Skip to contentSkip to conversation

drm/amdgpu: fix stall on CPU when allocate large system memory

PATCH Superseded James Zhu 4 participants 9 messages Nov 17, 2022 – Nov 22, 2022

Subsystems (2)
lore
Share & tools
lore

James Zhu

author
#0 lore raw

PATCH 1/1 drm/amdgpu: fix stall on CPU when allocate large system memory

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: 	create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu: 	8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137] 	(t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O      5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00
[  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603]  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 47 +++++++++++++++++--------
 1 file changed, 32 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +32 -15
index a48ea62b12b0..0425fc6a49aa 100644
@@ -163,6 +163,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       struct hmm_range **phmm_range)
 {
 	struct hmm_range *hmm_range;
+	unsigned long hmm_range_end;
 	unsigned long timeout;
 	unsigned long i;
 	unsigned long *pfns;
@@ -184,25 +185,41 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 		hmm_range->default_flags |= HMM_PFN_REQ_WRITE;
 	hmm_range->hmm_pfns = pfns;
 	hmm_range->start = start;
-	hmm_range->end = start + npages * PAGE_SIZE;
+	hmm_range_end = start + npages * PAGE_SIZE;
 	hmm_range->dev_private_owner = owner;
 
-	/* Assuming 512MB takes maxmium 1 second to fault page address */
-	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
-	timeout = jiffies + msecs_to_jiffies(timeout);
+#define MAX_WALK_BYTE	(64ULL<<30)
+	do {
+		hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, hmm_range_end);
+
+		pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+			hmm_range->start, hmm_range->end);
+
+		/* Assuming 512MB takes maxmium 1 second to fault page address */
+		timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+			HMM_RANGE_DEFAULT_TIMEOUT;
+		timeout = jiffies + msecs_to_jiffies(timeout);
 
 retry:
-	hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
-	r = hmm_range_fault(hmm_range);
-	if (unlikely(r)) {
-		/*
-		 * FIXME: This timeout should encompass the retry from
-		 * mmu_interval_read_retry() as well.
-		 */
-		if (r == -EBUSY && !time_after(jiffies, timeout))
-			goto retry;
-		goto out_free_pfns;
-	}
+		hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
+		r = hmm_range_fault(hmm_range);
+		if (unlikely(r)) {
+			/*
+			 * FIXME: This timeout should encompass the retry from
+			 * mmu_interval_read_retry() as well.
+			 */
+			if (r == -EBUSY && !time_after(jiffies, timeout))
+				goto retry;
+			goto out_free_pfns;
+		}
+
+		hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
+		hmm_range->start = hmm_range->end;
+		schedule();
+	} while (hmm_range->end < hmm_range_end);
+
+	hmm_range->start = start;
+	hmm_range->hmm_pfns = pfns;
 
 	/*
 	 * Due to default_flags, all pages are HMM_PFN_VALID or
Signature · 1 line
2.34.1
#1 lore raw

Am 2022-11-17 um 16:38 schrieb James Zhu:

Quoted 74 lines

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: 	create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu: 	8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137] 	(t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O      5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00
[  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603]  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]
---
  drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 47 +++++++++++++++++--------
  1 file changed, 32 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +1 -0
index a48ea62b12b0..0425fc6a49aa 100644
@@ -163,6 +163,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
  			       struct hmm_range **phmm_range)
  {
  	struct hmm_range *hmm_range;
+	unsigned long hmm_range_end;
  	unsigned long timeout;
  	unsigned long i;
  	unsigned long *pfns;

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, · line 188

Quoted 5 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +1 -1
@@ -184,25 +185,41 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
  		hmm_range->default_flags |= HMM_PFN_REQ_WRITE;
  	hmm_range->hmm_pfns = pfns;
  	hmm_range->start = start;
-	hmm_range->end = start + npages * PAGE_SIZE;
+	hmm_range_end = start + npages * PAGE_SIZE;

This variable name is too easy to confuse with hmm_range->end. I would suggest calling it "end", analogous to "start".

