Skip to contentSkip to conversation

tlb: hugetlb: Add arm64 contiguous hint awareness

PATCH In review Steve Capper 6 participants 14 messages Mar 23, 2022 – Apr 6, 2022

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 tlb: hugetlb: Add arm64 contiguous hint awareness

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

This patch adds the ability to define per-arch implementations of tlb_remove_huge_tlb_entry and supplies an arm64 implementation that covers the contiguous hint sizes.

---
 arch/arm64/include/asm/tlb.h | 14 ++++++++++++++
 include/asm-generic/tlb.h    |  2 ++
 2 files changed, 16 insertions(+)
arch/arm64/include/asm/tlb.h +14 -0
index c995d1f4594f..311d201d4e72 100644
@@ -19,6 +19,20 @@ static inline void __tlb_remove_table(void *_table)
 #define tlb_flush tlb_flush
 static void tlb_flush(struct mmu_gather *tlb);
 
+#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
+	do {							\
+		unsigned long _sz = huge_page_size(h);		\
+		if (_sz == CONT_PTE_SIZE)			\
+			tlb_flush_pte_range(tlb, address, _sz);	\
+		else if (_sz == PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else if (_sz == CONT_PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else if (_sz == PUD_SIZE)			\
+			tlb_flush_pud_range(tlb, address, _sz);	\
+		__tlb_remove_tlb_entry(tlb, ptep, address);	\
+	} while (0)
+
 #include <asm-generic/tlb.h>
 
 /*
include/asm-generic/tlb.h +2 -0
index 2c68a545ffa7..4622ee45f739 100644
@@ -562,6 +562,7 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
+#ifndef tlb_remove_huge_tlb_entry
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
@@ -571,6 +572,7 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
 			tlb_flush_pud_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
+#endif
 
 /**
  * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation
Signature · 1 line
2.35.1
maintainer Reviewed-by on v1 1/1
#1 lore raw
Quoted 13 lines · Steve Capper

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

This patch adds the ability to define per-arch implementations of tlb_remove_huge_tlb_entry and supplies an arm64 implementation that covers the contiguous hint sizes.

Quoted 7 lines
maintainer
#2 lore raw
In reply to Steve Capper

arch/arm64/include/asm/tlb.h static inline void __tlb_remove_table(void *_table) · line 34

Quoted 13 lines · Steve Capper
arch/arm64/include/asm/tlb.h +13 -0
+#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
+	do {							\
+		unsigned long _sz = huge_page_size(h);		\
+		if (_sz == CONT_PTE_SIZE)			\
+			tlb_flush_pte_range(tlb, address, _sz);	\
+		else if (_sz == PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else if (_sz == CONT_PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else if (_sz == PUD_SIZE)			\
+			tlb_flush_pud_range(tlb, address, _sz);	\
+		__tlb_remove_tlb_entry(tlb, ptep, address);	\
+	} while (0)

It occurs to me that perhaps this can be written like:

	unsigned long _sz = huge_page_size(h);
	if (_sz >= P4D_SIZE)
		tlb_flush_p4d_range(tlb, address, _sz);
	else if (_sz >= PUD_SIZE)
		tlb_flush_pud_range(tlb, address, _sz);
	else if (_sz >= PMD_SIZE)
		tlb_flush_pmd_range(tlb, address, _sz);
	else
		tlb_flush_pte_range(tlb, address, _sz);
	__tlb_remove_tlb_entry(tlb, ptep, address);

And then it can still be generic..

#3 lore raw
Quoted 30 lines · Peter Zijlstra

arch/arm64/include/asm/tlb.h static inline void __tlb_remove_table(void *_table) · line 34

Quoted 13 lines · Steve Capper
arch/arm64/include/asm/tlb.h +13 -0
+#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
+	do {							\
+		unsigned long _sz = huge_page_size(h);		\
+		if (_sz == CONT_PTE_SIZE)			\
+			tlb_flush_pte_range(tlb, address, _sz);	\
+		else if (_sz == PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else if (_sz == CONT_PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else if (_sz == PUD_SIZE)			\
+			tlb_flush_pud_range(tlb, address, _sz);	\
+		__tlb_remove_tlb_entry(tlb, ptep, address);	\
+	} while (0)

It occurs to me that perhaps this can be written like:

	unsigned long _sz = huge_page_size(h);
	if (_sz >= P4D_SIZE)
		tlb_flush_p4d_range(tlb, address, _sz);
	else if (_sz >= PUD_SIZE)
		tlb_flush_pud_range(tlb, address, _sz);
	else if (_sz >= PMD_SIZE)
		tlb_flush_pmd_range(tlb, address, _sz);
	else
		tlb_flush_pte_range(tlb, address, _sz);
	__tlb_remove_tlb_entry(tlb, ptep, address);
Quoted 1 line

And then it can still be generic..

