- 10 Nov, 2016 11 commits
-
-
https://github.com/01org/gvt-linuxDaniel Vetter authored
Merge tag 'gvt-next-kvmgt-framework' of https://github.com/01org/gvt-linux into drm-intel-next-queued Zhenyu Wang writes: gvt-next-kvmgt-framework This adds initial KVMGT framework based on GVT-g MPT(Mediated Passthrough) interface. Signed-off-by:
Daniel Vetter <daniel.vetter@intel.com>
-
Tvrtko Ursulin authored
At the moment we allocate enough sg table entries assuming we will not be able to do any coalescing. But since in practice we most often can, and more so very effectively, this ends up wasting a lot of memory. A simple and effective way of trimming the over-allocated entries is to copy the table over to a new one allocated to the exact size. Experiments on my freshly logged and idle desktop (KDE) showed that by doing this we can save approximately 1 MiB of RAM, or when running a typical benchmark like gl_manhattan I have even seen a 6 MiB saving. More complicated techniques such as only copying the last used page and freeing the rest are left to the reader. v2: * Update commit message. * Use temporary sg_table on stack. (Chris Wilson) v3: * Commit message update. * Comment added. * Replace memcpy with copy assignment. (Chris Wilson) Signed-off-by:
Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by:
Chris Wilson <chris@chris-wilson.co.uk> Link: http://patchwork.freedesktop.org/patch/msgid/1478704423-7447-1-git-send-email-tvrtko.ursulin@linux.intel.com
-
Jike Song authored
KVMGT is the MPT implementation based on VFIO/KVM. It provides a kvmgt_mpt ops to gvt for vGPU access mediation, e.g. to mediate and emulate the MMIO accesses, to inject interrupts to vGPU user, to intercept the GTT writing and replace it with DMA-able address, to write-protect guest PPGTT table for shadowing synchronization, etc. This patch provides the MPT implementation for GVT, not yet functional due to theabsence of mdev. It's built as kvmgt.ko, depends on vfio.ko, kvm.ko and mdev.ko, and being required by i915.ko. To not introduce hard dependency in i915.ko, we used indirect symbol reference. But that means users have to include kvmgt.ko into init ramdisk if their i915.ko is included. Signed-off-by:
Kevin Tian <kevin.tian@intel.com> Signed-off-by:
Xiaoguang Chen <xiaoguang.chen@intel.com> Signed-off-by:
Jike Song <jike.song@intel.com> Signed-off-by:
Zhenyu Wang <zhenyuw@linux.intel.com>
-
Jike Song authored
There are currently 4 methods in intel_gvt_io_emulation_ops to emulate CFG/MMIO reading/writing for intel vGPU. A possibly better scope is: add 3 more methods for vgpu create/destroy/reset respectively, and rename the ops to 'intel_gvt_ops', then pass it to the MPT module (say the future kvmgt) to use: they are all methods for external usage. Signed-off-by:
-
Jike Song authored
Hypervisors are different, the MPT ops is a only superset of all possibly supported hypervisors. There might be other way out of the MPT to achieve same target. e.g. vfio-based kvmgt won't provide map_gfn_to_mfn method to establish guest EPT mapping for aperture, since it will be done in QEMU/KVM, MMIO is also trapped elsewhere, etc. Signed-off-by:
-
Jike Song authored
GVT host needs init/exit hooks to do some initialization/cleanup work, e.g.: vfio mdev host device register/unregister. Signed-off-by:
-
Jike Song authored
Current GVT contains some obsolete logic originally cooked to support the old, non-vfio kvmgt, which is actually workarounds. We don't support that anymore, so it's safe to remove it and make a better framework. Signed-off-by:
-
Zhenyu Wang authored
By providing predefined vGPU types, users can choose which type a vgpu to create and use, without specifying detailed parameters. Signed-off-by:
-
Xiaoguang Chen authored
kmap_atomic doesn't allow sleep until unmapped. However, it's necessary to allow sleep during reading/writing guest memory, so use kmap instead. Signed-off-by:
Bing Niu <bing.niu@intel.com> Signed-off-by:
-
Bing Niu authored