Quoted 34 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +16 -14
  	hmm_range->dev_private_owner = owner;
 
-	/* Assuming 512MB takes maxmium 1 second to fault page address */
-	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
-	timeout = jiffies + msecs_to_jiffies(timeout);
+#define MAX_WALK_BYTE	(64ULL<<30)
+	do {
+		hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, hmm_range_end);
+
+		pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+			hmm_range->start, hmm_range->end);
+
+		/* Assuming 512MB takes maxmium 1 second to fault page address */
+		timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+			HMM_RANGE_DEFAULT_TIMEOUT;
+		timeout = jiffies + msecs_to_jiffies(timeout);
 
  retry:
-	hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
-	r = hmm_range_fault(hmm_range);
-	if (unlikely(r)) {
-		/*
-		 * FIXME: This timeout should encompass the retry from
-		 * mmu_interval_read_retry() as well.
-		 */
-		if (r == -EBUSY && !time_after(jiffies, timeout))
-			goto retry;
-		goto out_free_pfns;
-	}
+		hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
+		r = hmm_range_fault(hmm_range);
+		if (unlikely(r)) {
+			/*
+			 * FIXME: This timeout should encompass the retry from

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, · line 218

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +10 -0
+			 * mmu_interval_read_retry() as well.
+			 */
+			if (r == -EBUSY && !time_after(jiffies, timeout))
+				goto retry;
+			goto out_free_pfns;
+		}
+
+		hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
+		hmm_range->start = hmm_range->end;
+		schedule();

We don't need to schedule for ranges < MAX_WALK_BYTES. I guess these three lines could be conditional:

+ if (hmm_range->end == end)
+ break;

		hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
		hmm_range->start = hmm_range->end;
		schedule();

Regards,
  Felix

Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +4 -0
+	} while (hmm_range->end < hmm_range_end);
+
+	hmm_range->start = start;
+	hmm_range->hmm_pfns = pfns;
 
  	/*
  	 * Due to default_flags, all pages are HMM_PFN_VALID or
#2 lore raw
Quoted 76 lines · Felix Kuehling

Am 2022-11-17 um 16:38 schrieb James Zhu:

Quoted 75 lines

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu:     8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137]     (t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O 5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00 [  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603] amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]

---
  drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 47 +++++++++++++++++--------

  1 file changed, 32 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +1 -0
index a48ea62b12b0..0425fc6a49aa 100644
@@ -163,6 +163,7 @@ int amdgpu_hmm_range_get_pages(struct 
 mmu_interval_notifier *notifier,
                      struct hmm_range **phmm_range)
   {
       struct hmm_range *hmm_range;
+    unsigned long hmm_range_end;
       unsigned long timeout;
       unsigned long i;

      unsigned long *pfns;

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +0 -0
@@ -184,25 +185,41 @@ int amdgpu_hmm_range_get_pages(struct 
Quoted 8 lines

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, · line 188

Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +1 -1
 mmu_interval_notifier *notifier,
           hmm_range->default_flags |= HMM_PFN_REQ_WRITE;
       hmm_range->hmm_pfns = pfns;
       hmm_range->start = start;
-    hmm_range->end = start + npages * PAGE_SIZE;
+    hmm_range_end = start + npages * PAGE_SIZE;

This variable name is too easy to confuse with hmm_range->end. I would suggest calling it "end", analogous to "start".

[JZ] Sure

Quoted 50 lines
Quoted 39 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +0 -0
       hmm_range->dev_private_owner = owner;

  -    /* Assuming 512MB takes maxmium 1 second to fault page address */ -    timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT; -    timeout = jiffies + msecs_to_jiffies(timeout);
+#define MAX_WALK_BYTE    (64ULL<<30)
+    do {
+        hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, hmm_range_end);

