aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/i915_perf.c
AgeCommit message (Collapse)AuthorFilesLines
2020-11-16drm: fix some kernel-doc markupsMauro Carvalho Chehab1-3/+5
Some identifiers have different names between their prototypes and the kernel-doc markup. Others need to be fixed, as kernel-doc markups should use this format: identifier - description Signed-off-by: Mauro Carvalho Chehab <[email protected]> Acked-by: Jani Nikula <[email protected]> Signed-off-by: Daniel Vetter <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/12d4ca26f6843618200529ce5445063734d38c04.1605521731.git.mchehab+huawei@kernel.org
2020-09-07drm/i915: Convert i915_perf to ww locking as wellMaarten Lankhorst1-15/+42
We have the ordering of timeline->mutex vs resv_lock wrong, convert the i915_pin_vma and intel_context_pin as well to future-proof this. We may need to do future changes to do this more transaction-like, and only get down to a single i915_gem_ww_ctx, but for now this should work. Signed-off-by: Maarten Lankhorst <[email protected]> Reviewed-by: Thomas Hellström <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Signed-off-by: Joonas Lahtinen <[email protected]>
2020-07-10drm/i915/perf: Use GTT when saving/restoring engine GPRUmesh Nerlige Ramappa1-0/+1
MI_STORE_REGISTER_MEM and MI_LOAD_REGISTER_MEM need to know which translation to use when saving restoring the engine general purpose registers to and from the GT scratch. Since GT scratch is mapped to ggtt, we need to set an additional bit in the command to use GTT. Fixes: daed3e44396d17 ("drm/i915/perf: implement active wait for noa configurations") Suggested-by: Prathap Kumar Valsan <[email protected]> Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]> Reviewed-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Signed-off-by: Chris Wilson <[email protected]>
2020-07-08drm/i915: Release shortlived maps of longlived objectsChris Wilson1-2/+2
Some objects we map once during their construction, and then never access their mappings again, even if they are kept around for the duration of the driver. Keeping those pages mapped, often vmapped, is therefore wasteful and we should release the maps as soon as we no longer need them. Signed-off-by: Chris Wilson <[email protected]> Reviewed-by: Matthew Auld <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-07-08drm/i915/sseu: Move sseu_info under gt_infoVenkata Sandeep Dhanalakota1-5/+4
SSEUs are a GT capability, so track them under gt_info. Signed-off-by: Venkata Sandeep Dhanalakota <[email protected]> Signed-off-by: Daniele Ceraolo Spurio <[email protected]> Cc: Tvrtko Ursulin <[email protected]> Cc: Andi Shyti <[email protected]> Reviewed-by: Chris Wilson <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-06-10Merge branch 'uaccess.i915' of ↵Linus Torvalds1-3/+0
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull i915 uaccess updates from Al Viro: "Low-hanging fruit in i915; there are several trickier followups, but that'll wait for the next cycle" * 'uaccess.i915' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: i915:get_engines(): get rid of pointless access_ok() i915: alloc_oa_regs(): get rid of pointless access_ok() i915 compat ioctl(): just use drm_ioctl_kernel() i915: switch copy_perf_config_registers_or_number() to unsafe_put_user() i915: switch query_{topology,engine}_info() to copy_to_user()
2020-06-09mmap locking API: convert mmap_sem commentsMichel Lespinasse1-1/+1
Convert comments that reference mmap_sem to reference mmap_lock instead. [[email protected]: fix up linux-next leftovers] [[email protected]: s/lockaphore/lock/, per Vlastimil] [[email protected]: more linux-next fixups, per Michel] Signed-off-by: Michel Lespinasse <[email protected]> Signed-off-by: Andrew Morton <[email protected]> Reviewed-by: Vlastimil Babka <[email protected]> Reviewed-by: Daniel Jordan <[email protected]> Cc: Davidlohr Bueso <[email protected]> Cc: David Rientjes <[email protected]> Cc: Hugh Dickins <[email protected]> Cc: Jason Gunthorpe <[email protected]> Cc: Jerome Glisse <[email protected]> Cc: John Hubbard <[email protected]> Cc: Laurent Dufour <[email protected]> Cc: Liam Howlett <[email protected]> Cc: Matthew Wilcox <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Ying Han <[email protected]> Link: http://lkml.kernel.org/r/[email protected] Signed-off-by: Linus Torvalds <[email protected]>
2020-06-02Merge tag 'drm-next-2020-06-02' of git://anongit.freedesktop.org/drm/drmLinus Torvalds1-286/+291