Thanks Peter,
My concern with that would be the CONT_PMD_SIZE case would result in a call to tlb_flush_pte_range rather than tlb_flush_pmd_range causing some of the level parameters to be different.

Would that cause an issue?

Cheers,

Signature · 1 line
Steve
maintainer
#4 lore raw
Quoted 13 lines · Steve Capper
Quoted 13 lines

It occurs to me that perhaps this can be written like:

	unsigned long _sz = huge_page_size(h);
	if (_sz >= P4D_SIZE)
		tlb_flush_p4d_range(tlb, address, _sz);
	else if (_sz >= PUD_SIZE)
		tlb_flush_pud_range(tlb, address, _sz);
	else if (_sz >= PMD_SIZE)
		tlb_flush_pmd_range(tlb, address, _sz);
	else
		tlb_flush_pte_range(tlb, address, _sz);
	__tlb_remove_tlb_entry(tlb, ptep, address);
Quoted 6 lines
Quoted 1 line

And then it can still be generic..

Thanks Peter,
My concern with that would be the CONT_PMD_SIZE case would result in a call to tlb_flush_pte_range rather than tlb_flush_pmd_range causing some of the level parameters to be different.

arch/arm64/include/asm/pgtable-hwdef.h:#define CONT_PMD_SIZE (CONT_PMDS * PMD_SIZE)

Seems to imply CONT_PMD_SIZE >= PMD_SIZE, and would thus tickle:

Quoted 2 lines
Quoted 2 lines
	else if (_sz >= PMD_SIZE)
		tlb_flush_pmd_range(tlb, address, _sz);

Or am I confused?

#5 lore raw
Quoted 21 lines · Peter Zijlstra
Quoted 13 lines · Steve Capper
Quoted 13 lines

It occurs to me that perhaps this can be written like:

	unsigned long _sz = huge_page_size(h);
	if (_sz >= P4D_SIZE)
		tlb_flush_p4d_range(tlb, address, _sz);
	else if (_sz >= PUD_SIZE)
		tlb_flush_pud_range(tlb, address, _sz);
	else if (_sz >= PMD_SIZE)
		tlb_flush_pmd_range(tlb, address, _sz);
	else
		tlb_flush_pte_range(tlb, address, _sz);
	__tlb_remove_tlb_entry(tlb, ptep, address);
Quoted 6 lines
Quoted 1 line

And then it can still be generic..

Thanks Peter,
My concern with that would be the CONT_PMD_SIZE case would result in a call to tlb_flush_pte_range rather than tlb_flush_pmd_range causing some of the level parameters to be different.

Quoted 8 lines

arch/arm64/include/asm/pgtable-hwdef.h:#define CONT_PMD_SIZE (CONT_PMDS * PMD_SIZE)

Seems to imply CONT_PMD_SIZE >= PMD_SIZE, and would thus tickle:

Quoted 2 lines
Quoted 2 lines
	else if (_sz >= PMD_SIZE)
		tlb_flush_pmd_range(tlb, address, _sz);

Or am I confused?

Nope, it was me who was confused :-).
I misread one of the the lines sorry.
Yeah this should be fine for arm64.

Cheers,

Signature · 1 line
Steve
#6 lore raw

PATCH v2 1/1 tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

This patch adds inequality logic to the generic implementation of tlb_remove_huge_tlb_entry s.t. CONT_PTE_SIZE and CONT_PMD_SIZE are effectively covered on arm64. Also, as well as ptes, pmds and puds; p4ds are now considered too.

---

Changed in V2: instead of doing the per-arch implementation of tlb_remove_huge_tlb_entry we add to the generic implmentation, as suggested by PeterZ.

