[PATCH RFC/RFT v2 4/4] riscv: Stop emitting preventive sfence.vma for new userspace mappings with Svvptc

[Alexandre Ghiti <alexghiti@rivosinc.com>]

The preventive sfence.vma were emitted because new mappings must be made
visible to the page table walker but Svvptc guarantees that xRET act as
a fence, so no need to sfence.vma for the uarchs that implement this
extension.

This allows to drastically reduce the number of sfence.vma emitted:

* Ubuntu boot to login:
Before: ~630k sfence.vma
After:  ~200k sfence.vma

* ltp - mmapstress01
Before: ~45k
After:  ~6.3k

* lmbench - lat_pagefault
Before: ~665k
After:   832 (!)

* lmbench - lat_mmap
Before: ~546k
After:   718 (!)

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
 arch/riscv/include/asm/pgtable.h | 16 +++++++++++++++-
 arch/riscv/mm/pgtable.c          | 13 +++++++++++++
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 0c94260b5d0c..50986e4c4601 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -473,6 +473,9 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 		struct vm_area_struct *vma, unsigned long address,
 		pte_t *ptep, unsigned int nr)
 {
+	asm_volatile_goto(ALTERNATIVE("nop", "j %l[svvptc]", 0, RISCV_ISA_EXT_SVVPTC, 1)
+			  : : : : svvptc);
+
 	/*
 	 * The kernel assumes that TLBs don't cache invalid entries, but
 	 * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a
@@ -482,12 +485,23 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 	 */
 	while (nr--)
 		local_flush_tlb_page(address + nr * PAGE_SIZE);
+
+svvptc:
+	/*
+	 * Svvptc guarantees that xRET act as a fence, so when the uarch does
+	 * not cache invalid entries, we don't have to do anything.
+	 */
+	;
 }
 #define update_mmu_cache(vma, addr, ptep) \
 	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
 
 #define __HAVE_ARCH_UPDATE_MMU_TLB
-#define update_mmu_tlb update_mmu_cache
+static inline void update_mmu_tlb(struct vm_area_struct *vma,
+				  unsigned long address, pte_t *ptep)
+{
+	flush_tlb_range(vma, address, address + PAGE_SIZE);
+}
 
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmdp)
diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c
index ef887efcb679..99ed389e4c8a 100644
--- a/arch/riscv/mm/pgtable.c
+++ b/arch/riscv/mm/pgtable.c
@@ -9,6 +9,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 			  unsigned long address, pte_t *ptep,
 			  pte_t entry, int dirty)
 {
+	asm_volatile_goto(ALTERNATIVE("nop", "j %l[svvptc]", 0, RISCV_ISA_EXT_SVVPTC, 1)
+			  : : : : svvptc);
+
 	if (!pte_same(ptep_get(ptep), entry))
 		__set_pte_at(ptep, entry);
 	/*
@@ -16,6 +19,16 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * the case that the PTE changed and the spurious fault case.
 	 */
 	return true;
+
+svvptc:
+	if (!pte_same(ptep_get(ptep), entry)) {
+		__set_pte_at(ptep, entry);
+		/* Here only not svadu is impacted */
+		flush_tlb_page(vma, address);
+		return true;
+	}
+
+	return false;
 }
 
 int ptep_test_and_clear_young(struct vm_area_struct *vma,
-- 
2.39.2