[PATCH v5 2/4] mm: support Svnapot in physical page linear-mapping

[panqinglin2020 at iscas.ac.cn]

From: Qinglin Pan <panqinglin2020 at iscas.ac.cn>

Svnapot is powerful when a physical region is going to mapped to a
virtual region. Kernel will do like this when mapping all allocable
physical pages to kernel vm space. This commit modifies the
create_pte_mapping function used in linear-mapping procedure, so the
kernel can be able to use Svnapot when both address and length of
physical region are 64KB align. Code here will be executed only when
other size huge page is not suitable, so it can be an addition of
PMD_SIZE and PUD_SIZE mapping.

This commit also modifies the best_map_size function to give map_size
many times instead of only once, so a memory region can be mapped by
both PMD_SIZE and 64KB napot size.

It is tested by setting qemu's memory to a 262272k region, and the
kernel can boot successfully.

Currently, the modified create_pte_mapping will never take use of SVNAPOT,
because this extension is detected in riscv_fill_hwcap and enabled in
apply_boot_alternatives(called from setup_arch) which is called
after setup_vm_final. We will need to support function like
riscv_fill_hwcap_early to fill hardware capabilities more earlier, and
try to enable SVNAPOT more earlier in apply_early_boot_alternatives,
so that we can determine SVNAPOT's presence during setup_vm_final.

Signed-off-by: Qinglin Pan <panqinglin2020 at iscas.ac.cn>

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index b56a0a75533f..76317bb28f29 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -373,9 +373,21 @@ static void __init create_pte_mapping(pte_t *ptep,
 				      phys_addr_t sz, pgprot_t prot)
 {
 	uintptr_t pte_idx = pte_index(va);
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+	pte_t pte;
+
+	if (has_svnapot() && sz == NAPOT_CONT64KB_SIZE) {
+		do {
+			pte = pfn_pte(PFN_DOWN(pa), prot);
+			ptep[pte_idx] = pte_mknapot(pte, NAPOT_CONT64KB_ORDER);
+			pte_idx++;
+			sz -= PAGE_SIZE;
+		} while (sz > 0);
+		return;
+	}
+#endif
 
 	BUG_ON(sz != PAGE_SIZE);
-
 	if (pte_none(ptep[pte_idx]))
 		ptep[pte_idx] = pfn_pte(PFN_DOWN(pa), prot);
 }
@@ -673,10 +685,18 @@ void __init create_pgd_mapping(pgd_t *pgdp,
 static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
 {
 	/* Upgrade to PMD_SIZE mappings whenever possible */
-	if ((base & (PMD_SIZE - 1)) || (size & (PMD_SIZE - 1)))
+	base &= PMD_SIZE - 1;
+	if (!base && size >= PMD_SIZE)
+		return PMD_SIZE;
+
+	if (!has_svnapot())
 		return PAGE_SIZE;
 
-	return PMD_SIZE;
+	base &= NAPOT_CONT64KB_SIZE - 1;
+	if (!base && size >= NAPOT_CONT64KB_SIZE)
+		return NAPOT_CONT64KB_SIZE;
+
+	return PAGE_SIZE;
 }
 
 #ifdef CONFIG_XIP_KERNEL
@@ -1111,9 +1131,9 @@ static void __init setup_vm_final(void)
 		if (end >= __pa(PAGE_OFFSET) + memory_limit)
 			end = __pa(PAGE_OFFSET) + memory_limit;
 
-		map_size = best_map_size(start, end - start);
 		for (pa = start; pa < end; pa += map_size) {
 			va = (uintptr_t)__va(pa);
+			map_size = best_map_size(pa, end - pa);
 
 			create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
 					   pgprot_from_va(va));
-- 
2.35.1