riscv: mm: execute local TLB flush after populating vmemmap

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 sparse_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: d95f1a54 ("RISC-V: Implement sparsemem")
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20240117140333.2479667-1-vincent.chen@sifive.com
Fixes: 7a92fc8b ("mm: Introduce flush_cache_vmap_early()")
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/include/asm/tlbflush.h

@@ -75,6 +75,7 @@ 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 */

arch/riscv/mm/init.c

@@ -1385,6 +1385,10 @@ 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();

arch/riscv/mm/tlbflush.c

@@ -66,9 +66,10 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
+/* 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, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
 }
 
 static void __ipi_flush_tlb_all(void *info)