This works well on arm64 with contiguous PTEs/PMDs. Does this look reasonable to the ppc folk?

Cheers,
--
Steve

---
 include/asm-generic/tlb.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
include/asm-generic/tlb.h +7 -3
index 2c68a545ffa7..71942a1c642d 100644
@@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		if (_sz == PMD_SIZE)				\
-			tlb_flush_pmd_range(tlb, address, _sz);	\
-		else if (_sz == PUD_SIZE)			\
+		if (_sz >= P4D_SIZE)				\
+			tlb_flush_p4d_range(tlb, address, _sz);	\
+		else if (_sz >= PUD_SIZE)			\
 			tlb_flush_pud_range(tlb, address, _sz);	\
+		else if (_sz >= PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else						\
+			tlb_flush_pte_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
Signature · 1 line
2.35.1
Acked-by on v2 1/1
#7 lore raw

Re: [PATCH v2] tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

Quoted 50 lines · Steve Capper

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

This patch adds inequality logic to the generic implementation of tlb_remove_huge_tlb_entry s.t. CONT_PTE_SIZE and CONT_PMD_SIZE are effectively covered on arm64. Also, as well as ptes, pmds and puds; p4ds are now considered too.

---

Changed in V2: instead of doing the per-arch implementation of tlb_remove_huge_tlb_entry we add to the generic implmentation, as suggested by PeterZ.

This works well on arm64 with contiguous PTEs/PMDs. Does this look reasonable to the ppc folk?

Cheers,
--
Steve

---
 include/asm-generic/tlb.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
include/asm-generic/tlb.h +1 -3
index 2c68a545ffa7..71942a1c642d 100644
@@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		if (_sz == PMD_SIZE)				\
-			tlb_flush_pmd_range(tlb, address, _sz);	\
-		else if (_sz == PUD_SIZE)			\
+		if (_sz >= P4D_SIZE)				\

include/asm-generic/tlb.h static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, · line 578

Quoted 10 lines
include/asm-generic/tlb.h +6 -0
+			tlb_flush_p4d_range(tlb, address, _sz);	\
+		else if (_sz >= PUD_SIZE)			\
 			tlb_flush_pud_range(tlb, address, _sz);	\
+		else if (_sz >= PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else						\
+			tlb_flush_pte_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 

LGTM

Signature · 3 lines
Thanks,

David / dhildenb
#8 lore raw

Re: [PATCH v2] tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

In reply to Steve Capper
Quoted 22 lines · Steve Capper

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

This patch adds inequality logic to the generic implementation of tlb_remove_huge_tlb_entry s.t. CONT_PTE_SIZE and CONT_PMD_SIZE are effectively covered on arm64. Also, as well as ptes, pmds and puds; p4ds are now considered too.

Quoted 8 lines

---

Changed in V2: instead of doing the per-arch implementation of tlb_remove_huge_tlb_entry we add to the generic implmentation, as suggested by PeterZ.

This works well on arm64 with contiguous PTEs/PMDs. Does this look reasonable to the ppc folk?

I am wondering whether this should take care of gigantic PGDIR_SIZE based HugeTLB pages as well ? Although, it will require another new helper tlb_flush_pgd_range(). Any thoughts ?

Quoted 30 lines

Cheers,
--
Steve

---
 include/asm-generic/tlb.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
include/asm-generic/tlb.h +7 -3
index 2c68a545ffa7..71942a1c642d 100644
@@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		if (_sz == PMD_SIZE)				\
-			tlb_flush_pmd_range(tlb, address, _sz);	\
-		else if (_sz == PUD_SIZE)			\
+		if (_sz >= P4D_SIZE)				\
+			tlb_flush_p4d_range(tlb, address, _sz);	\
+		else if (_sz >= PUD_SIZE)			\
 			tlb_flush_pud_range(tlb, address, _sz);	\
+		else if (_sz >= PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else						\
+			tlb_flush_pte_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
maintainer
#9 lore raw

Re: [PATCH v2] tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

Quoted 3 lines · Anshuman Khandual

I am wondering whether this should take care of gigantic PGDIR_SIZE based HugeTLB pages as well ? Although, it will require another new helper tlb_flush_pgd_range(). Any thoughts ?