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +5 -0
+
+        pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+            hmm_range->start, hmm_range->end);
+
+        /* Assuming 512MB takes maxmium 1 second to fault page 

address */
+        timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+            HMM_RANGE_DEFAULT_TIMEOUT;
+        timeout = jiffies + msecs_to_jiffies(timeout); retry:
-    hmm_range->notifier_seq = mmu_interval_read_begin(notifier); -    r = hmm_range_fault(hmm_range);
-    if (unlikely(r)) {
-        /*
-         * FIXME: This timeout should encompass the retry from -         * mmu_interval_read_retry() as well.
-         */
-        if (r == -EBUSY && !time_after(jiffies, timeout)) -            goto retry;
-        goto out_free_pfns;
-    }
+        hmm_range->notifier_seq = mmu_interval_read_begin(notifier); +        r = hmm_range_fault(hmm_range);
+        if (unlikely(r)) {
+            /*
+             * FIXME: This timeout should encompass the retry from +             * mmu_interval_read_retry() as well.
+             */

Quoted 8 lines

+            if (r == -EBUSY && !time_after(jiffies, timeout)) +                goto retry;
+            goto out_free_pfns;
+        }
+
+        hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT; +        hmm_range->start = hmm_range->end;
+        schedule();

We don't need to schedule for ranges < MAX_WALK_BYTES. I guess these three lines could be conditional:

Quoted 6 lines

+        if (hmm_range->end == end)
+            break;

        hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT; hmm_range->start = hmm_range->end; schedule();

[JZ] Yes, it will be more accurate. I will update it. Thanks!

Quoted 11 lines

Regards,
  Felix

Quoted 6 lines

+    } while (hmm_range->end < hmm_range_end);
+
+    hmm_range->start = start;
+    hmm_range->hmm_pfns = pfns;
        /*
       * Due to default_flags, all pages are HMM_PFN_VALID or

author
#3 lore raw

PATCH v2 1/1 drm/amdgpu: fix stall on CPU when allocate large system memory

In reply to James Zhu

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: 	create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu: 	8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137] 	(t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O      5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00
[  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603]  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 49 +++++++++++++++++--------
 1 file changed, 34 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +34 -15
index a48ea62b12b0..fb51144ab77e 100644
@@ -163,6 +163,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       struct hmm_range **phmm_range)
 {
 	struct hmm_range *hmm_range;
+	unsigned long end;
 	unsigned long timeout;
 	unsigned long i;
 	unsigned long *pfns;
@@ -184,25 +185,43 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 		hmm_range->default_flags |= HMM_PFN_REQ_WRITE;
 	hmm_range->hmm_pfns = pfns;
 	hmm_range->start = start;
-	hmm_range->end = start + npages * PAGE_SIZE;
+	end = start + npages * PAGE_SIZE;
 	hmm_range->dev_private_owner = owner;
 
-	/* Assuming 512MB takes maxmium 1 second to fault page address */
-	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
-	timeout = jiffies + msecs_to_jiffies(timeout);
+#define MAX_WALK_BYTE	(64ULL<<30)
+	do {
+		hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, end);
+
+		pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+			hmm_range->start, hmm_range->end);
+
+		/* Assuming 512MB takes maxmium 1 second to fault page address */
+		timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+			HMM_RANGE_DEFAULT_TIMEOUT;
+		timeout = jiffies + msecs_to_jiffies(timeout);
 
 retry:
-	hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
-	r = hmm_range_fault(hmm_range);
-	if (unlikely(r)) {
-		/*
-		 * FIXME: This timeout should encompass the retry from
-		 * mmu_interval_read_retry() as well.
-		 */
-		if (r == -EBUSY && !time_after(jiffies, timeout))
-			goto retry;
-		goto out_free_pfns;
-	}
+		hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
+		r = hmm_range_fault(hmm_range);
+		if (unlikely(r)) {
+			/*
+			 * FIXME: This timeout should encompass the retry from
+			 * mmu_interval_read_retry() as well.
+			 */
+			if (r == -EBUSY && !time_after(jiffies, timeout))
+				goto retry;
+			goto out_free_pfns;
+		}
+
+		if (hmm_range->end == end)
+			break;
+		hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
+		hmm_range->start = hmm_range->end;
+		schedule();
+	} while (hmm_range->end < end);
+
+	hmm_range->start = start;
+	hmm_range->hmm_pfns = pfns;
 