Pull drm updates from Dave Airlie: "Highlights: - Core DRM had a lot of refactoring around managed drm resources to make drivers simpler. - Intel Tigerlake support is on by default - amdgpu now support p2p PCI buffer sharing and encrypted GPU memory Details: core: - uapi: error out EBUSY when existing master - uapi: rework SET/DROP MASTER permission handling - remove drm_pci.h - drm_pci* are now legacy - introduced managed DRM resources - subclassing support for drm_framebuffer - simple encoder helper - edid improvements - vblank + writeback documentation improved - drm/mm - optimise tree searches - port drivers to use devm_drm_dev_alloc dma-buf: - add flag for p2p buffer support mst: - ACT timeout improvements - remove drm_dp_mst_has_audio - don't use 2nd TX slot - spec recommends against it bridge: - dw-hdmi various improvements - chrontel ch7033 support - fix stack issues with old gcc hdmi: - add unpack function for drm infoframe fbdev: - misc fbdev driver fixes i915: - uapi: global sseu pinning - uapi: OA buffer polling - uapi: remove generated perf code - uapi: per-engine default property values in sysfs - Tigerlake GEN12 enabled. - Lots of gem refactoring - Tigerlake enablement patches - move to drm_device logging - Icelake gamma HW readout - push MST link retrain to hotplug work - bandwidth atomic helpers - ICL fixes - RPS/GT refactoring - Cherryview full-ppgtt support - i915 locking guidelines documented - require linear fb stride to be 512 multiple on gen9 - Tigerlake SAGV support amdgpu: - uapi: encrypted GPU memory handling - uapi: add MEM_SYNC IB flag - p2p dma-buf support - export VRAM dma-bufs - FRU chip access support - RAS/SR-IOV updates - Powerplay locking fixes - VCN DPG (powergating) enablement - GFX10 clockgating fixes - DC fixes - GPU reset fixes - navi SDMA fix - expose FP16 for modesetting - DP 1.4 compliance fixes - gfx10 soft recovery - Improved Critical Thermal Faults handling - resizable BAR on gmc10 amdkfd: - uapi: GWS resource management - track GPU memory per process - report PCI domain in topology radeon: - safe reg list generator fixes nouveau: - HD audio fixes on recent systems - vGPU detection (fail probe if we're on one, for now) - Interlaced mode fixes (mostly avoidance on Turing, which doesn't support it) - SVM improvements/fixes - NVIDIA format modifier support - Misc other fixes. adv7511: - HDMI SPDIF support ast: - allocate crtc state size - fix double assignment - fix suspend bochs: - drop connector register cirrus: - move to tiny drivers. exynos: - fix imported dma-buf mapping - enable runtime PM - fixes and cleanups mediatek: - DPI pin mode swap - config mipi_tx current/impedance lima: - devfreq + cooling device support - task handling improvements - runtime PM support pl111: - vexpress init improvements - fix module auto-load rcar-du: - DT bindings conversion to YAML - Planes zpos sanity check and fix - MAINTAINERS entry for LVDS panel driver mcde: - fix return value mgag200: - use managed config init stm: - read endpoints from DT vboxvideo: - use PCI managed functions - drop WC mtrr vkms: - enable cursor by default rockchip: - afbc support virtio: - various cleanups qxl: - fix cursor notify port hisilicon: - 128-byte stride alignment fix sun4i: - improved format handling" * tag 'drm-next-2020-06-02' of git://anongit.freedesktop.org/drm/drm: (1401 commits) drm/amd/display: Fix potential integer wraparound resulting in a hang drm/amd/display: drop cursor position check in atomic test drm/amdgpu: fix device attribute node create failed with multi gpu drm/nouveau: use correct conflicting framebuffer API drm/vblank: Fix -Wformat compile warnings on some arches drm/amdgpu: Sync with VM root BO when switching VM to CPU update mode drm/amd/display: Handle GPU reset for DC block drm/amdgpu: add apu flags (v2) drm/amd/powerpay: Disable gfxoff when setting manual mode on picasso and raven drm/amdgpu: fix pm sysfs node handling (v2) drm/amdgpu: move gpu_info parsing after common early init drm/amdgpu: move discovery gfx config fetching drm/nouveau/dispnv50: fix runtime pm imbalance on error drm/nouveau: fix runtime pm imbalance on error drm/nouveau: fix runtime pm imbalance on error drm/nouveau/debugfs: fix runtime pm imbalance on error drm/nouveau/nouveau/hmm: fix migrate zero page to GPU drm/nouveau/nouveau/hmm: fix nouveau_dmem_chunk allocations drm/nouveau/kms/nv50-: Share DP SST mode_valid() handling with MST drm/nouveau/kms/nv50-: Move 8BPC limit for MST into nv50_mstc_get_modes() ...
