Trap handler is set per-process per-device and is unrelated
to queue management.

Move implementation closer to TMA setup code.
Signed-off-by: NJay Cornwall <jay.cornwall@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Correct pipe offset calculation in is_pipe_enabled function,
it should be done in queues.
Signed-off-by: NJiansong Chen <Jiansong.Chen@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Add KFD support for dimgrey cavefish.

v2: rebase (Alex)
Signed-off-by: NChengming Gui <Jack.Gui@amd.com>
Reviewed-by: NTao Zhou <tao.zhou1@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This patch is to add GFX10 based APU Van Gogh KFD support. We will treat Van
Gogh as "dgpu" (bypass IOMMU v2).
Signed-off-by: NHuang Rui <ray.huang@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NYong Zhao <Yong.Zhao@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Move doorbell allocation for a process into kfd device and
allocate doorbell space in each PDD during process creation.
Currently, KFD manages its own doorbell space but for some
devices, amdgpu would allocate the complete doorbell
space instead of leaving a chunk of doorbell space for KFD to
manage. In a system with mix of such devices, KFD would need
to request process doorbell space based on the type of device,
either from amdgpu or from its own doorbell space.
Signed-off-by: NMukul Joshi <mukul.joshi@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Reduce the eviction and restore messages from INFO level to DEBUG level.
Signed-off-by: NPhilip Cox <Philip.Cox@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Add per-process eviction counters to sysfs to keep track of
how many eviction events have happened for each process.

v2: rename the stats dir, and track all evictions per process, per device.
v3: Simplify the stats kobject handling and cleanup.
v4: more code cleanup
Signed-off-by: NPhilip Cox <Philip.Cox@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Extending the module parameter debug_evictions to also print a stack
trace when the eviction code path is called.
Signed-off-by: NPhilip Cox <Philip.Cox@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

PASID is defined as a few different types in iommu including "int",
"u32", and "unsigned int". To be consistent and to match with uapi
definitions, define PASID and its variations (e.g. max PASID) as "u32".
"u32" is also shorter and a little more explicit than "unsigned int".

No PASID type change in uapi although it defines PASID as __u64 in
some places.
Suggested-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NFenghua Yu <fenghua.yu@intel.com>
Signed-off-by: NBorislav Petkov <bp@suse.de>
Reviewed-by: NTony Luck <tony.luck@intel.com>
Reviewed-by: NLu Baolu <baolu.lu@linux.intel.com>
Acked-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Acked-by: NJoerg Roedel <jroedel@suse.de>
Link: https://lkml.kernel.org/r/1600187413-163670-2-git-send-email-fenghua.yu@intel.com

In the resume stage of GPU recovery, start_cpsch will call pm_init
which set pm->allocated as false, cause the next pm_release_ib has
no chance to release ib memory.

Add pm_release_ib in stop_cpsch which will be called in the suspend
stage of GPU recovery.
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NDennis Li <Dennis.Li@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The crash log as the below:

