt (v2)Chengming Gui1-0/+45
outstanding log reaches threshold will trigger IH ring1/2's wptr reported, that will avoid generating interrupts to ring0 too frequent. But if ring1/2's wptr hasn't been increased for a long time, the outstanding log can't reach threshold so that driver can't get latest wptr info and miss some interrupts. v2: squash in warning fix Signed-off-by: Chengming Gui <[email protected]> Reviewed-by: Feifei Xu <[email protected]> Acked-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-07-15drm/amdgpu: add ih ip block for navy_flounderJiansong Chen1-0/+1
navy_flounder has the same osssys IP verison with sienna_cichlid, follow its setting. Signed-off-by: Jiansong Chen <[email protected]> Reviewed-by: Tao Zhou <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-06-03drm/amdgpu: add ih ip block for sienna_cichlidLikun Gao1-4/+17
Update IH handling for sienna_cichlid Signed-off-by: Likun Gao <[email protected]> Reviewed-by: Hawking Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-04-03amdgpu/drm: remove psp access on navi10 for sriovAlex Sierra1-9/+9
Navi ASICs don't require to access through PSP to osssys registers. This on SR-IOV configuration. Signed-off-by: Alex Sierra <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-04-01drm/amdgpu: reroute VMC and UMD to IH ring 1 for oss v5Alex Sierra1-0/+19
[Why] Due Page faults can easily overwhelm the interrupt handler. So to make sure that we never lose valuable interrupts on the primary ring we re-route page faults to IH ring 1. It also facilitates the recovery page process, since it's already running from a process context. This is valid for Arcturus and future Navi generation GPUs. [How] Setting IH_CLIENT_CFG_DATA for VMC and UMD IH clients. Signed-off-by: Alex Sierra <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-04-01drm/amdgpu: call psp to program ih cntl in SR-IOV for NaviAlex Sierra1-10/+80
call psp to program ih cntl in SR-IOV if supported on Navi and Arcturus. Signed-off-by: Alex Sierra <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-04-01drm/amdgpu: enable IH ring 1 and ring 2 for naviAlex Sierra1-16/+189
Support added into IH to enable ring1 and ring2 for navi10_ih. Signed-off-by: Alex Sierra <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-03-05drm/amdgpu: Rearm IRQ in Navi10 SR-IOV if IRQ lostSamir Dhume1-0/+36
Ported from Vega10. SDMA stress tests sometimes see IRQ lost. Signed-off-by: Samir Dhume <[email protected]> Reviewed-by: Monk Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2020-01-22drm/amdgpu: remove unnecessary conversion to boolNirmoy Das1-1/+1
Better clean that up before some automation starts to complain about it Signed-off-by: Nirmoy Das <[email protected]> Acked-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2019-12-23drm/amdgpu: Remove unneeded variable 'ret' in navi10_ih.cMa Feng1-2/+1
Fixes coccicheck warning: drivers/gpu/drm/amd/amdgpu/navi10_ih.c:113:5-8: Unneeded variable: "ret". Return "0" on line 182 Reported-by: Hulk Robot <[email protected]> Signed-off-by: Ma Feng <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.