2020-05-28Merge tag 'v5.7-rc7' into perf/core, to pick up fixesIngo Molnar1-4/+2
Signed-off-by: Ingo Molnar <[email protected]>
2020-05-14drm/i915: Extract i915_cs_timestamp_{ns_to_ticks,tick_to_ns}()Ville Syrjälä1-5/+2
Pull the code to do the CS timestamp ns<->ticks conversion into helpers and use them all over. The check in i915_perf_noa_delay_set() seems a bit dubious, so we switch it to do what I assume it wanted to do all along (ie. make sure the resulting delay in CS timestamp ticks doesn't exceed 32bits)? Cc: Lionel Landwerlin <[email protected]> Signed-off-by: Ville Syrjälä <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Reviewed-by: Chris Wilson <[email protected]>
2020-05-14drm/i915: Store CS timestamp frequency in HzVille Syrjälä1-6/+6
kHz isn't accurate enough for storing the CS timestamp frequency on some of the platforms. Store the value in Hz instead. Cc: Lionel Landwerlin <[email protected]> Signed-off-by: Ville Syrjälä <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Reviewed-by: Chris Wilson <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]>
2020-05-14drm/i915: Nuke pointless div by 64bitVille Syrjälä1-6/+5
Bunch of places use a 64bit divisor needlessly. Switch to 32bit divisor. Cc: Lionel Landwerlin <[email protected]> Signed-off-by: Ville Syrjälä <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Reviewed-by: Chris Wilson <[email protected]>
2020-05-06drm/i915/execlists: Track inflight CCIDChris Wilson1-2/+1
The presumption is that by using a circular counter that is twice as large as the maximum ELSP submission, we would never reuse the same CCID for two inflight contexts. However, if we continually preempt an active context such that it always remains inflight, it can be resubmitted with an arbitrary number of paired contexts. As each of its paired contexts will use a new CCID, eventually it will wrap and submit two ELSP with the same CCID. Rather than use a simple circular counter, switch over to a small bitmap of inflight ids so we can avoid reusing one that is still potentially active. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1796 Fixes: 2935ed5339c4 ("drm/i915: Remove logical HW ID") Signed-off-by: Chris Wilson <[email protected]> Cc: Mika Kuoppala <[email protected]> Cc: <[email protected]> # v5.5+ Reviewed-by: Mika Kuoppala <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry picked from commit 5c4a53e3b1cbc38d0906e382f1037290658759bb) (cherry picked from commit 134711240307d5586ae8e828d2699db70a8b74f2) Signed-off-by: Rodrigo Vivi <[email protected]>
2020-05-06drm/i915/execlists: Avoid reusing the same logical CCIDChris Wilson1-2/+1
The bspec is confusing on the nature of the upper 32bits of the LRC descriptor. Once upon a time, it said that it uses the upper 32b to decide if it should perform a lite-restore, and so we must ensure that each unique context submitted to HW is given a unique CCID [for the duration of it being on the HW]. Currently, this is achieved by using a small circular tag, and assigning every context submitted to HW a new id. However, this tag is being cleared on repinning an inflight context such that we end up re-using the 0 tag for multiple contexts. To avoid accidentally clearing the CCID in the upper 32bits of the LRC descriptor, split the descriptor into two dwords so we can update the GGTT address separately from the CCID. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1796 Fixes: 2935ed5339c4 ("drm/i915: Remove logical HW ID") Signed-off-by: Chris Wilson <[email protected]> Cc: Mika Kuoppala <[email protected]> Cc: <[email protected]> # v5.5+ Reviewed-by: Mika Kuoppala <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry picked from commit 2632f174a2e1a5fd40a70404fa8ccfd0b1f79ebd) (cherry picked from commit a4b70fcc587860f4b972f68217d8ebebe295ec15) Signed-off-by: Rodrigo Vivi <[email protected]>
2020-05-01i915: alloc_oa_regs(): get rid of pointless access_ok()Al Viro1-3/+0
Signed-off-by: Al Viro <[email protected]>
2020-04-28drm/i915/execlists: Track inflight CCIDChris Wilson1-2/+1
The presumption is that by using a circular counter that is twice as large as the maximum ELSP submission, we would never reuse the same CCID for two inflight contexts. However, if we continually preempt an active context such that it always remains inflight, it can be resubmitted with an arbitrary number of paired contexts. As each of its paired contexts will use a new CCID, eventually it will wrap and submit two ELSP with the same CCID. Rather than use a simple circular counter, switch over to a small bitmap of inflight ids so we can avoid reusing one that is still potentially active. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1796 Fixes: 2935ed5339c4 ("drm/i915: Remove logical HW ID") Signed-off-by: Chris Wilson <[email protected]> Cc: Mika Kuoppala <[email protected]> Cc: <[email protected]> # v5.5+ Reviewed-by: Mika Kuoppala <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-04-28drm/i915/execlists: Avoid reusing the same logical CCIDChris Wilson1-2/+1