[Thu Aug 20 23:18:14 2020] general protection fault: 0000 [#1] SMP NOPTI
[Thu Aug 20 23:18:14 2020] CPU: 152 PID: 1837 Comm: kworker/152:1 Tainted: G           OE     5.4.0-42-generic #46~18.04.1-Ubuntu
[Thu Aug 20 23:18:14 2020] Hardware name: GIGABYTE G482-Z53-YF/MZ52-G40-00, BIOS R12 05/13/2020
[Thu Aug 20 23:18:14 2020] Workqueue: events amdgpu_ras_do_recovery [amdgpu]
[Thu Aug 20 23:18:14 2020] RIP: 0010:evict_process_queues_cpsch+0xc9/0x130 [amdgpu]
[Thu Aug 20 23:18:14 2020] Code: 49 8d 4d 10 48 39 c8 75 21 eb 44 83 fa 03 74 36 80 78 72 00 74 0c 83 ab 68 01 00 00 01 41 c6 45 41 00 48 8b 00 48 39 c8 74 25 <80> 78 70 00 c6 40 6d 01 74 ee 8b 50 28 c6 40 70 00 83 ab 60 01 00
[Thu Aug 20 23:18:14 2020] RSP: 0018:ffffb29b52f6fc90 EFLAGS: 00010213
[Thu Aug 20 23:18:14 2020] RAX: 1c884edb0a118914 RBX: ffff8a0d45ff3c00 RCX: ffff8a2d83e41038
[Thu Aug 20 23:18:14 2020] RDX: 0000000000000000 RSI: 0000000000000082 RDI: ffff8a0e2e4178c0
[Thu Aug 20 23:18:14 2020] RBP: ffffb29b52f6fcb0 R08: 0000000000001b64 R09: 0000000000000004
[Thu Aug 20 23:18:14 2020] R10: ffffb29b52f6fb78 R11: 0000000000000001 R12: ffff8a0d45ff3d28
[Thu Aug 20 23:18:14 2020] R13: ffff8a2d83e41028 R14: 0000000000000000 R15: 0000000000000000
[Thu Aug 20 23:18:14 2020] FS:  0000000000000000(0000) GS:ffff8a0e2e400000(0000) knlGS:0000000000000000
[Thu Aug 20 23:18:14 2020] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[Thu Aug 20 23:18:14 2020] CR2: 000055c783c0e6a8 CR3: 00000034a1284000 CR4: 0000000000340ee0
[Thu Aug 20 23:18:14 2020] Call Trace:
[Thu Aug 20 23:18:14 2020]  kfd_process_evict_queues+0x43/0xd0 [amdgpu]
[Thu Aug 20 23:18:14 2020]  kfd_suspend_all_processes+0x60/0xf0 [amdgpu]
[Thu Aug 20 23:18:14 2020]  kgd2kfd_suspend.part.7+0x43/0x50 [amdgpu]
[Thu Aug 20 23:18:14 2020]  kgd2kfd_pre_reset+0x46/0x60 [amdgpu]
[Thu Aug 20 23:18:14 2020]  amdgpu_amdkfd_pre_reset+0x1a/0x20 [amdgpu]
[Thu Aug 20 23:18:14 2020]  amdgpu_device_gpu_recover+0x377/0xf90 [amdgpu]
[Thu Aug 20 23:18:14 2020]  ? amdgpu_ras_error_query+0x1b8/0x2a0 [amdgpu]
[Thu Aug 20 23:18:14 2020]  amdgpu_ras_do_recovery+0x159/0x190 [amdgpu]
[Thu Aug 20 23:18:14 2020]  process_one_work+0x20f/0x400
[Thu Aug 20 23:18:14 2020]  worker_thread+0x34/0x410

When GPU hang, user process will fail to create a compute queue whose
struct object will be freed later, but driver wrongly add this queue to
queue list of the proccess. And then kfd_process_evict_queues will
access a freed memory, which cause a system crash.

v2:
The failure to execute_queues should probably not be reported to
the caller of create_queue, because the queue was already created.
Therefore change to ignore the return value from execute_queues.
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NDennis Li <Dennis.Li@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

In the resume stage of GPU recovery, start_cpsch will call pm_init
which set pm->allocated as false, cause the next pm_release_ib has
no chance to release ib memory.

Add pm_release_ib in stop_cpsch which will be called in the suspend
stage of GPU recovery.
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NDennis Li <Dennis.Li@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The crash log as the below:

[Thu Aug 20 23:18:14 2020] general protection fault: 0000 [#1] SMP NOPTI
[Thu Aug 20 23:18:14 2020] CPU: 152 PID: 1837 Comm: kworker/152:1 Tainted: G           OE     5.4.0-42-generic #46~18.04.1-Ubuntu
[Thu Aug 20 23:18:14 2020] Hardware name: GIGABYTE G482-Z53-YF/MZ52-G40-00, BIOS R12 05/13/2020
[Thu Aug 20 23:18:14 2020] Workqueue: events amdgpu_ras_do_recovery [amdgpu]
[Thu Aug 20 23:18:14 2020] RIP: 0010:evict_process_queues_cpsch+0xc9/0x130 [amdgpu]
[Thu Aug 20 23:18:14 2020] Code: 49 8d 4d 10 48 39 c8 75 21 eb 44 83 fa 03 74 36 80 78 72 00 74 0c 83 ab 68 01 00 00 01 41 c6 45 41 00 48 8b 00 48 39 c8 74 25 <80> 78 70 00 c6 40 6d 01 74 ee 8b 50 28 c6 40 70 00 83 ab 60 01 00
[Thu Aug 20 23:18:14 2020] RSP: 0018:ffffb29b52f6fc90 EFLAGS: 00010213
[Thu Aug 20 23:18:14 2020] RAX: 1c884edb0a118914 RBX: ffff8a0d45ff3c00 RCX: ffff8a2d83e41038
[Thu Aug 20 23:18:14 2020] RDX: 0000000000000000 RSI: 0000000000000082 RDI: ffff8a0e2e4178c0
[Thu Aug 20 23:18:14 2020] RBP: ffffb29b52f6fcb0 R08: 0000000000001b64 R09: 0000000000000004
[Thu Aug 20 23:18:14 2020] R10: ffffb29b52f6fb78 R11: 0000000000000001 R12: ffff8a0d45ff3d28
[Thu Aug 20 23:18:14 2020] R13: ffff8a2d83e41028 R14: 0000000000000000 R15: 0000000000000000
[Thu Aug 20 23:18:14 2020] FS:  0000000000000000(0000) GS:ffff8a0e2e400000(0000) knlGS:0000000000000000
[Thu Aug 20 23:18:14 2020] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[Thu Aug 20 23:18:14 2020] CR2: 000055c783c0e6a8 CR3: 00000034a1284000 CR4: 0000000000340ee0
[Thu Aug 20 23:18:14 2020] Call Trace:
[Thu Aug 20 23:18:14 2020]  kfd_process_evict_queues+0x43/0xd0 [amdgpu]
[Thu Aug 20 23:18:14 2020]  kfd_suspend_all_processes+0x60/0xf0 [amdgpu]
[Thu Aug 20 23:18:14 2020]  kgd2kfd_suspend.part.7+0x43/0x50 [amdgpu]
[Thu Aug 20 23:18:14 2020]  kgd2kfd_pre_reset+0x46/0x60 [amdgpu]
[Thu Aug 20 23:18:14 2020]  amdgpu_amdkfd_pre_reset+0x1a/0x20 [amdgpu]
[Thu Aug 20 23:18:14 2020]  amdgpu_device_gpu_recover+0x377/0xf90 [amdgpu]
[Thu Aug 20 23:18:14 2020]  ? amdgpu_ras_error_query+0x1b8/0x2a0 [amdgpu]
[Thu Aug 20 23:18:14 2020]  amdgpu_ras_do_recovery+0x159/0x190 [amdgpu]
[Thu Aug 20 23:18:14 2020]  process_one_work+0x20f/0x400
[Thu Aug 20 23:18:14 2020]  worker_thread+0x34/0x410

When GPU hang, user process will fail to create a compute queue whose
struct object will be freed later, but driver wrongly add this queue to
queue list of the proccess. And then kfd_process_evict_queues will
access a freed memory, which cause a system crash.

v2:
The failure to execute_queues should probably not be reported to
the caller of create_queue, because the queue was already created.
Therefore change to ignore the return value from execute_queues.
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NDennis Li <Dennis.Li@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Add __user annotation to fix related sparse warning while reading
SDMA counters from userland.
Also, rework the read SDMA counters function by removing redundant
checks.
Reported-by: Nkernel test robot <lkp@intel.com>
Signed-off-by: NMukul Joshi <mukul.joshi@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The whole approach wasn't thought through till the end.

We already had a reset lock like this in the past and it caused the same problems like this one.

Completely revert the patch for now and add individual trylock protection to the hardware access functions as necessary.

This reverts commit df9c8d1a.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

when GPU hang, driver has multi-paths to enter amdgpu_device_gpu_recover,
the atomic adev->in_gpu_reset and hive->in_reset are used to avoid
re-entering GPU recovery.

