Re: [PATCH] riscv: mm: try VMA lock-based page fault handling first

From: Kefeng Wang
Date: Wed Jun 21 2023 - 02:15:38 EST




On 2023/5/24 0:59, Jisheng Zhang wrote:
Attempt VMA lock-based page fault handling first, and fall back to the
existing mmap_lock-based handling if that fails.

A simple running the ebizzy benchmark on Lichee Pi 4A shows that
PER_VMA_LOCK can improve the ebizzy benchmark by about 32.68%. In
theory, the more CPUs, the bigger improvement, but I don't have any
HW platform which has more than 4 CPUs.

This is the riscv variant of "x86/mm: try VMA lock-based page fault
handling first".

Signed-off-by: Jisheng Zhang <jszhang@xxxxxxxxxx>
---
Any performance numbers are welcome! Especially the numbers on HW
platforms with 8 or more CPUs.

arch/riscv/Kconfig | 1 +
arch/riscv/mm/fault.c | 33 +++++++++++++++++++++++++++++++++
2 files changed, 34 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 62e84fee2cfd..b958f67f9a12 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -42,6 +42,7 @@ config RISCV
select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
select ARCH_SUPPORTS_HUGETLBFS if MMU
select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU
+ select ARCH_SUPPORTS_PER_VMA_LOCK if MMU

no need if mmu, see PER_VMA_LOCK


config PER_VMA_LOCK
bool "allow VMA lock-based page fault"
def_bool y
depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP

Reviewed-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>

select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 8685f85a7474..eccdddf26f4b 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -286,6 +286,36 @@ void handle_page_fault(struct pt_regs *regs)
flags |= FAULT_FLAG_WRITE;
else if (cause == EXC_INST_PAGE_FAULT)
flags |= FAULT_FLAG_INSTRUCTION;
+#ifdef CONFIG_PER_VMA_LOCK
+ if (!(flags & FAULT_FLAG_USER))
+ goto lock_mmap;
+
+ vma = lock_vma_under_rcu(mm, addr);
+ if (!vma)
+ goto lock_mmap;
+
+ if (unlikely(access_error(cause, vma))) {
+ vma_end_read(vma);
+ goto lock_mmap;
+ }
+
+ fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs);
+ vma_end_read(vma);
+
+ if (!(fault & VM_FAULT_RETRY)) {
+ count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+ goto done;
+ }
+ count_vm_vma_lock_event(VMA_LOCK_RETRY);
+
+ if (fault_signal_pending(fault, regs)) {
+ if (!user_mode(regs))
+ no_context(regs, addr);
+ return;
+ }
+lock_mmap:
+#endif /* CONFIG_PER_VMA_LOCK */
+
retry:
mmap_read_lock(mm);
vma = find_vma(mm, addr);
@@ -355,6 +385,9 @@ void handle_page_fault(struct pt_regs *regs)
mmap_read_unlock(mm);
+#ifdef CONFIG_PER_VMA_LOCK
+done:
+#endif
if (unlikely(fault & VM_FAULT_ERROR)) {
tsk->thread.bad_cause = cause;
mm_fault_error(regs, addr, fault);