The bspec is confusing on the nature of the upper 32bits of the LRC descriptor. Once upon a time, it said that it uses the upper 32b to decide if it should perform a lite-restore, and so we must ensure that each unique context submitted to HW is given a unique CCID [for the duration of it being on the HW]. Currently, this is achieved by using a small circular tag, and assigning every context submitted to HW a new id. However, this tag is being cleared on repinning an inflight context such that we end up re-using the 0 tag for multiple contexts. To avoid accidentally clearing the CCID in the upper 32bits of the LRC descriptor, split the descriptor into two dwords so we can update the GGTT address separately from the CCID. Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1796 Fixes: 2935ed5339c4 ("drm/i915: Remove logical HW ID") Signed-off-by: Chris Wilson <[email protected]> Cc: Mika Kuoppala <[email protected]> Cc: <[email protected]> # v5.5+ Reviewed-by: Mika Kuoppala <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-04-24drm/i915: Make define for lrc state offsetMika Kuoppala1-1/+1
More often than not, we need a byte offset into lrc register state from the start of the hw state. Make it so. Signed-off-by: Mika Kuoppala <[email protected]> Reviewed-by: Chris Wilson <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-04-22Merge tag 'perf-core-for-mingo-5.8-20200420' of ↵Ingo Molnar1-7/+6
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core fixes and improvements from Arnaldo Carvalho de Melo: kernel + tools/perf: Alexey Budankov: - Introduce CAP_PERFMON to kernel and user space. callchains: Adrian Hunter: - Allow using Intel PT to synthesize callchains for regular events. Kan Liang: - Stitch LBR records from multiple samples to get deeper backtraces, there are caveats, see the csets for details. perf script: Andreas Gerstmayr: - Add flamegraph.py script BPF: Jiri Olsa: - Synthesize bpf_trampoline/dispatcher ksymbol events. perf stat: Arnaldo Carvalho de Melo: - Honour --timeout for forked workloads. Stephane Eranian: - Force error in fallback on :k events, to avoid counting nothing when the user asks for kernel events but is not allowed to. perf bench: Ian Rogers: - Add event synthesis benchmark. tools api fs: Stephane Eranian: - Make xxx__mountpoint() more scalable libtraceevent: He Zhe: - Handle return value of asprintf. Signed-off-by: Arnaldo Carvalho de Melo <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2020-04-16drm/i915/perf: Open access for CAP_PERFMON privileged processAlexey Budankov1-7/+6
Open access to i915_perf monitoring for CAP_PERFMON privileged process. Providing the access under CAP_PERFMON capability singly, without the rest of CAP_SYS_ADMIN credentials, excludes chances to misuse the credentials and makes operation more secure. CAP_PERFMON implements the principle of least privilege for performance monitoring and observability operations (POSIX IEEE 1003.1e 2.2.2.39 principle of least privilege: A security design principle that states that a process or program be granted only those privileges (e.g., capabilities) necessary to accomplish its legitimate function, and only for the time that such privileges are actually required) For backward compatibility reasons access to i915_events subsystem remains open for CAP_SYS_ADMIN privileged processes but CAP_SYS_ADMIN usage for secure i915_events monitoring is discouraged with respect to CAP_PERFMON capability. Signed-off-by: Alexey Budankov <[email protected]> Reviewed-by: James Morris <[email protected]> Acked-by: Lionel Landwerlin <[email protected]> Cc: Alexei Starovoitov <[email protected]> Cc: Andi Kleen <[email protected]> Cc: Igor Lubashev <[email protected]> Cc: Jiri Olsa <[email protected]> Cc: Namhyung Kim <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Serge Hallyn <[email protected]> Cc: Song Liu <[email protected]> Cc: Stephane Eranian <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Link: http://lore.kernel.org/lkml/[email protected] Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
2020-04-13drm/i915/perf: Do not clear pollin for small user read buffersAshutosh Dixit1-54/+11
It is wrong to block the user thread in the next poll when OA data is already available which could not fit in the user buffer provided in the previous read. In several cases the exact user buffer size is not known. Blocking user space in poll can lead to data loss when the buffer size used is smaller than the available data. This change fixes this issue and allows user space to read all OA data even when using a buffer size smaller than the available data using multiple non-blocking reads rather than staying blocked in poll till the next timer interrupt. v2: Fix ret value for blocking reads (Umesh) v3: Mistake during patch send (Ashutosh) v4: Remove -EAGAIN from comment (Umesh) v5: Improve condition for clearing pollin and return (Lionel) v6: Improve blocking read loop and other cleanups (Lionel) v7: Added Cc stable Testcase: igt/perf/polling-small-buf Reviewed-by: Lionel Landwerlin <[email protected]> Signed-off-by: Ashutosh Dixit <[email protected]> Cc: Umesh Nerlige Ramappa <[email protected]> Cc: <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry-picked from commit 6352219c39c04ed3f9a8d1cf93f87c21753a213e) Signed-off-by: Rodrigo Vivi <[email protected]>
2020-04-06drm/i915: Make exclusive awaits on i915_active optionalChris Wilson1-1/+1
Later use will require asynchronous waits on the active timelines, but will not utilize an async wait on the exclusive channel. Make the await on the exclusive fence explicit in the selection flags. Signed-off-by: Chris Wilson <[email protected]> Reviewed-by: Tvrtko Ursulin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-04-03drm/i915/perf: Do not clear pollin for small user read buffersAshutosh Dixit1-50/+11