 	/*
 	 * Due to default_flags, all pages are HMM_PFN_VALID or
Signature · 1 line
2.34.1
maintainer
#4 lore raw

Am 21.11.22 um 14:13 schrieb James Zhu:

Quoted 75 lines

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: 	create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu: 	8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137] 	(t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O      5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00
[  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603]  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]
---
  drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 49 +++++++++++++++++--------
  1 file changed, 34 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +1 -0
index a48ea62b12b0..fb51144ab77e 100644
@@ -163,6 +163,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
  			       struct hmm_range **phmm_range)
  {
  	struct hmm_range *hmm_range;
+	unsigned long end;
  	unsigned long timeout;
  	unsigned long i;
  	unsigned long *pfns;
@@ -184,25 +185,43 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
  		hmm_range->default_flags |= HMM_PFN_REQ_WRITE;

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, · line 191

Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +2 -4
  	hmm_range->hmm_pfns = pfns;
  	hmm_range->start = start;
-	hmm_range->end = start + npages * PAGE_SIZE;
+	end = start + npages * PAGE_SIZE;
  	hmm_range->dev_private_owner = owner;
 
-	/* Assuming 512MB takes maxmium 1 second to fault page address */
-	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
-	timeout = jiffies + msecs_to_jiffies(timeout);
+#define MAX_WALK_BYTE	(64ULL<<30)

Please don't add any defines in the middle of the code.

Quoted 47 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +31 -11
+	do {
+		hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, end);
+
+		pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+			hmm_range->start, hmm_range->end);
+
+		/* Assuming 512MB takes maxmium 1 second to fault page address */
+		timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+			HMM_RANGE_DEFAULT_TIMEOUT;
+		timeout = jiffies + msecs_to_jiffies(timeout);
 
  retry:
-	hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
-	r = hmm_range_fault(hmm_range);
-	if (unlikely(r)) {
-		/*
-		 * FIXME: This timeout should encompass the retry from
-		 * mmu_interval_read_retry() as well.
-		 */
-		if (r == -EBUSY && !time_after(jiffies, timeout))
-			goto retry;
-		goto out_free_pfns;
-	}
+		hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
+		r = hmm_range_fault(hmm_range);
+		if (unlikely(r)) {
+			/*
+			 * FIXME: This timeout should encompass the retry from
+			 * mmu_interval_read_retry() as well.
+			 */
+			if (r == -EBUSY && !time_after(jiffies, timeout))
+				goto retry;
+			goto out_free_pfns;
+		}
+
+		if (hmm_range->end == end)
+			break;
+		hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
+		hmm_range->start = hmm_range->end;
+		schedule();
+	} while (hmm_range->end < end);
+
+	hmm_range->start = start;
+	hmm_range->hmm_pfns = pfns;
 
  	/*
  	 * Due to default_flags, all pages are HMM_PFN_VALID or
#5 lore raw
Quoted 83 lines · Christian König

Am 21.11.22 um 14:13 schrieb James Zhu:

Quoted 80 lines

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu:     8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137]     (t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O 5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00 [  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603] amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]

---
  drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 49 +++++++++++++++++--------

  1 file changed, 34 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +1 -0
index a48ea62b12b0..fb51144ab77e 100644
@@ -163,6 +163,7 @@ int amdgpu_hmm_range_get_pages(struct 
 mmu_interval_notifier *notifier,
                      struct hmm_range **phmm_range)
   {
       struct hmm_range *hmm_range;
+    unsigned long end;
       unsigned long timeout;
       unsigned long i;

      unsigned long *pfns;

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +0 -1
@@ -184,25 +185,43 @@ int amdgpu_hmm_range_get_pages(struct 
 mmu_interval_notifier *notifier,
           hmm_range->default_flags |= HMM_PFN_REQ_WRITE;
       hmm_range->hmm_pfns = pfns;
       hmm_range->start = start;
-    hmm_range->end = start + npages * PAGE_SIZE;
Quoted 8 lines
Quoted 6 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +1 -0
+    end = start + npages * PAGE_SIZE;
       hmm_range->dev_private_owner = owner;

  -    /* Assuming 512MB takes maxmium 1 second to fault page address */ -    timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT; -    timeout = jiffies + msecs_to_jiffies(timeout);
+#define MAX_WALK_BYTE    (64ULL<<30)

Please don't add any defines in the middle of the code.