On guest writing a PPGTT entry, if it contains value and the old entry is valid, gvt will read it and find & free the corresponding old data for it. However, with the KVM write protection provided by page_track, the guest entry will be written with new value before gvt handling. To avoid that, we should use the shadow entry instead. Signed-off-by:
-
git://git.kernel.org/pub/scm/virt/kvm/kvmDaniel Vetter authored
Paulo Bonzini writes: The three KVM patches that KVMGT needs. Signed-off-by:
-
- 09 Nov, 2016 6 commits
-
-
Chris Wilson authored
When we need to reset the global seqno on wraparound, we have to wait until the current rbtrees are drained (or otherwise the next waiter will be out of sequence). The current mechanism to kick and spin until complete, may exit too early as it would break if the target thread was currently running. Instead, we must wake up the threads, but keep spinning until the trees have been deleted. In order to appease Tvrtko, busy spin rather than yield(). Signed-off-by:
-
Maarten Lankhorst authored
This gets rid of a warning that the connectors are used without locking when doing a nonblocking modeset. Signed-off-by:
Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Reviewed-by:
Ville Syrjälä <ville.syrjala@linux.intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1478609742-13603-11-git-send-email-maarten.lankhorst@linux.intel.com
-
Maarten Lankhorst authored
All of this state should be updated as soon as possible. It shouldn't be done later because then future updates may not depend on it. Changes since v1: - Move the modeset update to before drm_atomic_state_get. (Ville) Signed-off-by:
-
Maarten Lankhorst authored
The only user was i915, which is now gone. Signed-off-by:
-
Maarten Lankhorst authored
drm_select_eld requires mode_config.mutex and connection_mutex because it looks at the connector list and at the legacy encoders. This is not required, because when we call audio_codec_enable we know which connector it was called for, so pass the state. This also removes having to look at crtc->config. Changes since v1: - Use intel_crtc->pipe instead of drm_crtc_index. (Ville) Signed-off-by:
-
Maarten Lankhorst authored
This is the last connector still looking at crtc->config. Fix this. Signed-off-by:
-
- 08 Nov, 2016 8 commits
-
-
Arnd Bergmann authored
The newly added assert_kernel_context_is_current introduces a warning when built with W=1: drivers/gpu/drm/i915/i915_gem.c: In function ‘assert_kernel_context_is_current’: drivers/gpu/drm/i915/i915_gem.c:4417:63: error: suggest braces around empty body in an ‘else’ statement [-Werror=empty-body] Changing the GEM_BUG_ON() macro from an empty definition to "do { } while (0)" makes the macro more robust to use and avoids the warning. Fixes: 3033acab ("drm/i915: Queue the idling context switch after all other timelines") Signed-off-by:Arnd Bergmann <arnd@arndb.de> Reviewed-by:
Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161108135834.2166677-1-arnd@arndb.de
-
https://github.com/01org/gvt-linuxDaniel Vetter authored
gvt-next-2016-11-07 - Fix regression from e95433c7 - Some MMIO handler fixes - Add better handling for guest reset control - stratch page table tree for shadow ppgtt Signed-off-by:
-
Ville Syrjälä authored
The code to determine the primary plane offset for gen2/3 looks different than the code for gen4+, but in fact it's doing the same thing. Let's make it uniform. Allows us to eliminate the 'obj' from the list of local variables as well. Signed-off-by:
-
Ville Syrjälä authored
intel_cursor_plane_create() and intel_sprite_plane_create() return an error pointer, so let's not mistakenly look for a NULL pointer. Cc: Chris Wilson <chris@chris-wilson.co.uk> Reported-by:
-
Ville Syrjälä authored
Use the passed in plane_state instead of plane->state in vlv_update_plane(). Currently the two are one and the same, but if we start queuing up multiple plane updates they might not be. Looks like this was rebase fail on my part. Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Fixes: 8d0deca8 ("drm/i915: Pass 90/270 vs. 0/180 rotation info for intel_gen4_compute_page_offset()") Signed-off-by:
-
Chris Wilson authored
We always flush the chipset prior to executing with the GPU, so we can skip the flush during ordinary domain management. This should help mitigate some of the potential performance regressions, but likely trivial, from doing the flush unconditionally before execbuf introduced in commit dcd79934 ("drm/i915: Unconditionally flush any chipset buffers before execbuf") Signed-off-by:
Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
-
Joonas Lahtinen authored
Get rid of sloppy inline functions now that we don't have more users: i915_gem_request_get_seqno i915_gem_request_get_engine v2: - request->engine is always non-NULL (Chris) Signed-off-by:
-
Daniel Vetter authored
Signed-off-by:
-
- 07 Nov, 2016 15 commits
-
-
Chris Wilson authored
On LLC, or even snooped, machines rendering via the GPU ends up in the CPU cache. This cacheline dirt also needs to be flushed to main memory when moving to an incoherent domain, such as the display's scanout engine. Mostly, this happens because either the object is marked as dirty from its first use or is avoided by setting the object into the display domain from the start. v2: Treat WT as not requiring a clflush prior to use on the display engine as well. Fixes: 0f71979a ("drm/i915: Performed deferred clflush inside set-cache-level") References: https://bugs.freedesktop.org/show_bug.cgi?id=95414Signed-off-by:
-
Imre Deak authored
During resume we will reset the SW/HW tracking for each ring head/tail pointers and so are not prepared to replay any pending requests (as opposed to GPU reset time). Add an assert for this both to the suspend and the resume code. v2: - Check for ELSP port idle already during suspend and check !gt.awake during resume. (Chris) v3: - Move the !gt.awake check to i915_gem_resume(). v4: - s/intel_lr_engines_idle/intel_execlists_idle/ (Chris) Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Signed-off-by:
Imre Deak <imre.deak@intel.com> Reviewed-by:
-
Imre Deak authored
We assume that the GPU is idle once receiving the seqno via the last request's user interrupt. In execlist mode the corresponding context completed interrupt can be delayed though and until this latter interrupt arrives we consider the request to be pending on the ELSP submit port. This can cause a problem during system suspend where this last request will be seen by the resume code as still pending. Such pending requests are normally replayed after a GPU reset, but during resume we reset both SW and HW tracking of the ring head/tail pointers, so replaying the pending request with its stale tail pointer will leave the ring in an inconsistent state. A subsequent request submission can lead then to the GPU executing from uninitialized area in the ring behind the above stale tail pointer. Fix this by making sure any pending request on the ELSP port is completed before suspending. I used a polling wait since the completion time I measured was <1ms and since normally we only need to wait during system suspend. GPU idling during runtime suspend is scheduled with a delay (currently 50-100ms) after the retirement of the last request at which point the context completed interrupt must have arrived already. The chance of this bug was increased by commit 1c777c5d Author: Imre Deak <imre.deak@intel.com> Date: Wed Oct 12 17:46:37 2016 +0300 drm/i915/hsw: Fix GPU hang during resume from S3-devices state but it could happen even without the explicit GPU reset, since we disable interrupts afterwards during the suspend sequence. v2: - Do an unlocked poll-wait first. (Chris) v3-4: - s/intel_lr_engines_idle/intel_execlists_idle/ and move i915.enable_execlists check to the new helper. (Chris) Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98470Signed-off-by:
-
Imre Deak authored