It is wrong to block the user thread in the next poll when OA data is already available which could not fit in the user buffer provided in the previous read. In several cases the exact user buffer size is not known. Blocking user space in poll can lead to data loss when the buffer size used is smaller than the available data. This change fixes this issue and allows user space to read all OA data even when using a buffer size smaller than the available data using multiple non-blocking reads rather than staying blocked in poll till the next timer interrupt. v2: Fix ret value for blocking reads (Umesh) v3: Mistake during patch send (Ashutosh) v4: Remove -EAGAIN from comment (Umesh) v5: Improve condition for clearing pollin and return (Lionel) v6: Improve blocking read loop and other cleanups (Lionel) v7: Added Cc stable Testcase: igt/perf/polling-small-buf Reviewed-by: Lionel Landwerlin <[email protected]> Signed-off-by: Ashutosh Dixit <[email protected]> Cc: Umesh Nerlige Ramappa <[email protected]> Cc: <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-31drm/i915/perf: don't read head/tail pointers outside critical sectionLionel Landwerlin1-2/+5
Reading or writing those fields should only happen under stream->oa_buffer.ptr_lock. Signed-off-by: Lionel Landwerlin <[email protected]> Fixes: d1df41eb72ef ("drm/i915/perf: rework aging tail workaround") Reviewed-by: Chris Wilson <[email protected]> Acked-by: Ashutosh Dixit <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-30drm/i915/perf: Schedule oa_config after modifying the contextsChris Wilson1-55/+99
We wish that the scheduler emit the context modification commands prior to enabling the oa_config, for which we must explicitly inform it of the ordering constraints. This is especially important as we now wait for the final oa_config setup to be completed and as this wait may be on a distinct context to the state modifications, we need that command packet to be always last in the queue. We borrow the i915_active for its ability to track multiple timelines and the last dma_fence on each; a flexible dma_resv. Keeping track of each dma_fence is important for us so that we can efficiently schedule the requests and reprioritise as required. Reported-by: Lionel Landwerlin <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Cc: Lionel Landwerlin <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-27drm/i915/perf: add new open param to configure polling of OA bufferLionel Landwerlin1-7/+25
This new parameter let's the application choose how often the OA buffer should be checked on the CPU side for data availability. Longer polling period tend to reduce CPU overhead if the application does not care about somewhat real time data collection. v2: Allow disabling polling completely with 0 value (Lionel) v3: Version the new parameter (Joonas) v4: Rebase (Umesh) v5: Make poll delay value of 0 invalid (Umesh) v6: - Describe poll_oa_period (Ashutosh) - Fix comment for new poll parameter (Lionel) - Drop open_flags in read_properties_unlocked (Lionel) - Rename uapi parameter (Ashutosh) v7: Reword the comment in uapi (Ashutosh) Signed-off-by: Lionel Landwerlin <[email protected]> Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Reviewed-by: Ashutosh Dixit <[email protected]> Signed-off-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-27drm/i915/perf: move pollin setup to non hw specific codeLionel Landwerlin1-11/+3
This isn't really gen specific stuff, so just move it to the common code. v2: Rebase (Umesh) v3: Remove comment, pollin is a per stream state already (Ashutosh) Signed-off-by: Lionel Landwerlin <[email protected]> Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Reviewed-by: Ashutosh Dixit <[email protected]> Signed-off-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-27drm/i915/perf: rework aging tail workaroundLionel Landwerlin1-121/+83
We're about to introduce an options to open the perf stream, giving the user ability to configure how often it wants the kernel to poll the OA registers for available data. Right now the workaround against the OA tail pointer race condition requires at least twice the internal kernel polling timer to make any data available. This changes introduce checks on the OA data written into the circular buffer to make as much data as possible available on the first iteration of the polling timer. v2: Use OA_TAKEN macro without the gtt_offset (Lionel) v3: (Umesh) - Rebase - Change report to report32 from below review https://patchwork.freedesktop.org/patch/330704/?series=66697&rev=1 v4: (Ashutosh, Lionel) - Fix checkpatch errors - Fix aging_timestamp initialization - Check for only one valid landed report - Fix check for unlanded report v5: (Ashutosh) - Fix bug in accurately determining landed report. - Optimize the check for landed reports by going as far as the previously determined aged tail. Signed-off-by: Lionel Landwerlin <[email protected]> Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Reviewed-by: Ashutosh Dixit <[email protected]> Signed-off-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-20drm/i915/perf: Invalidate OA TLB on when closing perf streamUmesh Nerlige Ramappa1-0/+8
On running several back to back perf capture sessions involving closing and opening the perf stream, invalid OA reports are seen in the beginning of the OA buffer in some sessions. Fix this by invalidating OA TLB when the perf stream is closed or disabled on gen12. Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]> Fixes: 00a7f0d7155c ("drm/i915/tgl: Add perf support on TGL") Signed-off-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] (cherry picked from commit a639b0c15065df930467695b76ef38d5edaed049) Signed-off-by: Rodrigo Vivi <[email protected]>