[JZ] sure. can I have RB on this patch? Thanks!

Quoted 49 lines
Quoted 48 lines

+    do {
+        hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, end);

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +5 -0
+
+        pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+            hmm_range->start, hmm_range->end);
+
+        /* Assuming 512MB takes maxmium 1 second to fault page 

address */
+        timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+            HMM_RANGE_DEFAULT_TIMEOUT;
+        timeout = jiffies + msecs_to_jiffies(timeout); retry:
-    hmm_range->notifier_seq = mmu_interval_read_begin(notifier); -    r = hmm_range_fault(hmm_range);
-    if (unlikely(r)) {
-        /*
-         * FIXME: This timeout should encompass the retry from -         * mmu_interval_read_retry() as well.
-         */
-        if (r == -EBUSY && !time_after(jiffies, timeout)) -            goto retry;
-        goto out_free_pfns;
-    }
+        hmm_range->notifier_seq = mmu_interval_read_begin(notifier); +        r = hmm_range_fault(hmm_range);
+        if (unlikely(r)) {
+            /*
+             * FIXME: This timeout should encompass the retry from +             * mmu_interval_read_retry() as well.
+             */
+            if (r == -EBUSY && !time_after(jiffies, timeout)) +                goto retry;
+            goto out_free_pfns;
+        }

drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +10 -0
+
+        if (hmm_range->end == end)
+            break;
+        hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
+        hmm_range->start = hmm_range->end;
+        schedule();
+    } while (hmm_range->end < end);
+
+    hmm_range->start = start;
+    hmm_range->hmm_pfns = pfns;

        /*
       * Due to default_flags, all pages are HMM_PFN_VALID or

author
#6 lore raw

PATCH v3 1/1 drm/amdgpu: fix stall on CPU when allocate large system memory

In reply to James Zhu

-v2: 1. rename variable to redue confuse
2. optimize the code
-v3: move new define out of the middle of the code

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: 	create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu: 	8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137] 	(t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O      5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00
[  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603]  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 50 +++++++++++++++++--------
 1 file changed, 35 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +35 -15
index a48ea62b12b0..8a2e5716d8db 100644
@@ -51,6 +51,8 @@
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_hmm.h"
 
+#define MAX_WALK_BYTE	(64ULL<<30)
+
 /**
  * amdgpu_hmm_invalidate_gfx - callback to notify about mm change
  *
@@ -163,6 +165,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       struct hmm_range **phmm_range)
 {
 	struct hmm_range *hmm_range;
+	unsigned long end;
 	unsigned long timeout;
 	unsigned long i;
 	unsigned long *pfns;
@@ -184,25 +187,42 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 		hmm_range->default_flags |= HMM_PFN_REQ_WRITE;
 	hmm_range->hmm_pfns = pfns;
 	hmm_range->start = start;
-	hmm_range->end = start + npages * PAGE_SIZE;
+	end = start + npages * PAGE_SIZE;
 	hmm_range->dev_private_owner = owner;
 
-	/* Assuming 512MB takes maxmium 1 second to fault page address */
-	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
-	timeout = jiffies + msecs_to_jiffies(timeout);
+	do {
+		hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, end);
+
+		pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+			hmm_range->start, hmm_range->end);
+
+		/* Assuming 512MB takes maxmium 1 second to fault page address */
+		timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+			HMM_RANGE_DEFAULT_TIMEOUT;
+		timeout = jiffies + msecs_to_jiffies(timeout);
 
