- 27 Oct, 2017 17 commits
-
-
Andres Rodriguez authored
In systems under heavy load the IH work may experience significant scheduling delays. Under load + system workqueue: Max Latency: 7.023695 ms Avg Latency: 0.263994 ms Under load + high priority workqueue: Max Latency: 1.162568 ms Avg Latency: 0.163213 ms Further work is required to measure the impact of per-cpu settings on IH performance. Signed-off-by:Andres Rodriguez <andres.rodriguez@amd.com> Signed-off-by:
Felix Kuehling <Felix.Kuehling@amd.com> Acked-by:
Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by:
-
Andres Rodriguez authored
We don't need to wait for all work to complete in the IH exit function. We only need to make sure the interrupt_work has finished executing to guarantee that ih_kfifo is no longer in use. Signed-off-by:
-
Andres Rodriguez authored
A larger buffer will let us accommodate applications with a large amount of semi-simultaneous event signals. Signed-off-by:
-
Andres Rodriguez authored
Replace our implementation of a lockless ring buffer with the standard linux kernel kfifo. We shouldn't maintain our own version of a standard data structure. Signed-off-by:
-
Oded Gabbay authored
Signed-off-by:
Oded Gabbay <oded.gabbay@amd.com> Reviewed-by:
Ben Goz <ben.goz@amd.com> Signed-off-by:
-
Felix Kuehling authored
This allows increasing the KFD_SIGNAL_EVENT_LIMIT in kfd_ioctl.h without breaking processes built with older kfd_ioctl.h versions. Signed-off-by:
-
Felix Kuehling authored
This speeds up signal lookup when the IH ring entry includes a valid context ID or partial context ID. Only if the context ID is found to be invalid, fall back to an exhaustive search of all signaled events. Signed-off-by:
-
Felix Kuehling authored
Signal slots are identical to event IDs. Replace the used_slot_bitmap and events hash table with an IDR to allocate and lookup event IDs and signal slots more efficiently. Signed-off-by:
-
Felix Kuehling authored
The first event page is always big enough to handle all events. Handling of multiple events pages is not supported by user mode, and not necessary. Signed-off-by:
Yong Zhao <yong.zhao@amd.com> Signed-off-by:
-
Felix Kuehling authored
Use standard wait queues for waiting and waking up waiting threads instead of inventing our own. We still have our own wait loop because the HSA event semantics require the ability to have one thread waiting on multiple wait queues (events) at the same time. Signed-off-by:
Kent Russell <kent.russell@amd.com> Signed-off-by:
-
Felix Kuehling authored
This always identical with the index of the event_waiter in the array. No need to store it in the waiter record. Signed-off-by:
-
Felix Kuehling authored
When an event with pending waiters is destroyed, those waiters may end up sleeping forever unless they are notified and woken up. Implement the notification by clearing the waiter->event pointer, which becomes invalid anyway, when the event is freed, and waking up the waiting tasks. Waiters on an event that's destroyed return failure. Signed-off-by:
-
Felix Kuehling authored
Cleaned up the code while resolving some potential bugs and inconsistencies in the process. Clean-ups: * Remove enum kfd_event_wait_result, which duplicates KFD_IOC_EVENT_RESULT definitions * alloc_event_waiters can be called without holding p->event_mutex * Return an error code from copy_signaled_event_data instead of bool * Clean up error handling code paths to minimize duplication in kfd_wait_on_events Fixes: * Consistently return an error code from kfd_wait_on_events and set wait_result to KFD_IOC_WAIT_RESULT_FAIL in all failure cases. * Always call free_waiters while holding p->event_mutex * copy_signaled_event_data might sleep. Don't call it while the task state is TASK_INTERRUPTIBLE. Signed-off-by:
-
Sean Keely authored
Signed-off-by:
Sean Keely <sean.keely@amd.com> Signed-off-by:
-
Sean Keely authored
If kfd_wait_on_events can return immediately, we don't need to populate the wait list and don't need to enter the sleep-loop. Signed-off-by:
-
Felix Kuehling authored
The kfd_process doesn't own a reference to the mm_struct, so it can disappear without warning even while the kfd_process still exists. Therefore, avoid dereferencing the kfd_process.mm pointer and make it opaque. Use get_task_mm to get a temporary reference to the mm when it's needed. v2: removed unnecessary WARN_ON Signed-off-by:
-
Besar Wicaksono authored
This enables SDMA signalling with event interrupt. Signed-off-by:
Besar Wicaksono <Besar.Wicaksono@amd.com> Signed-off-by:
-
- 02 Nov, 2017 3 commits
-
-
Dave Airlie authored
Linux 4.14-rc7 Requested by Ben Skeggs for nouveau to avoid major conflicts, and things were getting a bit conflicty already, esp around amdgpu reverts.