There is a small race where a new request can be submitted and retired after the idle worker started to run which leads to idling the GPU too early. Fix this by deferring the idling to the pending instance of the worker. This scenario was pointed out by Chris. Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by:
-
Imre Deak authored
Atm, in case an idle work handler is already pending but haven't yet started to run, retiring a new request will not extend the active period as required, rather simply leaves the pending idle work to be scheduled at the original expiration time. This may lead to idling the GPU too early. Fix this by using the delayed-work scheduler alternative which makes sure the handler's expiration time is extended in this case. Cc: Chris Wilson <chris@chris-wilson.co.uk> Requested-by:
-
Chris Wilson authored
Valleyview appears to be limited to only scanning out from the first 512MiB of the Global GTT. Lets presume that this behaviour was inherited from the display block copied from g4x (not Ironlake) and all earlier generations are similarly affected, though testing suggests different symptoms. For simplicity, impose that these platforms must scanout from the mappable region. (For extra simplicity, use HAS_GMCH_DISPLAY even though this catches Cherryview which does not appear to be limited to the low aperture for its scanout.) v2: Use HAS_GMCH_DISPLAY() to more clearly convey my intent about limiting this workaround to the old style of display engine. v3: Update changelog to reflect testing by Ville Syrjälä v4: Include the changes to the comments as well Reported-by:
Luis Botello <luis.botello.ortega@intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98036 Fixes: 2efb813d ("drm/i915: Fallback to using unmappable memory for scanout") Signed-off-by:
-
Chris Wilson authored
When we split a large object up into chunks for GTT faulting (because we can't fit the whole object into the aperture) we have to align our cuts with the fence registers. Each partial VMA must cover a complete set of tile rows or the offset into each partial VMA is not aligned with the whole image. Currently we enforce a minimum size on each partial VMA, but this minimum size itself was not aligned to the tile row causing distortion. Reported-by:
Andreas Reis <andreas.reis@gmail.com> Reported-by:
Chris Clayton <chris2553@googlemail.com> Reported-by:
Norbert Preining <preining@logic.at> Tested-by:
-
Chris Wilson authored
Currently, the vma is being unlink from the object lookup on destroy. However, we are meant to be decoupling it upon close so that the user cannot access the closed vma whilst it remains active on the GPU. [ 34.074858] kernel BUG at drivers/gpu/drm/i915/i915_gem_gtt.c:3561! [ 34.074875] invalid opcode: 0000 [#1] PREEMPT SMP [ 34.074888] Modules linked in: snd_hda_intel i915 x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel lpc_ich mei_me mei snd_hda_codec_realtek snd_hda_codec_generic snd_hda_codec_hdmi snd_hda_codec snd_hwdep snd_hda_core i2c_designware_platform i2c_designware_core snd_pcm e1000e ptp pps_core sdhci_acpi sdhci mmc_core i2c_hid [last unloaded: i915] [ 34.075010] CPU: 1 PID: 6224 Comm: gem_close_race Tainted: G U 4.9.0-rc3-CI-CI_DRM_1800+ #1 [ 34.075034] Hardware name: /NUC5i7RYB, BIOS RYBDWi35.86A.0355.2016.0224.1501 02/24/2016 [ 34.075057] task: ffff8802459a8040 task.stack: ffffc90000524000 [ 34.075074] RIP: 0010:[<ffffffffa0392cbc>] [<ffffffffa0392cbc>] i915_gem_obj_lookup_or_create_vma+0x8c/0xc0 [i915] [ 34.075118] RSP: 0018:ffffc90000527b68 EFLAGS: 00010202 [ 34.075135] RAX: ffff8802426c5e40 RBX: 0000000000000000 RCX: ffff8802447fc2a8 [ 34.075158] RDX: 0000000000000000 RSI: ffff8802447fc2a8 RDI: ffff880248a4a880 [ 34.075181] RBP: ffffc90000527b88 R08: 0000000000000008 R09: 0000000000000000 [ 34.075203] R10: 0000000000000001 R11: 0000000000000000 R12: ffff880248a4a880 [ 34.075225] R13: ffff8802447fc2a8 R14: ffff880243e9afa8 R15: ffff880248a4a9c8 [ 34.075248] FS: 00007f9b43e59740(0000) GS:ffff880256c80000(0000) knlGS:0000000000000000 [ 34.075273] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 