#
46420777 |
|
04-Dec-2021 |
Rikard Falkeborn <rikard.falkeborn@gmail.com> |
drm/i915/gvt: Constify intel_gvt_sched_policy_ops These are never modified, so make them const to allow the compiler to put them in read-only memory. Signed-off-by: Rikard Falkeborn <rikard.falkeborn@gmail.com> Signed-off-by: Zhi Wang <zhi.a.wang@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20211204105527.15741-5-rikard.falkeborn@gmail.com Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
|
#
a61ac1e7 |
|
05-Mar-2020 |
Chris Wilson <chris@chris-wilson.co.uk> |
drm/i915/gvt: Wean gvt off using dev_priv Teach gvt to use intel_gt directly as it currently assumes direct HW access. [Zhenyu: rebase, fix compiling] Cc: Ding Zhuocheng <zhuocheng.ding@intel.com> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20200304032307.2983-3-zhenyuw@linux.intel.com
|
#
8fde4107 |
|
03-Mar-2020 |
Chris Wilson <chris@chris-wilson.co.uk> |
drm/i915/gvt: Wean gvt off dev_priv->engine[] Stop trying to escape out of the gvt layer to find the engine that we initially setup for use with gvt. Record the engines during initialisation and use them henceforth. add/remove: 1/4 grow/shrink: 22/28 up/down: 341/-1410 (-1069) [Zhenyu: rebase, fix nonpriv register check fault, fix gvt engine thread run failure.] Cc: Ding Zhuocheng <zhuocheng.ding@intel.com> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20200304032307.2983-2-zhenyuw@linux.intel.com
|
#
d858d569 |
|
13-Jun-2019 |
Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> |
drm/i915: update rpm_get/put to use the rpm structure The functions where internally already only using the structure, so we need to just flip the interface. v2: rebase Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Imre Deak <imre.deak@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Acked-by: Imre Deak <imre.deak@intel.com> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20190613232156.34940-7-daniele.ceraolospurio@intel.com
|
#
2e679d48 |
|
21-Jan-2019 |
Jani Nikula <jani.nikula@intel.com> |
drm/i915/gvt: switch to kernel types Mixed C99 and kernel types use is getting ugly. Prefer kernel types. sed -i 's/\buint\(8\|16\|32\|64\)_t\b/u\1/g' Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
16e4dd03 |
|
14-Jan-2019 |
Chris Wilson <chris@chris-wilson.co.uk> |
drm/i915: Markup paired operations on wakerefs The majority of runtime-pm operations are bounded and scoped within a function; these are easy to verify that the wakeref are handled correctly. We can employ the compiler to help us, and reduce the number of wakerefs tracked when debugging, by passing around cookies provided by the various rpm_get functions to their rpm_put counterpart. This makes the pairing explicit, and given the required wakeref cookie the compiler can verify that we pass an initialised value to the rpm_put (quite handy for double checking error paths). For regular builds, the compiler should be able to eliminate the unused local variables and the program growth should be minimal. Fwiw, it came out as a net improvement as gcc was able to refactor rpm_get and rpm_get_if_in_use together, v2: Just s/rpm_put/rpm_put_unchecked/ everywhere, leaving the manual mark up for smaller more targeted patches. v3: Mention the cookie in Returns Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Jani Nikula <jani.nikula@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190114142129.24398-2-chris@chris-wilson.co.uk
|
#
54ff01fd |
|
29-Aug-2018 |
Zhenyu Wang <zhenyuw@linux.intel.com> |
drm/i915/gvt: Give new born vGPU higher scheduling chance This trys to give new born vGPU with higher scheduling chance not only with adding to sched list head and also have higher priority for workload sched for 2 seconds after starting to schedule it. In order for fast GPU execution during VM boot, and ensure guest driver setup with required state given in time. This fixes recent failure seen on one VM with multiple linux VMs running on kernel with commit 2621cefaa42b3("drm/i915: Provide a timeout to i915_gem_wait_for_idle() on setup"), which had shorter setup timeout that caused context state init failed. v2: change to 2s for higher scheduling period Cc: Yuan Hang <hang.yuan@intel.com> Reviewed-by: Hang Yuan <hang.yuan@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
b2b599fb |
|
29-Aug-2018 |
Hang Yuan <hang.yuan@linux.intel.com> |
drm/i915/gvt: move intel_runtime_pm_get out of spin_lock in stop_schedule pm_runtime_get_sync in intel_runtime_pm_get might sleep if i915 device is not active. When stop vgpu schedule, the device may be inactive. So need to move runtime_pm_get out of spin_lock/unlock. Fixes: b24881e0b0b6("drm/i915/gvt: Add runtime_pm_get/put into gvt_switch_mmio Cc: <stable@vger.kernel.org> Signed-off-by: Hang Yuan <hang.yuan@linux.intel.com> Signed-off-by: Xiong Zhang <xiong.y.zhang@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