During GPU reset and resume, it is unsafe that other threads access GPU,
which maybe cause GPU reset failed. Therefore the new rw_semaphore
adev->reset_sem is introduced, which protect GPU from being accessed by
external threads during recovery.

v2:
1. add rwlock for some ioctls, debugfs and file-close function.
2. change to use dqm->is_resetting and dqm_lock for protection in kfd
driver.
3. remove try_lock and change adev->in_gpu_reset as atomic, to avoid
re-enter GPU recovery for the same GPU hang.

v3:
1. change back to use adev->reset_sem to protect kfd callback
functions, because dqm_lock couldn't protect all codes, for example:
free_mqd must be called outside of dqm_lock;

[ 1230.176199] Hardware name: Supermicro SYS-7049GP-TRT/X11DPG-QT, BIOS 3.1 05/23/2019
[ 1230.177221] Call Trace:
[ 1230.178249]  dump_stack+0x98/0xd5
[ 1230.179443]  amdgpu_virt_kiq_reg_write_reg_wait+0x181/0x190 [amdgpu]
[ 1230.180673]  gmc_v9_0_flush_gpu_tlb+0xcc/0x310 [amdgpu]
[ 1230.181882]  amdgpu_gart_unbind+0xa9/0xe0 [amdgpu]
[ 1230.183098]  amdgpu_ttm_backend_unbind+0x46/0x180 [amdgpu]
[ 1230.184239]  ? ttm_bo_put+0x171/0x5f0 [ttm]
[ 1230.185394]  ttm_tt_unbind+0x21/0x40 [ttm]
[ 1230.186558]  ttm_tt_destroy.part.12+0x12/0x60 [ttm]
[ 1230.187707]  ttm_tt_destroy+0x13/0x20 [ttm]
[ 1230.188832]  ttm_bo_cleanup_memtype_use+0x36/0x80 [ttm]
[ 1230.189979]  ttm_bo_put+0x1be/0x5f0 [ttm]
[ 1230.191230]  amdgpu_bo_unref+0x1e/0x30 [amdgpu]
[ 1230.192522]  amdgpu_amdkfd_free_gtt_mem+0xaf/0x140 [amdgpu]
[ 1230.193833]  free_mqd+0x25/0x40 [amdgpu]
[ 1230.195143]  destroy_queue_cpsch+0x1a7/0x270 [amdgpu]
[ 1230.196475]  pqm_destroy_queue+0x105/0x260 [amdgpu]
[ 1230.197819]  kfd_ioctl_destroy_queue+0x37/0x70 [amdgpu]
[ 1230.199154]  kfd_ioctl+0x277/0x500 [amdgpu]
[ 1230.200458]  ? kfd_ioctl_get_clock_counters+0x60/0x60 [amdgpu]
[ 1230.201656]  ? tomoyo_file_ioctl+0x19/0x20
[ 1230.202831]  ksys_ioctl+0x98/0xb0
[ 1230.204004]  __x64_sys_ioctl+0x1a/0x20
[ 1230.205174]  do_syscall_64+0x5f/0x250
[ 1230.206339]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

2. remove try_lock and introduce atomic hive->in_reset, to avoid
re-enter GPU recovery.

v4:
1. remove an unnecessary whitespace change in kfd_chardev.c
2. remove comment codes in amdgpu_device.c
3. add more detailed comment in commit message
4. define a wrap function amdgpu_in_reset

v5:
1. Fix some style issues.
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Suggested-by: NAndrey Grodzovsky <andrey.grodzovsky@amd.com>
Suggested-by: NChristian König <christian.koenig@amd.com>
Suggested-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Suggested-by: NLijo Lazar <Lijo.Lazar@amd.com>
Suggested-by: NLuben Tukov <luben.tuikov@amd.com>
Signed-off-by: NDennis Li <Dennis.Li@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Add KFD support for Navy Flounder.
Signed-off-by: NChengming Gui <Jack.Gui@amd.com>
Reviewed-by: NTao Zhou <tao.zhou1@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

[  150.887733] ======================================================
[  150.893903] WARNING: possible circular locking dependency detected
[  150.905917] ------------------------------------------------------
[  150.912129] kfdtest/4081 is trying to acquire lock:
[  150.917002] ffff8f7f3762e118 (&mm->mmap_sem#2){++++}, at:
                                 __might_fault+0x3e/0x90
[  150.924490]
               but task is already holding lock:
[  150.930320] ffff8f7f49d229e8 (&dqm->lock_hidden){+.+.}, at:
                                destroy_queue_cpsch+0x29/0x210 [amdgpu]
[  150.939432]
               which lock already depends on the new lock.