34.075292] CR2: 00007f9b43419140 CR3: 000000024455d000 CR4: 00000000003406e0 [ 34.075314] Stack: [ 34.075323] 0000000000000000 ffffc90000527bd0 ffff880243cb8008 ffff880243e9afa8 [ 34.075353] ffffc90000527c08 ffffffffa03874c7 ffffc90000527bb8 ffff880243e9afa8 [ 34.075383] ffff880243e9afb0 ffffc90000527e10 ffff8802447fc2a8 ffff880243cb8040 [ 34.075414] Call Trace: [ 34.075435] [<ffffffffa03874c7>] eb_lookup_vmas.isra.7+0x247/0x330 [i915] [ 34.075468] [<ffffffffa0388c34>] i915_gem_do_execbuffer.isra.15+0x604/0x1a10 [i915] [ 34.075507] [<ffffffffa039c957>] ? i915_gem_object_get_sg+0x347/0x380 [i915] [ 34.075532] [<ffffffff811a69ce>] ? __might_fault+0x3e/0x90 [ 34.075562] [<ffffffffa038a430>] i915_gem_execbuffer2+0xc0/0x250 [i915] [ 34.075585] [<ffffffff81552926>] drm_ioctl+0x1f6/0x480 [ 34.075604] [<ffffffff8100107a>] ? trace_hardirqs_on_thunk+0x1a/0x1c [ 34.075635] [<ffffffffa038a370>] ? i915_gem_execbuffer+0x330/0x330 [i915] [ 34.075658] [<ffffffff81202d2e>] do_vfs_ioctl+0x8e/0x690 [ 34.075677] [<ffffffff8181582d>] ? _raw_spin_unlock_irqrestore+0x3d/0x60 [ 34.075700] [<ffffffff810fcd51>] ? SyS_timer_settime+0x141/0x1e0 [ 34.075721] [<ffffffff810d6de2>] ? trace_hardirqs_on_caller+0x122/0x1b0 [ 34.075742] [<ffffffff8120336c>] SyS_ioctl+0x3c/0x70 [ 34.075760] [<ffffffff8181602e>] entry_SYSCALL_64_fastpath+0x1c/0xb1 [ 34.075781] Code: 44 a0 48 c7 c2 9a 7e 43 a0 be e0 0d 00 00 48 c7 c7 a0 45 44 a0 e8 55 b8 ce e0 48 85 db 74 a3 49 83 bd f8 03 00 00 00 74 99 0f 0b <0f> 0b 48 89 da 4c 89 ee 4c 89 e7 e8 04 a9 ff ff 48 89 da 49 89 [ 34.075955] RIP [<ffffffffa0392cbc>] i915_gem_obj_lookup_or_create_vma+0x8c/0xc0 [i915] [ 34.075994] RSP <ffffc90000527b68> Testcase: igt/gem_close_race/basic-threads Fixes: db6c2b41 ("drm/i915: Store the vma in an rbtree...") Signed-off-by:
-
Ping Gao authored
All the unused entries in the page table tree(PML4E->PDPE->PDE->PTE) should point to scratch page table/scratch page to avoid page walk error due to the page prefetching. When removing an entry in shadow PPGTT, it need map to scratch page also, the older implementation use single scratch page to assign to all level entries, it doesn't align the page walk behavior when removed entry is in PML, PDP, PD. To avoid potential page walk error this patch implement a scratch page tree to replace the single scratch page. v2: more details in commit message address Kevin's comments. Signed-off-by:
Ping Gao <ping.a.gao@intel.com> Signed-off-by:
-
Du, Changbin authored
When SW wishes to reset the render engine, it will program engine's reset control register and wait response from HW. We need emulate the behavior of this register so guest i915 driver could walk through the engine reset flow. The registers are not emulated in gvt yet, this patch add the emulation logic. v2: add more desc info in commit message. Signed-off-by:
Zhi Wang <zhi.a.wang@intel.com> Signed-off-by:
Du, Changbin <changbin.du@intel.com> Signed-off-by:
-
Zhenyu Wang authored
From commit e95433c7, workload status setting was changed to only capture on error path, but we need to set it properly in normal path too, otherwise we'll fail to complete workload which could lead guest VM vGPU reset. v2: uses braces and add Fixes tag. Fixes: e95433c7 ("drm/i915: Rearrange i915_wait_request() accounting with callers") Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by:
-
Ping Gao authored
Misc ctl related registers are for WA purpose, should detect the stepping info first before updating HW value. Signed-off-by:
-
Ping Gao authored
Need a explicit write_vreg in TLB MMIO write handler, beside that TLB vreg should update correspondingly following HW status to do correct emulation. Signed-off-by:
-
Ping Gao authored
Missing write_vreg in DMA_CTRL write handler would make obsolete value return when read vreg. v2: get data from vreg after updating it. Signed-off-by:
-
Ping Gao authored
Remove the variable 'execlist' as it's unused in function vgpu_has_pending_workload. Signed-off-by:
-
