UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/amdkfd: Fix circular locking dependency warning 

[  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: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Mukul Joshi 2020-06-24 13:47:12 -04:00 committed by Alex Deucher
parent 7ee78aff9d
commit d69fd951e6
3 changed files with 159 additions and 62 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

73
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
View File

@ -153,24 +153,23 @@ static void decrement_queue_count(struct device_queue_manager *dqm,
dqm->active_cp_queue_count--;
}
int read_sdma_queue_counter(struct queue *q, uint64_t *val)
int read_sdma_queue_counter(uint64_t q_rptr, uint64_t *val)
{
int ret;
uint64_t tmp = 0;
if (!q || !val)
if (!val)
return -EINVAL;
/*
* SDMA activity counter is stored at queue's RPTR + 0x8 location.
*/
if (!access_ok((const void __user *)((uint64_t)q->properties.read_ptr +
if (!access_ok((const void __user *)(q_rptr +
sizeof(uint64_t)), sizeof(uint64_t))) {
pr_err("Can't access sdma queue activity counter\n");
return -EFAULT;
}
ret = get_user(tmp, (uint64_t *)((uint64_t)(q->properties.read_ptr) +
sizeof(uint64_t)));
ret = get_user(tmp, (uint64_t *)(q_rptr + sizeof(uint64_t)));
if (!ret) {
*val = tmp;
}
@ -178,27 +177,6 @@ int read_sdma_queue_counter(struct queue *q, uint64_t *val)
return ret;
}
static int update_sdma_queue_past_activity_stats(struct kfd_process_device *pdd,
struct queue *q)
{
int ret;
uint64_t val = 0;
if (!pdd)
return -ENODEV;
ret = read_sdma_queue_counter(q, &val);
if (ret) {
pr_err("Failed to read SDMA queue counter for queue: %d\n",
q->properties.queue_id);
return ret;
}
pdd->sdma_past_activity_counter += val;
return ret;
}
static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
{
struct kfd_dev *dev = qpd->dqm->dev;
@ -533,11 +511,6 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
if (retval == -ETIME)
qpd->reset_wavefronts = true;
/* Get the SDMA queue stats */
if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
(q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
update_sdma_queue_past_activity_stats(qpd_to_pdd(qpd), q);
}
mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
@ -573,9 +546,23 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
struct queue *q)
{
int retval;
uint64_t sdma_val = 0;
struct kfd_process_device *pdd = qpd_to_pdd(qpd);
/* Get the SDMA queue stats */
if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
(q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
retval = read_sdma_queue_counter((uint64_t)q->properties.read_ptr,
&sdma_val);
if (retval)
pr_err("Failed to read SDMA queue counter for queue: %d\n",
q->properties.queue_id);
}
dqm_lock(dqm);
retval = destroy_queue_nocpsch_locked(dqm, qpd, q);
if (!retval)
pdd->sdma_past_activity_counter += sdma_val;
dqm_unlock(dqm);
return retval;
@ -1480,6 +1467,18 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
{
int retval;
struct mqd_manager *mqd_mgr;
uint64_t sdma_val = 0;
struct kfd_process_device *pdd = qpd_to_pdd(qpd);
/* Get the SDMA queue stats */
if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
(q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
retval = read_sdma_queue_counter((uint64_t)q->properties.read_ptr,
&sdma_val);
if (retval)
pr_err("Failed to read SDMA queue counter for queue: %d\n",
q->properties.queue_id);
}
retval = 0;
@ -1501,10 +1500,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
deallocate_doorbell(qpd, q);
if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
deallocate_sdma_queue(dqm, q);
else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)
if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
(q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
deallocate_sdma_queue(dqm, q);
pdd->sdma_past_activity_counter += sdma_val;
}
list_del(&q->list);
qpd->queue_count--;
@ -1520,11 +1520,6 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
}
}
/* Get the SDMA queue stats */
if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
(q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
update_sdma_queue_past_activity_stats(qpd_to_pdd(qpd), q);
}
/*
* Unconditionally decrement this counter, regardless of the queue's
* type

3
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
View File

@ -251,6 +251,5 @@ static inline void dqm_unlock(struct device_queue_manager *dqm)
mutex_unlock(&dqm->lock_hidden);
}
int read_sdma_queue_counter(struct queue *q, uint64_t *val);
int read_sdma_queue_counter(uint64_t q_rptr, uint64_t *val);
#endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */

145
drivers/gpu/drm/amd/amdkfd/kfd_process.c
View File

@ -86,6 +86,13 @@ struct kfd_sdma_activity_handler_workarea {
uint64_t sdma_activity_counter;
};
struct temp_sdma_queue_list {
uint64_t rptr;
uint64_t sdma_val;
unsigned int queue_id;
struct list_head list;
};
static void kfd_sdma_activity_worker(struct work_struct *work)
{
struct kfd_sdma_activity_handler_workarea *workarea;
@ -96,6 +103,8 @@ static void kfd_sdma_activity_worker(struct work_struct *work)
struct qcm_process_device *qpd;
struct device_queue_manager *dqm;
int ret = 0;
struct temp_sdma_queue_list sdma_q_list;
struct temp_sdma_queue_list *sdma_q, *next;
workarea = container_of(work, struct kfd_sdma_activity_handler_workarea,
sdma_activity_work);
@ -109,41 +118,135 @@ static void kfd_sdma_activity_worker(struct work_struct *work)
qpd = &pdd->qpd;
if (!dqm || !qpd)
return;
/*
* Total SDMA activity is current SDMA activity + past SDMA activity
* Past SDMA count is stored in pdd.
* To get the current activity counters for all active SDMA queues,
* we loop over all SDMA queues and get their counts from user-space.
*
* We cannot call get_user() with dqm_lock held as it can cause
* a circular lock dependency situation. To read the SDMA stats,
* we need to do the following:
*
* 1. Create a temporary list of SDMA queue nodes from the qpd->queues_list,
* with dqm_lock/dqm_unlock().
* 2. Call get_user() for each node in temporary list without dqm_lock.
* Save the SDMA count for each node and also add the count to the total
* SDMA count counter.
* Its possible, during this step, a few SDMA queue nodes got deleted
* from the qpd->queues_list.
* 3. Do a second pass over qpd->queues_list to check if any nodes got deleted.
* If any node got deleted, its SDMA count would be captured in the sdma
* past activity counter. So subtract the SDMA counter stored in step 2
* for this node from the total SDMA count.
*/
INIT_LIST_HEAD(&sdma_q_list.list);
mm = get_task_mm(pdd->process->lead_thread);
if (!mm) {
/*
* Create the temp list of all SDMA queues
*/
dqm_lock(dqm);
list_for_each_entry(q, &qpd->queues_list, list) {
if ((q->properties.type != KFD_QUEUE_TYPE_SDMA) &&
(q->properties.type != KFD_QUEUE_TYPE_SDMA_XGMI))
continue;
sdma_q = kzalloc(sizeof(struct temp_sdma_queue_list), GFP_KERNEL);
if (!sdma_q) {
dqm_unlock(dqm);
goto cleanup;
}
INIT_LIST_HEAD(&sdma_q->list);
sdma_q->rptr = (uint64_t)q->properties.read_ptr;
sdma_q->queue_id = q->properties.queue_id;
list_add_tail(&sdma_q->list, &sdma_q_list.list);
}
/*
* If the temp list is empty, then no SDMA queues nodes were found in
* qpd->queues_list. Return the past activity count as the total sdma
* count
*/
if (list_empty(&sdma_q_list.list)) {
workarea->sdma_activity_counter = pdd->sdma_past_activity_counter;
dqm_unlock(dqm);
return;
}
dqm_unlock(dqm);
/*
* Get the usage count for each SDMA queue in temp_list.
*/
mm = get_task_mm(pdd->process->lead_thread);
if (!mm)
goto cleanup;
use_mm(mm);
list_for_each_entry(sdma_q, &sdma_q_list.list, list) {
val = 0;
ret = read_sdma_queue_counter(sdma_q->rptr, &val);
if (ret) {
pr_debug("Failed to read SDMA queue active counter for queue id: %d",
sdma_q->queue_id);
} else {
sdma_q->sdma_val = val;
workarea->sdma_activity_counter += val;
}
}
unuse_mm(mm);
mmput(mm);
/*
* Do a second iteration over qpd_queues_list to check if any SDMA
* nodes got deleted while fetching SDMA counter.
*/
dqm_lock(dqm);
/*
* Total SDMA activity is current SDMA activity + past SDMA activity
*/
workarea->sdma_activity_counter = pdd->sdma_past_activity_counter;
workarea->sdma_activity_counter += pdd->sdma_past_activity_counter;
/*
* Get the current activity counters for all active SDMA queues
*/
list_for_each_entry(q, &qpd->queues_list, list) {
if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) ||
(q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
val = 0;
ret = read_sdma_queue_counter(q, &val);
if (ret)
pr_debug("Failed to read SDMA queue active "
"counter for queue id: %d",
q->properties.queue_id);
else
workarea->sdma_activity_counter += val;
if (list_empty(&sdma_q_list.list))
break;
if ((q->properties.type != KFD_QUEUE_TYPE_SDMA) &&
(q->properties.type != KFD_QUEUE_TYPE_SDMA_XGMI))
continue;
list_for_each_entry_safe(sdma_q, next, &sdma_q_list.list, list) {
if (((uint64_t)q->properties.read_ptr == sdma_q->rptr) &&
(sdma_q->queue_id == q->properties.queue_id)) {
list_del(&sdma_q->list);
kfree(sdma_q);
break;
}
}
}
dqm_unlock(dqm);
unuse_mm(mm);
mmput(mm);
/*
* If temp list is not empty, it implies some queues got deleted
* from qpd->queues_list during SDMA usage read. Subtract the SDMA
* count for each node from the total SDMA count.
*/
list_for_each_entry_safe(sdma_q, next, &sdma_q_list.list, list) {
workarea->sdma_activity_counter -= sdma_q->sdma_val;
list_del(&sdma_q->list);
kfree(sdma_q);
}
return;
cleanup:
list_for_each_entry_safe(sdma_q, next, &sdma_q_list.list, list) {
list_del(&sdma_q->list);
kfree(sdma_q);
}
}
static ssize_t kfd_procfs_show(struct kobject *kobj, struct attribute *attr,