[  150.947603]
               the existing dependency chain (in reverse order) is:
[  150.955074]
               -> #3 (&dqm->lock_hidden){+.+.}:
[  150.960822]        __mutex_lock+0xa1/0x9f0
[  150.964996]        evict_process_queues_cpsch+0x22/0x120 [amdgpu]
[  150.971155]        kfd_process_evict_queues+0x3b/0xc0 [amdgpu]
[  150.977054]        kgd2kfd_quiesce_mm+0x25/0x60 [amdgpu]
[  150.982442]        amdgpu_amdkfd_evict_userptr+0x35/0x70 [amdgpu]
[  150.988615]        amdgpu_mn_invalidate_hsa+0x41/0x60 [amdgpu]
[  150.994448]        __mmu_notifier_invalidate_range_start+0xa4/0x240
[  151.000714]        copy_page_range+0xd70/0xd80
[  151.005159]        dup_mm+0x3ca/0x550
[  151.008816]        copy_process+0x1bdc/0x1c70
[  151.013183]        _do_fork+0x76/0x6c0
[  151.016929]        __x64_sys_clone+0x8c/0xb0
[  151.021201]        do_syscall_64+0x4a/0x1d0
[  151.025404]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  151.030977]
               -> #2 (&adev->notifier_lock){+.+.}:
[  151.036993]        __mutex_lock+0xa1/0x9f0
[  151.041168]        amdgpu_mn_invalidate_hsa+0x30/0x60 [amdgpu]
[  151.047019]        __mmu_notifier_invalidate_range_start+0xa4/0x240
[  151.053277]        copy_page_range+0xd70/0xd80
[  151.057722]        dup_mm+0x3ca/0x550
[  151.061388]        copy_process+0x1bdc/0x1c70
[  151.065748]        _do_fork+0x76/0x6c0
[  151.069499]        __x64_sys_clone+0x8c/0xb0
[  151.073765]        do_syscall_64+0x4a/0x1d0
[  151.077952]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  151.083523]
               -> #1 (mmu_notifier_invalidate_range_start){+.+.}:
[  151.090833]        change_protection+0x802/0xab0
[  151.095448]        mprotect_fixup+0x187/0x2d0
[  151.099801]        setup_arg_pages+0x124/0x250
[  151.104251]        load_elf_binary+0x3a4/0x1464
[  151.108781]        search_binary_handler+0x6c/0x210
[  151.113656]        __do_execve_file.isra.40+0x7f7/0xa50
[  151.118875]        do_execve+0x21/0x30
[  151.122632]        call_usermodehelper_exec_async+0x17e/0x190
[  151.128393]        ret_from_fork+0x24/0x30
[  151.132489]
               -> #0 (&mm->mmap_sem#2){++++}:
[  151.138064]        __lock_acquire+0x11a1/0x1490
[  151.142597]        lock_acquire+0x90/0x180
[  151.146694]        __might_fault+0x68/0x90
[  151.150879]        read_sdma_queue_counter+0x5f/0xb0 [amdgpu]
[  151.156693]        update_sdma_queue_past_activity_stats+0x3b/0x90 [amdgpu]
[  151.163725]        destroy_queue_cpsch+0x1ae/0x210 [amdgpu]
[  151.169373]        pqm_destroy_queue+0xf0/0x250 [amdgpu]
[  151.174762]        kfd_ioctl_destroy_queue+0x32/0x70 [amdgpu]
[  151.180577]        kfd_ioctl+0x223/0x400 [amdgpu]
[  151.185284]        ksys_ioctl+0x8f/0xb0
[  151.189118]        __x64_sys_ioctl+0x16/0x20
[  151.193389]        do_syscall_64+0x4a/0x1d0
[  151.197569]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  151.203141]
               other info that might help us debug this:

[  151.211140] Chain exists of:
                 &mm->mmap_sem#2 --> &adev->notifier_lock --> &dqm->lock_hidden

[  151.222535]  Possible unsafe locking scenario:

[  151.228447]        CPU0                    CPU1
[  151.232971]        ----                    ----
[  151.237502]   lock(&dqm->lock_hidden);
[  151.241254]                                lock(&adev->notifier_lock);
[  151.247774]                                lock(&dqm->lock_hidden);
[  151.254038]   lock(&mm->mmap_sem#2);