2020-03-18drm/i915/perf: Invalidate OA TLB on when closing perf streamUmesh Nerlige Ramappa1-0/+8
On running several back to back perf capture sessions involving closing and opening the perf stream, invalid OA reports are seen in the beginning of the OA buffer in some sessions. Fix this by invalidating OA TLB when the perf stream is closed or disabled on gen12. Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]> Fixes: 00a7f0d7155c ("drm/i915/tgl: Add perf support on TGL") Signed-off-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-17drm/i915/perf: introduce global sseu pinningLionel Landwerlin1-2/+74
On Gen11 powergating half the execution units is a functional requirement when using the VME samplers. Not fullfilling this requirement can lead to hangs. This unfortunately plays fairly poorly with the NOA requirements. NOA requires a stable power configuration to maintain its configuration. As a result using OA (and NOA feeding into it) so far has required us to use a power configuration that can work for all contexts. The only power configuration fullfilling this is powergating half the execution units. This makes performance analysis for 3D workloads somewhat pointless. Failing to find a solution that would work for everybody, this change introduces a new i915-perf stream open parameter that punts the decision off to userspace. If this parameter is omitted, the existing Gen11 behavior remains (half EU array powergating). This change takes the initiative to move all perf related sseu configuration into i915_perf.c v2: Make parameter priviliged if different from default v3: Fix context modifying its sseu config while i915-perf is enabled v4: Always consider global sseu a privileged operation (Tvrtko) Override req_sseu point in intel_sseu_make_rpcs() (Tvrtko) Remove unrelated changes (Tvrtko) v5: Some typos (Tvrtko) Process sseu param in read_properties_unlocked() (Tvrtko) v6: Actually commit the bits from v5... Fixup some checkpath warnings v7: Only compare engine uabi field (Chris) Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Tvrtko Ursulin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-17drm/i915/perf: remove redundant power configuration register overrideLionel Landwerlin1-7/+0
The caller of i915_oa_init_reg_state() already sets this. Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Tvrtko Ursulin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-17drm/i915/perf: remove generated codeLionel Landwerlin1-80/+1
A little bit of history : Back when i915-perf was introduced (4.13), there was no way to dynamically add new OA configurations to i915. Only the generated configs baked in at build time were allowed. It quickly became obvious that we would need to allow applications to upload their own configurations, for instance to be able to test new ones, and so by the next stable version (4.14) we added uAPIs to allow uploading new configurations. When adding that capability, we took the opportunity to remove most HW configurations except the TestOa one which is a configuration IGT would rely on to verify that the HW is outputting correct values. At the time it made sense to have that confiuration in at the same time a given HW platform added to the i915-perf driver. Now that IGT has become the reference point for HW configurations (see commit 53f8f541ca ("lib: Add i915_perf library"), previously this was located in the GPUTop repository), the need for having those configurations in i915-perf is gone. On the Mesa side, we haven't relied on this test configuration for a while. The MDAPI library always required 4.14 feature level and always loaded its configuration into i915. I'm sure nobody will miss this generated stuff in i915 :) v2: Fix selftests by creating an empty config v3: Fix unlocking on allocation error (Dan Carpenter) v4: Fixup checkpatch warnings v5: Fix incorrect unlock in error path (Umesh) Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Umesh Nerlige Ramappa <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-03-02drm/i915/perf: Reintroduce wait on OA configuration completionChris Wilson1-17/+41
We still need to wait for the initial OA configuration to happen before we enable OA report writes to the OA buffer. Reported-by: Lionel Landwerlin <[email protected]> Fixes: 15d0ace1f876 ("drm/i915/perf: execute OA configuration from command stream") Closes: https://gitlab.freedesktop.org/drm/intel/issues/1356 Testcase: igt/perf/stream-open-close Signed-off-by: Chris Wilson <[email protected]> Cc: Lionel Landwerlin <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-02-28drm/i915/perf: Manually acquire engine-wakeref around use of kernel_contextChris Wilson1-0/+2
The engine->kernel_context is a special case for request emission. Since it is used as the barrier within the engine's wakeref, we must acquire the wakeref before submitting a request to the kernel_context. Reported-by: Lionel Landwerlin <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Cc: Lionel Landwerlin <[email protected]> Reviewed-by: Mika Kuoppala <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-02-28drm/i915/perf: Mark up the racy use of perf->exclusive_streamChris Wilson1-6/+7