9a512e23 |
|
18-May-2018 |
Colin Xu <colin.xu@intel.com> |
drm/i915/gvt: Use sched_lock to protect gvt scheduler logic. The scheduler lock(gvt->sched_lock) is used to protect gvt scheduler logic, including the gvt scheduler structure(gvt->scheduler and per vgpu schedule data(vgpu->sched_data, vgpu->sched_ctl). v9: - Change commit author since the patches are improved a lot compared with original version. Original author: Pei Zhang <pei.zhang@intel.com> - Rebase to latest gvt-staging. v8: - Correct coding wqstyle. - Rebase to latest gvt-staging. v7: - Remove gtt_lock since already proteced by gvt_lock and vgpu_lock. v6: - Rebase to latest gvt-staging. v5: - Rebase to latest gvt-staging. v4: - Rebase to latest gvt-staging. v3: update to latest code base Signed-off-by: Pei Zhang <pei.zhang@intel.com> Signed-off-by: Colin Xu <colin.xu@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
89babe7c |
|
03-Apr-2018 |
Zhipeng Gong <zhipeng.gong@intel.com> |
drm/i915/gvt: Update time slice more frequently When there is only one vGPU in GVT-g and it submits workloads continuously, it will not be scheduled out, vgpu_update_timeslice is not called and its sched_in_time is not updated in a long time, which can be several seconds or longer. Once GVT-g pauses to submit workload for this vGPU due to heavy host CPU workload, this vGPU get scheduled out and vgpu_update_timeslice is called, its left_ts will be subtract by a big value from sched_out_time - sched_in_time. When GVT-g is going to submit workload for this vGPU again, it will not be scheduled in until gvt_balance_timeslice reaches stage 0 and reset its left_ts, which introduces several hunderand milliseconds latency. This patch updates time slice in every ms to update sched_in_time timely. v2: revise commit message v3: use more concise expr. (Zhenyu) Signed-off-by: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Zhenyu Wang <zhenyuw@linux.intel.com> Cc: Min He <min.he@intel.com> Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
|
#
292bb0d3 |
|
03-Apr-2018 |
Zhipeng Gong <zhipeng.gong@intel.com> |
drm/i915/gvt: Use real time to do timer check intel_gvt_schedule check timer through a counter and is supposed to wake up to increase the counter every ms. In a system with heavy workload, gvt_service_thread can not get a chance to run right after wake up and will be delayed several milliseconds. As a result, one hundred counter interval means several hundred milliseconds in real time. This patch use real time instead of counter to do timer check. v2: remove static variable. (Zhenyu) v3: correct expire_time update. (Zhenyu) Signed-off-by: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Zhenyu Wang <zhenyuw@linux.intel.com> Cc: Min He <min.he@intel.com> Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
|
#
98039845 |
|
22-Feb-2018 |
Zhenyu Wang <zhenyuw@linux.intel.com> |
drm/i915/gvt: Fix vGPU sched timeslice calculation warning Fix below warning by using proper ktime helper to calculate timeslice. CHECK drivers/gpu/drm/i915//gvt/sched_policy.c drivers/gpu/drm/i915//gvt/sched_policy.c:108 gvt_balance_timeslice() debug: sval_binop_signed: invalid divide LLONG_MIN/-1 drivers/gpu/drm/i915//gvt/sched_policy.c:108 gvt_balance_timeslice() debug: sval_binop_signed: invalid divide LLONG_MIN/-1 Reviewed-by: Zhi Wang <zhi.a.wang@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
9212b13f |
|
26-Jan-2018 |
Weinan Li <weinan.z.li@intel.com> |
drm/i915/gvt: only reset execlist state of one engine during VM engine reset Only reset vgpu execlist state of the exact engine which gets reset request from VM. After read context status from HWSP enabled, KMD will use the saved CSB read pointer but not always read from MMIO. When one engine reset happen, only the read pointer of this engine will be reset, in GVT-g host side also need to align with this policy, otherwise VM may get wrong CSB status after one engine reset compeleted. v2: Split refine and fix patch, code refine(Zhenyu) v3: Move active flag of vgpu scheduler into sched_data(Zhenyu) Cc: Fred Gao <fred.gao@intel.com> Cc: Zhi Wang <zhi.a.wang@intel.com> Cc: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Weinan Li <weinan.z.li@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Zhi Wang <zhi.a.wang@intel.com> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
|
#
61a66947 |
|
15-Jan-2018 |
Zhenyu Wang <zhenyuw@linux.intel.com> |
