│ void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
│ {
│ → callq __fentry__
│ push %rbp
0.46 │ mov %rsp,%rbp
│ smp_mb(); /* C */ /* Avoid leaking the critical section. */
99.10 │ lock addl $0x0,-0x4(%rsp)
│ this_cpu_inc(ssp->sda->srcu_unlock_count[idx]);
0.01 │ movslq %esi,%rsi
│ mov 0xc500(%rdi),%rax
0.22 │ incq %gs:0x10(%rax,%rsi,8)
│ }
│ pop %rbp
0.21 │ ← retq
as for soft lockup, kfd ioctl would try lock process_info which is hold by kernel restrore thread and it runs for a long time. maybe some debug logs below helps.
[ 637.463063] XH: lock &process_info->lock for 24s
[ 637.463070] CPU: 42 PID: 450 Comm: kworker/42:1 Not tainted 5.13.0+ #5
[ 637.463072] Hardware name: Supermicro SYS-4028GR-TRT2/X10DRG-OT+-CPU, BIOS 2.0c 07/21/2017
[ 637.463074] Workqueue: events amdgpu_amdkfd_restore_userptr_worker [amdgpu]
[ 637.463416] Call Trace:
[ 637.463418] dump_stack+0x7d/0x9c
[ 637.463422] mutex_unlock_xh+0x7e/0xb0 [amdgpu]
[ 637.463652] amdgpu_amdkfd_restore_userptr_worker+0x470/0x790 [amdgpu]
[ 637.463878] process_one_work+0x236/0x420
[ 637.463882] worker_thread+0x34/0x400
[ 637.463884] ? process_one_work+0x420/0x420
[ 637.463887] kthread+0x126/0x140
[ 637.463890] ? kthread_park+0x90/0x90
[ 637.463892] ret_from_fork+0x22/0x30
[ 637.463908] mutex_lock_xh+0x32/0x60 [amdgpu]
[ 637.464134] amdgpu_amdkfd_restore_userptr_worker+0xd1/0x790 [amdgpu]
[ 637.464360] process_one_work+0x236/0x420
[ 637.464362] worker_thread+0x34/0x400
[ 637.464364] kthread+0x126/0x140
[ 637.464366] ret_from_fork+0x22/0x30
[ 637.468717] XH: lock &p->mutex for 24s
[ 637.468722] CPU: 14 PID: 2104 Comm: kfdtest Not tainted 5.13.0+ #5
[ 637.468726] Hardware name: Supermicro SYS-4028GR-TRT2/X10DRG-OT+-CPU, BIOS 2.0c 07/21/2017
[ 637.468728] Call Trace:
[ 637.468730] dump_stack+0x7d/0x9c
[ 637.468735] mutex_unlock_xh+0x7e/0xb0 [amdgpu]
[ 637.469251] kfd_ioctl_map_memory_to_gpu+0x38a/0x5a0 [amdgpu]
[ 637.469780] kfd_ioctl+0x51f/0x6f0 [amdgpu]
[ 637.470308] ? kfd_ioctl_unmap_memory_from_gpu+0x520/0x520 [amdgpu]
[ 637.470836] ? __vm_munmap+0xa0/0x130
[ 637.470842] __x64_sys_ioctl+0x96/0xd0
[ 637.470849] ? exit_to_user_mode_prepare+0x32/0x1d0
[ 637.470858] do_syscall_64+0x3c/0xb0
[ 637.470864] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 637.470869] RIP: 0033:0x7f3e6bac3317
[ 637.470875] Code: b3 66 90 48 8b 05 71 4b 2d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 41 4b 2d 00 f7 d8 64 89 01 48
[ 637.470879] RSP: 002b:00007ffcfea0f668 EFLAGS: 00000202 ORIG_RAX: 0000000000000010
[ 637.470884] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007f3e6bac3317
[ 637.470887] RDX: 00007ffcfea0f6f0 RSI: 00000000c0184b18 RDI: 0000000000000003
[ 637.470889] RBP: 00007ffcfea0f6a0 R08: 0000000000000000 R09: 0000000000000000
[ 637.470892] R10: 000055afe3e7a010 R11: 0000000000000202 R12: 000055afe2e4f3ba
[ 637.470894] R13: 0000000000000000 R14: 0000000000000021 R15: 0000000000000000
[ 637.470919] mutex_lock_xh+0x32/0x60 [amdgpu]
[ 637.471455] kfd_ioctl_map_memory_to_gpu+0x1eb/0x5a0 [amdgpu]
[ 637.472006] kfd_ioctl+0x51f/0x6f0 [amdgpu]
[ 637.472544] __x64_sys_ioctl+0x96/0xd0
[ 637.472550] do_syscall_64+0x3c/0xb0
[ 637.472554] entry_SYSCALL_64_after_hwframe+0x44/0xae
vm_cpu_update is called by amdgpu_vm_bo_update_mapping which already calls drm_dev_enter/exit.
yes, gmc_init_pdb0 could be called during s3, I will add the enter/exit there too.