Inside the general i915_oa_init_reg_state() we avoid using the perf->mutex. However, we rely on perf->exclusive_stream being valid to access at that point, and for that we have to control the race with disabling perf. This relies on the disabling being a heavy barrier that inspects all active contexts, after marking the perf->exclusive_stream as not available. This should ensure that there are no more concurrent accesses to the perf->exclusive_stream as we destroy it. Mark up the races around the perf->exclusive_stream so that they stand out much more. (And hopefully we will be running kcsan to start validating that the only races we have are carefully controlled.) Signed-off-by: Chris Wilson <[email protected]> Cc: Lionel Landwerlin <[email protected]> Reviewed-by: Mika Kuoppala <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-02-21drm/i915/perf: conversion to struct drm_device based logging macros.Wambui Karuga1-10/+17
Manual conversion of instances of printk based drm logging macros to the struct drm_device based logging macros in i915/i915_perf.c. Also involves extraction of the struct drm_i915_private device from various intel types for use in the macros. Instances of the DRM_DEBUG printk macro were not converted due to the lack of an analogous struct drm_device based logging macro. v2: remove instances of DRM_DEBUG that were converted. References: https://lists.freedesktop.org/archives/dri-devel/2020-January/253381.html Signed-off-by: Wambui Karuga <[email protected]> Signed-off-by: Jani Nikula <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-02-04drm/i915: conversion to drm_device logging macros when drm_i915_private is ↵Wambui Karuga1-2/+3
present. Converts various instances of the printk drm logging macros to the struct drm_device based logging macros in the drm/i915 folder using the following coccinelle script that transforms based on the existence of the struct drm_i915_private device pointer: @@ identifier fn, T; @@ fn(...) { ... struct drm_i915_private *T = ...; <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } @@ identifier fn, T; @@ fn(...,struct drm_i915_private *T,...) { <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } Checkpatch warnings were fixed manually. Instances of the DRM_DEBUG macro were not converted due to lack of a consensus of an analogous struct drm_device based macro. References: https://lists.freedesktop.org/archives/dri-devel/2020-January/253381.html Signed-off-by: Wambui Karuga <[email protected]> Signed-off-by: Jani Nikula <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-01-27drm/i915/perf: Fix OA context id overlap with idle context idUmesh Nerlige Ramappa1-2/+8
Engine context pinned in perf OA was set to same context id as the idle context. Set the context id to an unused value. Clear the sw context id field in lrc descriptor before ORing with ce->tag (Chris) Closes: https://gitlab.freedesktop.org/drm/intel/issues/756 Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Reviewed-by: Chris Wilson <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-01-22drm/i915: Make WARN* drm specific where uncore or stream ptr is availablePankaj Bharadiya1-16/+22
drm specific WARN* calls include device information in the backtrace, so we know what device the warnings originate from. Covert all the calls of WARN* with device specific drm_WARN* variants in functions where intel_uncore/i915_perf_stream struct pointer is readily available. The conversion was done automatically with below coccinelle semantic patch. checkpatch errors/warnings are fixed manually. @@ identifier func, T; @@ func(...) { ... struct intel_uncore *T = ...; <... ( -WARN( +drm_WARN(&T->i915->drm, ...) | -WARN_ON( +drm_WARN_ON(&T->i915->drm, ...) | -WARN_ONCE( +drm_WARN_ONCE(&T->i915->drm, ...) | -WARN_ON_ONCE( +drm_WARN_ON_ONCE(&T->i915->drm, ...) ) ...> } @@ identifier func, T; @@ func(struct intel_uncore *T,...) { <... ( -WARN( +drm_WARN(&T->i915->drm, ...) | -WARN_ON( +drm_WARN_ON(&T->i915->drm, ...) | -WARN_ONCE( +drm_WARN_ONCE(&T->i915->drm, ...) | -WARN_ON_ONCE( +drm_WARN_ON_ONCE(&T->i915->drm, ...) ) ...> } @@ identifier func, T; @@ func(struct i915_perf_stream *T,...) { +struct drm_i915_private *i915 = T->perf->i915; <+... ( -WARN( +drm_WARN(&i915->drm, ...) | -WARN_ON( +drm_WARN_ON(&i915->drm, ...) | -WARN_ONCE( +drm_WARN_ONCE(&i915->drm, ...) | -WARN_ON_ONCE( +drm_WARN_ON_ONCE(&i915->drm, ...) ) ...+> } command: ls drivers/gpu/drm/i915/*.c | xargs spatch --sp-file <script> \ --linux-spacing --in-place Signed-off-by: Pankaj Bharadiya <[email protected]> Signed-off-by: Jani Nikula <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2020-01-09drm/i915: Pin the context as we work on itChris Wilson1-10/+5
Since we now allow the intel_context_unpin() to run unserialised, we risk our operations under the intel_context_lock_pinned() being run as the context is unpinned (and thus invalidating our state). We can atomically acquire the pin, testing to see if it is pinned in the process, thus ensuring that the state remains consistent during the course of the whole operation. Fixes: 841350223816 ("drm/i915/gt: Drop mutex serialisation between context pin/unpin") Signed-off-by: Chris Wilson <[email protected]> Cc: Tvrtko Ursulin <[email protected]> Reviewed-by: Mika Kuoppala <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-12-21drm/i915: Remove i915->kernel_contextChris Wilson1-3/+0