-
Dave Airlie authored
For 4.15 * tag 'drm-hisilicon-next-2017-11-01' of github.com:xin3liang/linux: drm/hisilicon: Ensure LDI regs are properly configured.
-
git://people.freedesktop.org/~robclark/linuxDave Airlie authored
+ preemption support for a5xx[1][2] + display fixes for 8x96 (snapdragon 820) including fixes for 4k scanout (hwpipe assignment re-work to handle multiple hwpipe assigned to plane for wide scanout) + async cursor plane updates and fixes + refactor adreno_bind/hwinit.. still defer fw loading until device open, but move clk/irq/etc to probe/bind time to fix issues when fw isn't present in filesys + clk/dt bindings cleanups w/ backward compat via msm_clk_get() (dt docs part ack'ed by Rob Herring) + fw loading re-work with helper to handle either /lib/firmware/qcom/$fw or /lib/firmware/$fw.. background, we've started landing fw for some of generations in linux-firmware, but there is a preference to put fw files under 'qcom' subdirectory, which is not what was done on android or for people who copied fw from android. So now we first look in qcom subdir and then fallback to the original location. + bunch of GPU debugging enhancements, to dump full cmdline of processes that trigger faults, and to add a new debugfs to capture cmdstream of just submits that triggered faults.. both quite useful for piglit ;-) * tag 'drm-msm-next-2017-11-01' of git://people.freedesktop.org/~robclark/linux: (38 commits) drm/msm: use %z format modifier for printing size_t drm/msm/mdp5: Don't use async plane update path if plane visibility changes drm/msm/mdp5: mdp5_crtc: Restore cursor state only if LM cursors are enabled drm/msm/mdp5: Update mdp5_pipe_assign to spit out both planes drm/msm/mdp5: Prepare mdp5_pipe_assign for some rework drm/msm: remove mdp5_cursor_plane_funcs drm/msm: update cursors asynchronously through atomic drm/msm/atomic: switch to drm_atomic_helper_check drm/msm/mdp5: restore cursor state when enabling crtc drm/msm/mdp5: don't use autosuspend drm/msm/mdp5: ignore planes that are not visible drm/msm: dump submits which triggered gpu hang drm/msm: preserve IOVAs in submit's bo table drm/msm/rd: allow adding addition msg to top of dump drm/msm: split rd debugfs file drm/msm: add special _get_vaddr_active() for cmdstream dumps drm/msm: show task cmdline in gpu recovery messages drm/msm: dump a rd GPUADDR header for all buffers in the command drm/msm: Removed unused struct_mutex_task drm/msm: Implement preemption for A5XX targets ...