drm/i915/gvt: cancel scheduler timer when no vGPU exists Stop gvt scheduler timer if no vGPU exists, otherwise it keeps gvt service thread busy to handle request schedule event but no actual schedule activity required. Reviewed-by: Zhi Wang <zhi.a.wang@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
|
#
c130456c |
|
29-Nov-2017 |
Changbin Du <changbin.du@intel.com> |
drm/i915/gvt: Kick scheduler when new workload queued The current schedule policy rely on a 1ms timer to execute workload. This can introduce maximum 1ms unnecessary latency. This is especially bad for small media workloads. And I don't think we need this timer for QoS, but the change is not simply remove the code. So I made a new API intel_gvt_kick_schedule() for future change. Signed-off-by: Changbin Du <changbin.du@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
ba3ee006 |
|
21-Sep-2017 |
Changbin Du <changbin.du@intel.com> |
drm/i915/gvt: Fix GPU hang after reusing vGPU instance across different guest OS We have implemented delayed ring mmio switch mechanism to reduce unnecessary mmio switch. While the vGPU is being destroyed or detached from VM, we need to force the ring switch to host context. The later deadline is missed. Then it got a chance that word load from VM2 might execute under the ring context of VM1 which was attached to a same vGPU instance. Finally, the GPU is hang. This patch guarantee the two deadline are performed. v2: Remove unused variable 'scheduler' Signed-off-by: Changbin Du <changbin.du@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
c713cb2f |
|
24-May-2017 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: Support event based scheduling This patch decouple the time slice calculation and scheduler, let other event be able to trigger scheduling without impact the calculation for QoS. v2: add only one new enum definition. v3: fix typo. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
0e86cc9c |
|
03-May-2017 |
Changbin Du <changbin.du@intel.com> |
drm/i915/gvt: implement per-vm mmio switching optimization Commit ab9da627906a ("drm/i915: make context status notifier head be per engine") gives us a chance to inspect every single request. Then we can eliminate unnecessary mmio switching for same vGPU. We only need mmio switching for different VMs (including host). This patch introduced a new general API intel_gvt_switch_mmio() to replace the old intel_gvt_load/restore_render_mmio(). This function can be further optimized for vGPU to vGPU switching. To support individual ring switch, we track the owner who occupy each ring. When another VM or host request a ring we do the mmio context switching. Otherwise no need to switch the ring. This optimization is very useful if only one guest has plenty of workloads and the host is mostly idle. The best case is no mmio switching will happen. v2: o fix missing ring switch issue. (chuanxiao) o support individual ring switch. Signed-off-by: Changbin Du <changbin.du@intel.com> Reviewed-by: Chuanxiao Dong <chuanxiao.dong@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
ae157902 |
|
19-Apr-2017 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: avoid unnecessary vgpu switch It's no need to switch vgpu if next vgpu is the same with current vgpu, otherwise it will make performance drop in some case. v2: correct the comments. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
954180aa |
|
12-Apr-2017 |
Zhenyu Wang <zhenyuw@linux.intel.com> |
drm/i915/gvt: remove some debug messages in scheduler timer handler As those debug messages might appear in every timer call for scheduler, it's too noisy, eat too much log and aren't meaningful. So remove them. Cc: Ping Gao <ping.a.gao@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
0b063bd3 |
|
31-Mar-2017 |
Zhenyu Wang <zhenyuw@linux.intel.com> |
drm/i915/gvt: cleanup some too chatty scheduler message It's too chatty to have three places to tell us which one is next vgpu for schedule. My log file was bloated to eat all disk space.. Cc: Ping Gao <ping.a.gao@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
b35f34d1 |
|
29-Mar-2017 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: control the scheduler by timeslice usage The timeslice usage will determine vGPU whether has chance to schedule or not at every vGPU switch checkpoint. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
39d467c2 |
|
29-Mar-2017 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: add basic function for weight control This method tries to guarantee precision in second level, with the adjustment conducted in every 100ms. At the end of each vGPU switch calculate the sched time and subtract it from the time slice allocated; the allocated time slice for every 100ms together with remaining timeslice, will be used to decide how much timeslice allocated to this vGPU in the next 100ms slice, with the end goal to guarantee weight ratio in second level. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