 retry:
-	hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
-	r = hmm_range_fault(hmm_range);
-	if (unlikely(r)) {
-		/*
-		 * FIXME: This timeout should encompass the retry from
-		 * mmu_interval_read_retry() as well.
-		 */
-		if (r == -EBUSY && !time_after(jiffies, timeout))
-			goto retry;
-		goto out_free_pfns;
-	}
+		hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
+		r = hmm_range_fault(hmm_range);
+		if (unlikely(r)) {
+			/*
+			 * FIXME: This timeout should encompass the retry from
+			 * mmu_interval_read_retry() as well.
+			 */
+			if (r == -EBUSY && !time_after(jiffies, timeout))
+				goto retry;
+			goto out_free_pfns;
+		}
+
+		if (hmm_range->end == end)
+			break;
+		hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
+		hmm_range->start = hmm_range->end;
+		schedule();
+	} while (hmm_range->end < end);
+
+	hmm_range->start = start;
+	hmm_range->hmm_pfns = pfns;
 
 	/*
 	 * Due to default_flags, all pages are HMM_PFN_VALID or
Signature · 1 line
2.34.1
#7 lore raw

Ping...

Quoted 144 lines · James Zhu
(quoted diff) +0 -2
-v2: 1. rename variable to redue confuse
      2. optimize the code
-v3: move new define out of the middle of the code

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: 	create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu: 	8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137] 	(t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O      5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00
[  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603]  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]
---
  drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 50 +++++++++++++++++--------
  1 file changed, 35 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +35 -15
index a48ea62b12b0..8a2e5716d8db 100644
@@ -51,6 +51,8 @@
  #include "amdgpu_amdkfd.h"
  #include "amdgpu_hmm.h"
 
+#define MAX_WALK_BYTE	(64ULL<<30)
+
  /**
   * amdgpu_hmm_invalidate_gfx - callback to notify about mm change
   *
@@ -163,6 +165,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
  			       struct hmm_range **phmm_range)
  {
  	struct hmm_range *hmm_range;
+	unsigned long end;
  	unsigned long timeout;
  	unsigned long i;
  	unsigned long *pfns;
@@ -184,25 +187,42 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
  		hmm_range->default_flags |= HMM_PFN_REQ_WRITE;
  	hmm_range->hmm_pfns = pfns;
  	hmm_range->start = start;
-	hmm_range->end = start + npages * PAGE_SIZE;
+	end = start + npages * PAGE_SIZE;
  	hmm_range->dev_private_owner = owner;
 
-	/* Assuming 512MB takes maxmium 1 second to fault page address */
-	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
-	timeout = jiffies + msecs_to_jiffies(timeout);
+	do {
+		hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, end);
+
+		pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+			hmm_range->start, hmm_range->end);
+
+		/* Assuming 512MB takes maxmium 1 second to fault page address */
+		timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+			HMM_RANGE_DEFAULT_TIMEOUT;
+		timeout = jiffies + msecs_to_jiffies(timeout);
 
  retry:
-	hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
-	r = hmm_range_fault(hmm_range);
-	if (unlikely(r)) {
-		/*
-		 * FIXME: This timeout should encompass the retry from
-		 * mmu_interval_read_retry() as well.
-		 */
-		if (r == -EBUSY && !time_after(jiffies, timeout))
-			goto retry;
-		goto out_free_pfns;
-	}
+		hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
+		r = hmm_range_fault(hmm_range);
+		if (unlikely(r)) {
+			/*
+			 * FIXME: This timeout should encompass the retry from
+			 * mmu_interval_read_retry() as well.
+			 */
+			if (r == -EBUSY && !time_after(jiffies, timeout))
+				goto retry;
+			goto out_free_pfns;
+		}
+
+		if (hmm_range->end == end)
+			break;
+		hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
+		hmm_range->start = hmm_range->end;
+		schedule();
+	} while (hmm_range->end < end);
+
+	hmm_range->start = start;
+	hmm_range->hmm_pfns = pfns;
 
  	/*
  	 * Due to default_flags, all pages are HMM_PFN_VALID or
Reviewed-by on v3 1/1
#8 lore raw
In reply to James Zhu

Am 2022-11-21 um 09:53 schrieb James Zhu:

Quoted 60 lines
(quoted diff) +0 -2
-v2: 1. rename variable to redue confuse
      2. optimize the code
-v3: move new define out of the middle of the code

When applications try to allocate large system (more than > 128GB), "stall cpu" is reported.

for such large system memory, walk_page_range takes more than 20s usually. The warning message can be removed when splitting hmm range into smaller ones which is not more 64GB for each walk_page_range.