-
- 01 Nov, 2017 2 commits
-
-
Arnd Bergmann authored
The return type of ARRAY_SIZE() is size_t, so we have to use %zu instead of %lu to avoid this warning: drivers/gpu/drm/msm/msm_gpu.c: In function 'msm_gpu_init': drivers/gpu/drm/msm/msm_gpu.c:742:31: error: format '%lu' expects argument of type 'long unsigned int', but argument 7 has type 'unsigned int' [-Werror=format=] The warning it otherwise harmless as size_t is always the same size as unsigned long in all supported architectures, but gcc doesn't know that. Fixes: c2fceabca6d5 ("drm/msm: Support multiple ringbuffers") Signed-off-by:Arnd Bergmann <arnd@arndb.de> Signed-off-by:
Rob Clark <robdclark@gmail.com>
-
Peter Griffin authored
This patch fixes the following soft lockup: BUG: soft lockup - CPU#0 stuck for 23s! [weston:307] On weston idle-timeout the IP is powered down and reset asserted. On weston resume we get a massive vblank IRQ storm due to the LDI registers having lost some state. This state loss is caused by ade_crtc_atomic_begin() not calling ade_ldi_set_mode(). With this patch applied resuming from Weston idle-timeout works well. Signed-off-by:
Peter Griffin <peter.griffin@linaro.org> Tested-by:
John Stultz <john.stultz@linaro.org> Cc: stable@vger.kernel.org Reviewed-by:
Xinliang Liu <xinliang.liu@linaro.org> Signed-off-by:
-
- 29 Oct, 2017 18 commits
-
-
Linus Torvalds authored
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/netLinus Torvalds authored
Pull networking fixes from David Miller: 1) Fix route leak in xfrm_bundle_create(). 2) In mac80211, validate user rate mask before configuring it. From Johannes Berg. 3) Properly enforce memory limits in fair queueing code, from Toke Hoiland-Jorgensen. 4) Fix lockdep splat in inet_csk_route_req(), from Eric Dumazet. 5) Fix TSO header allocation and management in mvpp2 driver, from Yan Markman. 6) Don't take socket lock in BH handler in strparser code, from Tom Herbert. 7) Don't show sockets from other namespaces in AF_UNIX code, from Andrei Vagin. 8) Fix double free in error path of tap_open(), from Girish Moodalbail. 9) Fix TX map failure path in igb and ixgbe, from Jean-Philippe Brucker and Alexander Duyck. 10) Fix DCB mode programming in stmmac driver, from Jose Abreu. 11) Fix err_count handling in various tunnels (ipip, ip6_gre). From Xin Long. 12) Properly align SKB head before building SKB in tuntap, from Jason Wang. 13) Avoid matching qdiscs with a zero handle during lookups, from Cong Wang. 14) Fix various endianness bugs in sctp, from Xin Long. 15) Fix tc filter callback races and add selftests which trigger the problem, from Cong Wang. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (73 commits) selftests: Introduce a new test case to tc testsuite selftests: Introduce a new script to generate tc batch file net_sched: fix call_rcu() race on act_sample module removal net_sched: add rtnl assertion to tcf_exts_destroy() net_sched: use tcf_queue_work() in tcindex filter net_sched: use tcf_queue_work() in rsvp filter net_sched: use tcf_queue_work() in route filter net_sched: use tcf_queue_work() in u32 filter net_sched: use tcf_queue_work() in matchall filter net_sched: use tcf_queue_work() in fw filter net_sched: use tcf_queue_work() in flower filter net_sched: use tcf_queue_work() in flow filter net_sched: use tcf_queue_work() in cgroup filter net_sched: use tcf_queue_work() in bpf filter net_sched: use tcf_queue_work() in basic filter net_sched: introduce a workqueue for RCU callbacks of tc filter sctp: fix some type cast warnings introduced since very beginning sctp: fix a type cast warnings that causes a_rwnd gets the wrong value sctp: fix some type cast warnings introduced by transport rhashtable sctp: fix some type cast warnings introduced by stream reconf ... -
David S. Miller authored