bc90d097 |
|
29-Mar-2017 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: define weight according to vGPU type The weight defines proportional control of physical GPU resource shared between vGPUs. So far the weight is tied to a specific vGPU type, i.e when creating multiple vGPUs with different types, they will inherit different weights. e.g. The weight of type GVTg_V5_2 is 8, the weight of type GVTg_V5_4 is 4, so vGPU of type GVTg_V5_2 has double vGPU resource of vGPU type GVTg_V5_4. TODO: allow user control the weight setting in the future. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
32356920 |
|
29-Mar-2017 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: factor out the scheduler Factor out the scheduler to a more clear structure, the basic logic is to find out next vGPU first and then schedule it. vGPUs were ordered in a LRU list, scheduler scan from the LRU list head and choose the first vGPU who has pending workload. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
f6504cce |
|
29-Mar-2017 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: add some statistic routine for scheduler Add some statistic routine to collect the time when vGPU is scheduled in/out and the time of the last ctx submission. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
91d0101a |
|
29-Mar-2017 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: use hrtimer replace delayed_work in scheduler Currently the scheduler is triggered by delayed_work, which doesn't provide precision at microsecond level. Move to hrtimer instead for more accurate control. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Reviewed-by: Kevin Tian <kevin.tian@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
2958b901 |
|
16-Mar-2017 |
Zhenyu Wang <zhenyuw@linux.intel.com> |
drm/i915/gvt: Fix gvt scheduler interval time Fix to correctly assign 1ms for gvt scheduler interval time, as previous code using HZ is pretty broken. And use no delay for start gvt scheduler function. Fixes: 4b63960ebd3f ("drm/i915/gvt: vGPU schedule policy framework") Cc: Zhi Wang <zhi.a.wang@intel.com> Cc: stable@vger.kernel.org # v4.10+ Acked-by: Chuanxiao Dong <chuanxiao.dong@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
6e3745ce |
|
08-Feb-2017 |
Changbin Du <changbin.du@intel.com> |
drm/i915/gvt: remove a noisy unimportant log in sched_policy Remove below unimportant log which is too noisy. 'no current vgpu search from q head' Signed-off-by: Changbin Du <changbin.du@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
337d0665 |
|
26-Oct-2016 |
Ping Gao <ping.a.gao@intel.com> |
drm/i915/gvt: remove unused variable 'execlist' Remove the variable 'execlist' as it's unused in function vgpu_has_pending_workload. Signed-off-by: Ping Gao <ping.a.gao@intel.com> Reviewed-by: Zhi Wang <zhi.a.wang@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
999ccb40 |
|
20-Oct-2016 |
Changbin Du <changbin.du@intel.com> |
drm/i915/gvt: mark symbols static where possible Mark all local functions & variables as static. Signed-off-by: Du, Changbin <changbin.du@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
0fac21e7 |
|
19-Oct-2016 |
Zhenyu Wang <zhenyuw@linux.intel.com> |
drm/i915/gvt: properly access enabled intel_engine_cs Switch to use new for_each_engine() helper to properly access enabled intel_engine_cs as i915 core has changed that to be dynamic managed. At GVT-g init time would still depend on ring mask to determine engine list as it's earlier. Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
feddf6e8 |
|
20-Oct-2016 |
Zhenyu Wang <zhenyuw@linux.intel.com> |
drm/i915/gvt: clean up intel_gvt.h as interface for i915 core i915 core should only call functions and structures exposed through intel_gvt.h. Remove internal gvt.h and i915_pvinfo.h. Change for internal intel_gvt structure as private handler which not requires to expose gvt internal structure for i915 core. v2: Fix per Chris's comment - carefully handle dev_priv->gvt assignment - add necessary bracket for macro helper - forward declartion struct intel_gvt - keep free operation within same file handling alloc v3: fix use after free and remove intel_gvt.initialized v4: change to_gvt() to an inline Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|
#
4b63960e |
|
01-May-2016 |
Zhi Wang <zhi.a.wang@intel.com> |
drm/i915/gvt: vGPU schedule policy framework This patch introduces a vGPU schedule policy framework, with a timer based schedule policy module for now Signed-off-by: Zhi Wang <zhi.a.wang@intel.com> Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
|