I will do the plug/unplug test to verfiy it.
_______________________________________
发件人: Grodzovsky, Andrey <Andrey.Grodzovsky@xxxxxxx>
发送时间: 2021年9月15日 11:02
收件人: Pan, Xinhui; amd-gfx@xxxxxxxxxxxxxxxxxxxxx
抄送: Deucher, Alexander; Koenig, Christian
主题: Re: [PATCH] drm/amdgpu: Put drm_dev_enter/exit outside hot codepath
On 2021-09-14 9:42 p.m., xinhui pan wrote:
We hit soft hang while doing memory pressure test on one numa system.
After a qucik look, this is because kfd invalid/valid userptr memory
frequently with process_info lock hold.
perf top says below,
75.81% [kernel] [k] __srcu_read_unlock
Do you have any idea why most of CPU cycles would be spent in SRCU
unlock ? It's
not waiting on anything within this function and does some simple
arithmetic inside
as far as I see.
6.19% [amdgpu] [k] amdgpu_gmc_set_pte_pde
3.56% [kernel] [k] __srcu_read_lock
2.20% [amdgpu] [k] amdgpu_vm_cpu_update
2.20% [kernel] [k] __sg_page_iter_dma_next
2.15% [drm] [k] drm_dev_enter
1.70% [drm] [k] drm_prime_sg_to_dma_addr_array
1.18% [kernel] [k] __sg_alloc_table_from_pages
1.09% [drm] [k] drm_dev_exit
So move drm_dev_enter/exit outside gmc code, instead let caller do it.
Not clear from explanation here how the soft hang with process_info lock
being hold
is related to to SRCU lock of drm_dev_enter/exit.
They are gart_unbind, gart_map, vm_cpu_update(already hold in its
caller)
Where in the caller ?
and gmc_init_pdb0(no need)
Why no need ? Those guards protect from accessing MMIO ranges after
device is hot removed and hence they don't belong to him anymore. The
function above is also called during device resume from S3 and it's possible
to hot unplug device during S3 so this might be called with extracted device
Is it possible to run libdrm amdgpu test hot plug test suite on this
change (before and after)
to verify if this actually breaks hot unplug ? The suite is committed
into latest libdrm but disabled
until latest fixes from amd-staging-drm-next reach upstream drm-next. So
to enable it this
code
https://gitlab.freedesktop.org/mesa/drm/-/blob/main/tests/amdgpu/hotunplug_tests.c#L65
needs to be commented out.
Andrey
Signed-off-by: xinhui pan <xinhui.pan@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 11 +++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 7 -------
2 files changed, 11 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 76efd5f8950f..d7e4f4660acf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -34,6 +34,7 @@
#include <asm/set_memory.h>
#endif
#include "amdgpu.h"
+#include <drm/drm_drv.h>
/*
* GART
@@ -230,12 +231,16 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
u64 page_base;
/* Starting from VEGA10, system bit must be 0 to mean invalid. */
uint64_t flags = 0;
+ int idx;
if (!adev->gart.ready) {
WARN(1, "trying to unbind memory from uninitialized GART !\n");
return -EINVAL;
}
+ if (!drm_dev_enter(&adev->ddev, &idx))
+ return 0;
+
t = offset / AMDGPU_GPU_PAGE_SIZE;
p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
for (i = 0; i < pages; i++, p++) {
@@ -254,6 +259,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
for (i = 0; i < adev->num_vmhubs; i++)
amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
+ drm_dev_exit(idx);
return 0;
}
@@ -276,12 +282,16 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
{
uint64_t page_base;
unsigned i, j, t;
+ int idx;
if (!adev->gart.ready) {
WARN(1, "trying to bind memory to uninitialized GART !\n");
return -EINVAL;
}
+ if (!drm_dev_enter(&adev->ddev, &idx))
+ return 0;
+
t = offset / AMDGPU_GPU_PAGE_SIZE;
for (i = 0; i < pages; i++) {
@@ -291,6 +301,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
page_base += AMDGPU_GPU_PAGE_SIZE;
}
}
+ drm_dev_exit(idx);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 54f059501a33..e973488250e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -31,7 +31,6 @@
#include "amdgpu_ras.h"
#include "amdgpu_xgmi.h"
-#include <drm/drm_drv.h>
/**
* amdgpu_gmc_pdb0_alloc - allocate vram for pdb0
@@ -153,10 +152,6 @@ int amdgpu_gmc_set_pte_pde(struct amdgpu_device *adev, void *cpu_pt_addr,
{
void __iomem *ptr = (void *)cpu_pt_addr;
uint64_t value;
- int idx;
-
- if (!drm_dev_enter(&adev->ddev, &idx))
- return 0;
/*
* The following is for PTE only. GART does not have PDEs.
@@ -165,8 +160,6 @@ int amdgpu_gmc_set_pte_pde(struct amdgpu_device *adev, void *cpu_pt_addr,
value |= flags;
writeq(value, ptr + (gpu_page_idx * 8));
- drm_dev_exit(idx);
-
return 0;
}