Allocate only an internal intel_context for the kernel_context, forgoing a global GEM context for internal use as we only require a separate address space (for our own protection). Now having weaned GT from requiring ce->gem_context, we can stop referencing it entirely. This also means we no longer have to create random and unnecessary GEM contexts for internal use. GEM contexts are now entirely for tracking GEM clients, and intel_context the execution environment on the GPU. Signed-off-by: Chris Wilson <[email protected]> Cc: Andi Shyti <[email protected]> Acked-by: Andi Shyti <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-12-20drm/i915: Drop GEM context as a direct link from i915_requestChris Wilson1-2/+2
Keep the intel_context as being the primary state for i915_request, with the GEM context a backpointer from the low level state for the rarer cases we need client information. Our goal is to remove such references to clients from the backend, and leave the HW submission agnostic to client interfaces and self-contained. Signed-off-by: Chris Wilson <[email protected]> Cc: Andi Shyti <[email protected]> Reviewed-by: Andi Shyti <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-12-13drm/i915/perf: Register sysctl path globallyVenkata Sandeep Dhanalakota1-4/+13
We do not require to register the sysctl paths per instance, so making registration global. v2: make sysctl path register and unregister function driver specific (Tvrtko and Lucas). Cc: Sudeep Dutt <[email protected]> Cc: Rodrigo Vivi <[email protected]> Cc: Daniel Vetter <[email protected]> Cc: Chris Wilson <[email protected]> Cc: Jani Nikula <[email protected]> Signed-off-by: Venkata Sandeep Dhanalakota <[email protected]> Reviewed-by: Chris Wilson <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-12-09drm/i915/perf: Configure OAR for specific contextUmesh Nerlige Ramappa1-87/+112
Gen12 supports saving/restoring render counters per context. Apply OAR configuration only for the context that is passed in to perf. v2: - Fix OACTXCONTROL value to only stop/resume counters. - Remove gen12_update_reg_state_unlocked as power state is already applied by the caller. v3: (Lionel) - Move register initialization into the array - Assume a valid oa_config in enable_metric_set Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Fixes: 00a7f0d7155c ("drm/i915/tgl: Add perf support on TGL") Reviewed-by: Lionel Landwerlin <[email protected]> Signed-off-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-12-09drm/i915/perf: Allow non-privileged access when OA buffer is not sampledUmesh Nerlige Ramappa1-2/+3
SAMPLE_OA_REPORT enables sampling of OA reports from the OA buffer. Since reports from OA buffer had system wide visibility, collecting samples from the OA buffer was a privileged operation on previous platforms. Prior to TGL, it was also necessary to sample the OA buffer to normalize reports from MI REPORT PERF COUNT. TGL has a dedicated OAR unit to sample perf reports for a specific render context. This removes the necessity to sample OA buffer. - If not sampling the OA buffer, allow non-privileged access. An earlier patch allows the non-privilege access: https://patchwork.freedesktop.org/patch/337716/?series=68582&rev=1 - Clear up the path for non-privileged access in this patch Signed-off-by: Umesh Nerlige Ramappa <[email protected]> Fixes: 00a7f0d7155c ("drm/i915/tgl: Add perf support on TGL") Reviewed-by: Lionel Landwerlin <[email protected]> Signed-off-by: Lionel Landwerlin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-12-04drm/i915/perf: drop pointless static qualifier in i915_perf_add_config_ioctl()Mao Wenan1-1/+1
There is no need to have the 'T *v' variable static since new value always be assigned before use it. Reported-by: Hulk Robot <[email protected]> Signed-off-by: Mao Wenan <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-11-25drm/i915: Serialise with engine-pm around requests on the kernel_contextChris Wilson1-1/+3
As the engine->kernel_context is used within the engine-pm barrier, we have to be careful when emitting requests outside of the barrier, as the strict timeline locking rules do not apply. Instead, we must ensure the engine_park() cannot be entered as we build the request, which is simplest by taking an explicit engine-pm wakeref around the request construction. Signed-off-by: Chris Wilson <[email protected]> Reviewed-by: Tvrtko Ursulin <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-11-15drm/i915/perf: Add preemption check while waiting for OALionel Landwerlin1-0/+2
While we're waiting for the OA configuration to apply, let's give a chance to other contexts that might need to run other workloads. Signed-off-by: Lionel Landwerlin <[email protected]> Suggested-by: Chris Wilson <[email protected]> Reviewed-by: Chris Wilson <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
2019-11-14drm/i915/perf: don't forget noa wait after oa configLionel Landwerlin1-2/+7
I'm observing incoherence metric values, changing from run to run. It appears the patches introducing noa wait & reconfiguration from command stream switched places in the series multiple times during the review. This lead to the dependency of one onto the order to go missing... Signed-off-by: Lionel Landwerlin <[email protected]> Fixes: 15d0ace1f876 ("drm/i915/perf: execute OA configuration from command stream") Reviewed-by: Chris Wilson <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Powered by cgit, Gruvboxed by Blaster4385.