[  164.437617] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1753: amdgpu: 	create BO VA 0x7f63c7a00000 size 0x2f16000000 domain CPU
[  164.488847] amdgpu:amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu:1785: amdgpu: creating userptr BO for user_addr = 7f63c7a00000
[  185.439116] rcu: INFO: rcu_sched self-detected stall on CPU
[  185.439125] rcu: 	8-....: (20999 ticks this GP) idle=e22/1/0x4000000000000000 softirq=2242/2242 fqs=5249
[  185.439137] 	(t=21000 jiffies g=6325 q=1215)
[  185.439141] NMI backtrace for cpu 8
[  185.439143] CPU: 8 PID: 3470 Comm: kfdtest Kdump: loaded Tainted: G           O      5.12.0-0_fbk5_zion_rc1_5697_g2c723fb88626 #1
[  185.439147] Hardware name: HPE ProLiant XL675d Gen10 Plus/ProLiant XL675d Gen10 Plus, BIOS A47 11/06/2020
[  185.439150] Call Trace:
[  185.439153]  <IRQ>
[  185.439157]  dump_stack+0x64/0x7c
[  185.439163]  nmi_cpu_backtrace.cold.7+0x30/0x65
[  185.439165]  ? lapic_can_unplug_cpu+0x70/0x70
[  185.439170]  nmi_trigger_cpumask_backtrace+0xf9/0x100
[  185.439174]  rcu_dump_cpu_stacks+0xc5/0xf5
[  185.439178]  rcu_sched_clock_irq.cold.97+0x112/0x38c
[  185.439182]  ? tick_sched_handle.isra.21+0x50/0x50
[  185.439185]  update_process_times+0x8c/0xc0
[  185.439189]  tick_sched_timer+0x63/0x70
[  185.439192]  __hrtimer_run_queues+0xff/0x250
[  185.439195]  hrtimer_interrupt+0xf4/0x200
[  185.439199]  __sysvec_apic_timer_interrupt+0x51/0xd0
[  185.439201]  sysvec_apic_timer_interrupt+0x69/0x90
[  185.439206]  </IRQ>
[  185.439207]  asm_sysvec_apic_timer_interrupt+0x12/0x20
[  185.439211] RIP: 0010:clear_page_rep+0x7/0x10
[  185.439214] Code: e8 fe 7c 51 00 44 89 e2 48 89 ee 48 89 df e8 60 ff ff ff c6 03 00 5b 5d 41 5c c3 cc cc cc cc cc cc cc cc b9 00 02 00 00 31 c0 <f3> 48 ab c3 0f 1f 44 00 00 31 c0 b9 40 00 00 00 66 0f 1f 84 00 00
[  185.439218] RSP: 0018:ffffc9000f58f818 EFLAGS: 00000246
[  185.439220] RAX: 0000000000000000 RBX: 0000000000000881 RCX: 000000000000005c
[  185.439223] RDX: 0000000000100dca RSI: 0000000000000000 RDI: ffff88a59e0e5d20
[  185.439225] RBP: ffffea0096783940 R08: ffff888118c35280 R09: ffffea0096783940
[  185.439227] R10: ffff888000000000 R11: 0000160000000000 R12: ffffea0096783980
[  185.439228] R13: ffffea0096783940 R14: ffff88b07fdfdd00 R15: 0000000000000000
[  185.439232]  prep_new_page+0x81/0xc0
[  185.439236]  get_page_from_freelist+0x13be/0x16f0
[  185.439240]  ? release_pages+0x16a/0x4a0
[  185.439244]  __alloc_pages_nodemask+0x1ae/0x340
[  185.439247]  alloc_pages_vma+0x74/0x1e0
[  185.439251]  __handle_mm_fault+0xafe/0x1360
[  185.439255]  handle_mm_fault+0xc3/0x280
[  185.439257]  hmm_vma_fault.isra.22+0x49/0x90
[  185.439261]  __walk_page_range+0x692/0x9b0
[  185.439265]  walk_page_range+0x9b/0x120
[  185.439269]  hmm_range_fault+0x4f/0x90
[  185.439274]  amdgpu_hmm_range_get_pages+0x24f/0x260 [amdgpu]
[  185.439463]  amdgpu_ttm_tt_get_user_pages+0xc2/0x190 [amdgpu]
[  185.439603]  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x49f/0x7a0 [amdgpu]
[  185.439774]  kfd_ioctl_alloc_memory_of_gpu+0xfb/0x410 [amdgpu]
Quoted 1 line
Quoted 83 lines
---
  drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 50 +++++++++++++++++--------
  1 file changed, 35 insertions(+), 15 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +35 -15
index a48ea62b12b0..8a2e5716d8db 100644
@@ -51,6 +51,8 @@
  #include "amdgpu_amdkfd.h"
  #include "amdgpu_hmm.h"
 