I'm thinking that should be straight forward, you need a ->cleared_pgds along with all that, but yeah.

Reviewed-by on v2 1/1
#10 lore raw

Re: [PATCH v2] tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

In reply to Steve Capper
Quoted 14 lines · Steve Capper

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

This patch adds inequality logic to the generic implementation of tlb_remove_huge_tlb_entry s.t. CONT_PTE_SIZE and CONT_PMD_SIZE are effectively covered on arm64. Also, as well as ptes, pmds and puds; p4ds are now considered too.

Quoted 7 lines
Quoted 39 lines

---

Changed in V2: instead of doing the per-arch implementation of tlb_remove_huge_tlb_entry we add to the generic implmentation, as suggested by PeterZ.

This works well on arm64 with contiguous PTEs/PMDs. Does this look reasonable to the ppc folk?

Cheers,
--
Steve

---
 include/asm-generic/tlb.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
include/asm-generic/tlb.h +7 -3
index 2c68a545ffa7..71942a1c642d 100644
@@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		if (_sz == PMD_SIZE)				\
-			tlb_flush_pmd_range(tlb, address, _sz);	\
-		else if (_sz == PUD_SIZE)			\
+		if (_sz >= P4D_SIZE)				\
+			tlb_flush_p4d_range(tlb, address, _sz);	\
+		else if (_sz >= PUD_SIZE)			\
 			tlb_flush_pud_range(tlb, address, _sz);	\
+		else if (_sz >= PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else						\
+			tlb_flush_pte_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
maintainer Reviewed-by on v2 1/1
#11 lore raw

Re: [PATCH v2] tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

In reply to Steve Capper
Quoted 14 lines · Steve Capper

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

This patch adds inequality logic to the generic implementation of tlb_remove_huge_tlb_entry s.t. CONT_PTE_SIZE and CONT_PMD_SIZE are effectively covered on arm64. Also, as well as ptes, pmds and puds; p4ds are now considered too.

Quoted 7 lines
maintainer Acked-by on v2 1/1
#12 lore raw

Re: [PATCH v2] tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

In reply to Steve Capper
Quoted 14 lines · Steve Capper

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

This patch adds inequality logic to the generic implementation of tlb_remove_huge_tlb_entry s.t. CONT_PTE_SIZE and CONT_PMD_SIZE are effectively covered on arm64. Also, as well as ptes, pmds and puds; p4ds are now considered too.

Quoted 7 lines
Quoted 29 lines
---
 include/asm-generic/tlb.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)
include/asm-generic/tlb.h +7 -3
index 2c68a545ffa7..71942a1c642d 100644
@@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		if (_sz == PMD_SIZE)				\
-			tlb_flush_pmd_range(tlb, address, _sz);	\
-		else if (_sz == PUD_SIZE)			\
+		if (_sz >= P4D_SIZE)				\
+			tlb_flush_p4d_range(tlb, address, _sz);	\
+		else if (_sz >= PUD_SIZE)			\
 			tlb_flush_pud_range(tlb, address, _sz);	\
+		else if (_sz >= PMD_SIZE)			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
+		else						\
+			tlb_flush_pte_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
Signature · 1 line
2.35.1
maintainer Applied
#13 lore raw

Re: [PATCH v2] tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

In reply to Steve Capper
Quoted 10 lines · Steve Capper

tlb_remove_huge_tlb_entry only considers PMD_SIZE and PUD_SIZE when updating the mmu_gather structure.

Unfortunately on arm64 there are two additional huge page sizes that need to be covered: CONT_PTE_SIZE and CONT_PMD_SIZE. Where an end-user attempts to employ contiguous huge pages, a VM_BUG_ON can be experienced due to the fact that the tlb structure hasn't been correctly updated by the relevant tlb_flush_p.._range() call from tlb_remove_huge_tlb_entry.

[...]

Applied to arm64 (for-next/fixes), thanks!

[1/1] tlb: hugetlb: Add more sizes to tlb_remove_huge_tlb_entry

      https://git.kernel.org/arm64/c/697a1d44af8b

Cheers,

Signature · 5 lines
Will

https://fixes.arm64.dev
https://next.arm64.dev
https://will.arm64.dev