HAVE_MOVE_PUD enables remapping pages at the PUD level if both the
source and destination addresses are PUD-aligned.
With HAVE_MOVE_PUD enabled it can be inferred that there is approximately
a 19x improvement in performance on arm64. (See data below).
------- Test Results ---------
The following results were obtained using a 5.4 kernel, by remapping
a PUD-aligned, 1GB sized region to a PUD-aligned destination.
The results from 10 iterations of the test are given below:
Total mremap times for 1GB data on arm64. All times are in nanoseconds.
Control HAVE_MOVE_PUD
1247761 74271
1219896 46771
1094792 59687
1227760 48385
1043698 76666
1101771 50365
1159896 52500
1143594 75261
1025833 61354
1078125 48697
1134312.6 59395.7 <-- Mean time in nanoseconds
A 1GB mremap completion time drops from ~1.1 milliseconds
to ~59 microseconds on arm64. (~19x speed up).
Signed-off-by: Kalesh Singh <[email protected]>
Acked-by: Kirill A. Shutemov <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Andrew Morton <[email protected]>
---
Changes in v3:
- Add set_pud_at() macro - Used by move_normal_pud().
Changes in v4:
- Add Kirill's Acked-by.
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/pgtable.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 434d6791e869..7191a79fb44d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -124,6 +124,7 @@ config ARM64
select HANDLE_DOMAIN_IRQ
select HARDIRQS_SW_RESEND
select HAVE_MOVE_PMD
+ select HAVE_MOVE_PUD
select HAVE_PCI
select HAVE_ACPI_APEI if (ACPI && EFI)
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index a11bf52e0c38..0b0b36974757 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -454,6 +454,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
#define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
#define set_pmd_at(mm, addr, pmdp, pmd) set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
+#define set_pud_at(mm, addr, pudp, pud) set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud))
#define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d))
#define __phys_to_p4d_val(phys) __phys_to_pte_val(phys)
--
2.28.0.1011.ga647a8990f-goog