+#define MAX_WALK_BYTE	(64ULL<<30)
+
  /**
   * amdgpu_hmm_invalidate_gfx - callback to notify about mm change
   *
@@ -163,6 +165,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
  			       struct hmm_range **phmm_range)
  {
  	struct hmm_range *hmm_range;
+	unsigned long end;
  	unsigned long timeout;
  	unsigned long i;
  	unsigned long *pfns;
@@ -184,25 +187,42 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
  		hmm_range->default_flags |= HMM_PFN_REQ_WRITE;
  	hmm_range->hmm_pfns = pfns;
  	hmm_range->start = start;
-	hmm_range->end = start + npages * PAGE_SIZE;
+	end = start + npages * PAGE_SIZE;
  	hmm_range->dev_private_owner = owner;
 
-	/* Assuming 512MB takes maxmium 1 second to fault page address */
-	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
-	timeout = jiffies + msecs_to_jiffies(timeout);
+	do {
+		hmm_range->end = min(hmm_range->start + MAX_WALK_BYTE, end);
+
+		pr_debug("hmm range: start = 0x%lx, end = 0x%lx",
+			hmm_range->start, hmm_range->end);
+
+		/* Assuming 512MB takes maxmium 1 second to fault page address */
+		timeout = max((hmm_range->end - hmm_range->start) >> 29, 1ULL) *
+			HMM_RANGE_DEFAULT_TIMEOUT;
+		timeout = jiffies + msecs_to_jiffies(timeout);
 
  retry:
-	hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
-	r = hmm_range_fault(hmm_range);
-	if (unlikely(r)) {
-		/*
-		 * FIXME: This timeout should encompass the retry from
-		 * mmu_interval_read_retry() as well.
-		 */
-		if (r == -EBUSY && !time_after(jiffies, timeout))
-			goto retry;
-		goto out_free_pfns;
-	}
+		hmm_range->notifier_seq = mmu_interval_read_begin(notifier);
+		r = hmm_range_fault(hmm_range);
+		if (unlikely(r)) {
+			/*
+			 * FIXME: This timeout should encompass the retry from
+			 * mmu_interval_read_retry() as well.
+			 */
+			if (r == -EBUSY && !time_after(jiffies, timeout))
+				goto retry;
+			goto out_free_pfns;
+		}
+
+		if (hmm_range->end == end)
+			break;
+		hmm_range->hmm_pfns += MAX_WALK_BYTE >> PAGE_SHIFT;
+		hmm_range->start = hmm_range->end;
+		schedule();
+	} while (hmm_range->end < end);
+
+	hmm_range->start = start;
+	hmm_range->hmm_pfns = pfns;
 
  	/*
  	 * Due to default_flags, all pages are HMM_PFN_VALID or