This commit fixes the warning by ensuring get_user() is not called
while reading SDMA stats with dqm_lock held as get_user() could cause a
page fault which leads to the circular locking scenario.
Signed-off-by: NMukul Joshi <mukul.joshi@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Used sparse(make C=1) to find these loose ends.

v2:
removed unwanted extra line
Signed-off-by: NNirmoy Das <nirmoy.das@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

v4: drop get_tile_config, comment out other callbacks
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Track SDMA usage on a per process basis and report it through sysfs.
The value in the sysfs file indicates the amount of time SDMA has
been in-use by this process since the creation of the process.
This value is in microsecond granularity.
Signed-off-by: NMukul Joshi <mukul.joshi@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The queue mask used for set_resources always assumes the queue number
per pipe is 8, so KFD needs to align with that by using function
amdgpu_queue_mask_bit_to_set_resource_bit().
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The current GWS usage model will only allows a single GWS-enabled
process to be active on the GPU at once. This ensures that a
barrier-using kernel gets a known amount of GPU hardware, to
prevent deadlock due to inability to go beyond the GWS barrier.

The HWS watches how many GWS entries are assigned to each process,
and goes into over-subscription mode when two processes need more
than the 64 that are available. The current KFD method for working
with this is to allocate all 64 GWS entries to each GWS-capable
process.

When more than one GWS-enabled process is in the runlist, we must
make sure the runlist is in over-subscription mode, so that the
HWS gets a chained RUN_LIST packet and continues scheduling
kernels.
Signed-off-by: NJoseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

SDMA MQD memory type is NC that causes MQD data overwritten
accidentally by an old stable cache line. Changing it to UC
default for GART will fix the issue.

The mqd_gfx9 parameter is meant for control stacks that are
allocated together with user mode queue MQDs. Setting
mqd_gfx9 to true maps the control stack pages as NC.
Here it was accidentally applied to SDMA MQDs,
which are allocated together with the HIQ MQD. Setting
the mqd_gfx9 to false avoids that.
Signed-off-by: NEric Huang <jinhuieric.huang@amd.com>
Acked-by: NYong Zhao <Yong.Zhao@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The previous way of using SDMA queue count to infer whether we should unmap
SDMA engines has bugs. The reason it did not cause issues is because MEC
firmware unmaps all queues (CP + SDMA) when a unmap package for compute
engine is received. Becasue of that, only one unmap queue package
is needed, instead of one unmap queue package for CP and each SDMA engine,
which results in much simpler driver code.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Those printings are duplicated or useless.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The previous code of calculating active CP queues is problematic if
some SDMA queues are inactive. Fix that by counting CP queues directly.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The queues represented in queue_bitmap are only CP queues.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The name is easier to understand the code.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Acked-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The sdma_queue_count increment should be done before
execute_queues_cpsch(), which calls pm_calc_rlib_size() where
sdma_queue_count is used to calculate whether over_subscription is
triggered.

With the previous code, when a SDMA queue is created,
compute_queue_count in pm_calc_rlib_size() is one more than the
actual compute queue number, because the queue_count has been
incremented while sdma_queue_count has not. This patch fixes that.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

SW scheduler is previously called non HW scheduler, or non HWS. This
message is useful when triaging issues from dmesg.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Acked-by: NHuang Rui <ray.huang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Don't use the HWS if it's known to be hanging. In a reset also
don't try to destroy the HIQ because that may hang on SRIOV if the
KIQ is unresponsive.
Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Tested-by: NEmily Deng <Emily.Deng@amd.com>
Reviewed-by: Nshaoyunl  <shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Move HWS hang detection into unmap_queues_cpsch to catch hangs in all
cases. If this happens during a reset, don't schedule another reset
because the reset already in progress is expected to take care of it.
Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Tested-by: NEmily Deng <Emily.Deng@amd.com>
Reviewed-by: Nshaoyunl  <shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

dqm->pipeline_mem wasn't used anywhere.
Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Nshaoyunl  <shaoyun.liu@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

It is the same as KFD_MQD_TYPE_CP, so delete it. As a result, we will
have one less mqd mananger per device.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The doorbell offset could mean the byte offset or the dword offset,
and the 0 offset place is also different, sometimes the start of PCI
doorbell bar or the start of process doorbell pages. Use better name
to avoid confusion.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

If device reset/suspend/resume failed for some reason, dqm lock is
hold forever and this causes deadlock. Below is a kernel backtrace when
application open kfd after suspend/resume failed.