Cong Wang says: ==================== net_sched: fix races with RCU callbacks Recently, the RCU callbacks used in TC filters and TC actions keep drawing my attention, they introduce at least 4 race condition bugs: 1. A simple one fixed by Daniel: commit c78e1746 Author: Daniel Borkmann <daniel@iogearbox.net> Date: Wed May 20 17:13:33 2015 +0200 net: sched: fix call_rcu() race on classifier module unloads 2. A very nasty one fixed by me: commit 1697c4bb Author: Cong Wang <xiyou.wangcong@gmail.com> Date: Mon Sep 11 16:33:32 2017 -0700 net_sched: carefully handle tcf_block_put() 3. Two more bugs found by Chris: https://patchwork.ozlabs.org/patch/826696/ https://patchwork.ozlabs.org/patch/826695/ Usually RCU callbacks are simple, however for TC filters and actions, they are complex because at least TC actions could be destroyed together with the TC filter in one callback. And RCU callbacks are invoked in BH context, without locking they are parallel too. All of these contribute to the cause of these nasty bugs. Alternatively, we could also: a) Introduce a spinlock to serialize these RCU callbacks. But as I said in commit 1697c4bb ("net_sched: carefully handle tcf_block_put()"), it is very hard to do because of tcf_chain_dump(). Potentially we need to do a lot of work to make it possible (if not impossible). b) Just get rid of these RCU callbacks, because they are not necessary at all, callers of these call_rcu() are all on slow paths and holding RTNL lock, so blocking is allowed in their contexts. However, David and Eric dislike adding synchronize_rcu() here. As suggested by Paul, we could defer the work to a workqueue and gain the permission of holding RTNL again without any performance impact, however, in tcf_block_put() we could have a deadlock when flushing workqueue while hodling RTNL lock, the trick here is to defer the work itself in workqueue and make it queued after all other works so that we keep the same ordering to avoid any use-after-free. Please see the first patch for details. Patch 1 introduces the infrastructure, patch 2~12 move each tc filter to the new tc filter workqueue, patch 13 adds an assertion to catch potential bugs like this, patch 14 closes another rcu callback race, patch 15 and patch 16 add new test cases. ==================== Reported-by:
Chris Mi <chrism@mellanox.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Pirko <jiri@resnulli.us> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by:
Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Chris Mi authored
In this patchset, we fixed a tc bug. This patch adds the test case that reproduces the bug. To run this test case, user should specify an existing NIC device: # sudo ./tdc.py -d enp4s0f0 This test case belongs to category "flower". If user doesn't specify a NIC device, the test cases belong to "flower" will not be run. In this test case, we create 1M filters and all filters share the same action. When destroying all filters, kernel should not panic. It takes about 18s to run it. Acked-by:
Jamal Hadi Salim <jhs@mojatatu.com> Acked-by:
Lucas Bates <lucasb@mojatatu.com> Signed-off-by:
-
Chris Mi authored
# ./tdc_batch.py -h usage: tdc_batch.py [-h] [-n NUMBER] [-o] [-s] [-p] device file TC batch file generator positional arguments: device device name file batch file name optional arguments: -h, --help show this help message and exit -n NUMBER, --number NUMBER how many lines in batch file -o, --skip_sw skip_sw (offload), by default skip_hw -s, --share_action all filters share the same action -p, --prio all filters have different prio Acked-by: -
Cong Wang authored
Similar to commit c78e1746 ("net: sched: fix call_rcu() race on classifier module unloads"), we need to wait for flying RCU callback tcf_sample_cleanup_rcu(). Cc: Yotam Gigi <yotamg@mellanox.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Pirko <jiri@resnulli.us> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by:
-
Cong Wang authored
After previous patches, it is now safe to claim that tcf_exts_destroy() is always called with RTNL lock. Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Pirko <jiri@resnulli.us> Cc: John Fastabend <john.fastabend@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
Cong Wang authored
Defer the tcf_exts_destroy() in RCU callback to tc filter workqueue and get RTNL lock. Reported-by:
-
