[PATCH v5] riscv: mm: execute local TLB flush after populating vmemmap

[Vincent Chen]

The spare_init() calls memmap_populate() many times to create VA to PA
mapping for the VMEMMAP area, where all "struct page" are located once
CONFIG_SPARSEMEM_VMEMMAP is defined. These "struct page" are later
initialized in the zone_sizes_init() function. However, during this
process, no sfence.vma instruction is executed for this VMEMMAP area.
This omission may cause the hart to fail to perform page table walk
because some data related to the address translation is invisible to the
hart. To solve this issue, the local_flush_tlb_kernel_range() is called
right after the spare_init() to execute a sfence.vma instruction for this
VMEMMAP area, ensuring that all data related to the address translation
is visible to the hart.

Fixes: d95f1a542c3d ("RISC-V: Implement sparsemem")
Signed-off-by: Vincent Chen <vincent.chen at sifive.com>
---
 arch/riscv/include/asm/tlbflush.h | 2 ++
 arch/riscv/mm/init.c              | 5 +++++
 arch/riscv/mm/tlbflush.c          | 6 ++++++
 3 files changed, 13 insertions(+)

diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 8f3418c5f172..525267379ccb 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -46,6 +46,7 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end);
 #endif
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #else /* CONFIG_SMP && CONFIG_MMU */
 
 #define flush_tlb_all() local_flush_tlb_all()
@@ -66,6 +67,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 
 #define flush_tlb_mm(mm) flush_tlb_all()
 #define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
+#define local_flush_tlb_kernel_range(start, end) flush_tlb_all()
 #endif /* !CONFIG_SMP || !CONFIG_MMU */
 
 #endif /* _ASM_RISCV_TLBFLUSH_H */
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 2e011cbddf3a..cc56a0945120 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1377,6 +1377,10 @@ void __init misc_mem_init(void)
 	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
 	arch_numa_init();
 	sparse_init();
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	/* The entire VMEMMAP region has been populated. Flush TLB for this region */
+	local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END);
+#endif
 	zone_sizes_init();
 	arch_reserve_crashkernel();
 	memblock_dump_all();
@@ -1386,6 +1390,7 @@ void __init misc_mem_init(void)
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 			       struct vmem_altmap *altmap)
 {
+	/* Defer the required TLB flush until the entire VMEMMAP region has been populated */
 	return vmemmap_populate_basepages(start, end, node, NULL);
 }
 #endif
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index e6659d7368b3..d11a4ae87ec1 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -193,6 +193,12 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 	__flush_tlb_range(NULL, start, end - start, PAGE_SIZE);
 }
 
+/* Flush a range of kernel pages without broadcasting */
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end)
-- 
2.34.1