Instead of holding dqm lock in pre_reset and releasing dqm lock in
post_reset, add dqm->sched_running flag which is modified in
dqm->ops.start and dqm->ops.stop. The flag doesn't need lock protection
because write/read are all inside dqm lock.

For HWS case, map_queues_cpsch and unmap_queues_cpsch checks
sched_running flag before sending the updated runlist.

v2: For no-HWS case, when device is stopped, don't call
load/destroy_mqd for eviction, restore and create queue, and avoid
debugfs dump hdqs.

Backtrace of dqm lock deadlock:

[Thu Oct 17 16:43:37 2019] INFO: task rocminfo:3024 blocked for more
than 120 seconds.
[Thu Oct 17 16:43:37 2019]       Not tainted
5.0.0-rc1-kfd-compute-rocm-dkms-no-npi-1131 #1
[Thu Oct 17 16:43:37 2019] "echo 0 >
/proc/sys/kernel/hung_task_timeout_secs" disables this message.
[Thu Oct 17 16:43:37 2019] rocminfo        D    0  3024   2947
0x80000000
[Thu Oct 17 16:43:37 2019] Call Trace:
[Thu Oct 17 16:43:37 2019]  ? __schedule+0x3d9/0x8a0
[Thu Oct 17 16:43:37 2019]  schedule+0x32/0x70
[Thu Oct 17 16:43:37 2019]  schedule_preempt_disabled+0xa/0x10
[Thu Oct 17 16:43:37 2019]  __mutex_lock.isra.9+0x1e3/0x4e0
[Thu Oct 17 16:43:37 2019]  ? __call_srcu+0x264/0x3b0
[Thu Oct 17 16:43:37 2019]  ? process_termination_cpsch+0x24/0x2f0
[amdgpu]
[Thu Oct 17 16:43:37 2019]  process_termination_cpsch+0x24/0x2f0
[amdgpu]
[Thu Oct 17 16:43:37 2019]
kfd_process_dequeue_from_all_devices+0x42/0x60 [amdgpu]
[Thu Oct 17 16:43:37 2019]  kfd_process_notifier_release+0x1be/0x220
[amdgpu]
[Thu Oct 17 16:43:37 2019]  __mmu_notifier_release+0x3e/0xc0
[Thu Oct 17 16:43:37 2019]  exit_mmap+0x160/0x1a0
[Thu Oct 17 16:43:37 2019]  ? __handle_mm_fault+0xba3/0x1200
[Thu Oct 17 16:43:37 2019]  ? exit_robust_list+0x5a/0x110
[Thu Oct 17 16:43:37 2019]  mmput+0x4a/0x120
[Thu Oct 17 16:43:37 2019]  do_exit+0x284/0xb20
[Thu Oct 17 16:43:37 2019]  ? handle_mm_fault+0xfa/0x200
[Thu Oct 17 16:43:37 2019]  do_group_exit+0x3a/0xa0
[Thu Oct 17 16:43:37 2019]  __x64_sys_exit_group+0x14/0x20
[Thu Oct 17 16:43:37 2019]  do_syscall_64+0x4f/0x100
[Thu Oct 17 16:43:37 2019]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
Suggested-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NPhilip Yang <Philip.Yang@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Previously only PCIe-optimized SDMA engine hqds were
exposed in debug fs. Print all SDMA engine hqds.
Reported-by: NJonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: NJonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: NOak Zeng <Oak.Zeng@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

On device initialization, a chunk of GTT memory is pre-allocated for
HIQ and all SDMA queues mqd. The size of this allocation was wrong.
The correct sdma engine number should be PCIe-optimized SDMA engine
number plus xgmi SDMA engine number.
Reported-by: NJonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: NJonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: NOak Zeng <Oak.Zeng@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This makes possible the vmid pasid mapping query through software.
Signed-off-by: NYong Zhao <Yong.Zhao@amd.com>
Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>