mm/sparse-vmemmap: generalise vmemmap_populate_hugepages()

Generalise vmemmap_populate_hugepages() so ARM64 & X86 & LoongArch can
share its implementation.

Link: https://lkml.kernel.org/r/20221027125253.3458989-4-chenhuacai@loongson.cn
Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Min Zhou <zhoumin@loongson.cn>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Philippe Mathieu-Daudé <philmd@linaro.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Xuefeng Li <lixuefeng@loongson.cn>
Cc: Xuerui Wang <kernel@xen0n.name>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/arm64/mm/mmu.c

@@ -1137,53 +1137,28 @@ static void free_empty_tables(unsigned long addr, unsigned long end,
 }
 #endif
 
+void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node,
+			       unsigned long addr, unsigned long next)
+{
+	pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
+}
+
+int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node,
+				unsigned long addr, unsigned long next)
+{
+	vmemmap_verify((pte_t *)pmdp, node, addr, next);
+	return 1;
+}
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
-	unsigned long addr = start;
-	unsigned long next;
-	pgd_t *pgdp;
-	p4d_t *p4dp;
-	pud_t *pudp;
-	pmd_t *pmdp;
-
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
 
 	if (!ARM64_KERNEL_USES_PMD_MAPS)
 		return vmemmap_populate_basepages(start, end, node, altmap);
-
+	else
-	do {
+		return vmemmap_populate_hugepages(start, end, node, altmap);
-		next = pmd_addr_end(addr, end);
-
-		pgdp = vmemmap_pgd_populate(addr, node);
-		if (!pgdp)
-			return -ENOMEM;
-
-		p4dp = vmemmap_p4d_populate(pgdp, addr, node);
-		if (!p4dp)
-			return -ENOMEM;
-
-		pudp = vmemmap_pud_populate(p4dp, addr, node);
-		if (!pudp)
-			return -ENOMEM;
-
-		pmdp = pmd_offset(pudp, addr);
-		if (pmd_none(READ_ONCE(*pmdp))) {
-			void *p = NULL;
-
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
-			if (!p) {
-				if (vmemmap_populate_basepages(addr, next, node, altmap))
-					return -ENOMEM;
-				continue;
-			}
-
-			pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL));
-		} else
-			vmemmap_verify((pte_t *)pmdp, node, addr, next);
-	} while (addr = next, addr != end);
-
-	return 0;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG

arch/loongarch/mm/init.c

@@ -153,52 +153,25 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-static int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
-						int node, struct vmem_altmap *altmap)
+			       unsigned long addr, unsigned long next)
 {
-	unsigned long addr = start;
+	pmd_t entry;
-	unsigned long next;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
 
-	for (addr = start; addr < end; addr = next) {
+	entry = pfn_pmd(virt_to_pfn(p), PAGE_KERNEL);
-		next = pmd_addr_end(addr, end);
+	pmd_val(entry) |= _PAGE_HUGE | _PAGE_HGLOBAL;
+	set_pmd_at(&init_mm, addr, pmd, entry);
+}
 
-		pgd = vmemmap_pgd_populate(addr, node);
+int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
-		if (!pgd)
+				unsigned long addr, unsigned long next)
-			return -ENOMEM;
+{
-		p4d = vmemmap_p4d_populate(pgd, addr, node);
+	int huge = pmd_val(*pmd) & _PAGE_HUGE;
-		if (!p4d)
-			return -ENOMEM;
-		pud = vmemmap_pud_populate(p4d, addr, node);
-		if (!pud)
-			return -ENOMEM;
 
-		pmd = pmd_offset(pud, addr);
+	if (huge)
-		if (pmd_none(*pmd)) {
+		vmemmap_verify((pte_t *)pmd, node, addr, next);
-			void *p = NULL;
 
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node, NULL);
+	return huge;
-			if (p) {
-				pmd_t entry;
-
-				entry = pfn_pmd(virt_to_pfn(p), PAGE_KERNEL);
-				pmd_val(entry) |= _PAGE_HUGE | _PAGE_HGLOBAL;
-				set_pmd_at(&init_mm, addr, pmd, entry);
-
-				continue;
-			}
-		} else if (pmd_val(*pmd) & _PAGE_HUGE) {
-			vmemmap_verify((pte_t *)pmd, node, addr, next);
-			continue;
-		}
-		if (vmemmap_populate_basepages(addr, next, node, NULL))
-			return -ENOMEM;
-	}
-
-	return 0;
 }
 
 int __meminit vmemmap_populate(unsigned long start, unsigned long end,

arch/x86/mm/init_64.c

@@ -1492,72 +1492,44 @@ static long __meminitdata addr_start, addr_end;
 static void __meminitdata *p_start, *p_end;
 static int __meminitdata node_start;
 
-static int __meminit vmemmap_populate_hugepages(unsigned long start,
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
-		unsigned long end, int node, struct vmem_altmap *altmap)
+			       unsigned long addr, unsigned long next)
 {
-	unsigned long addr;
+	pte_t entry;
-	unsigned long next;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
 
-	for (addr = start; addr < end; addr = next) {
+	entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
-		next = pmd_addr_end(addr, end);
+			PAGE_KERNEL_LARGE);
+	set_pmd(pmd, __pmd(pte_val(entry)));
 
-		pgd = vmemmap_pgd_populate(addr, node);
+	/* check to see if we have contiguous blocks */
-		if (!pgd)
+	if (p_end != p || node_start != node) {
-			return -ENOMEM;
+		if (p_start)
-
+			pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
-		p4d = vmemmap_p4d_populate(pgd, addr, node);
+				addr_start, addr_end-1, p_start, p_end-1, node_start);
-		if (!p4d)
+		addr_start = addr;
-			return -ENOMEM;
+		node_start = node;
-
+		p_start = p;
-		pud = vmemmap_pud_populate(p4d, addr, node);
-		if (!pud)
-			return -ENOMEM;
-
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
-			void *p;
-
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
-			if (p) {
-				pte_t entry;
-
-				entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
-						PAGE_KERNEL_LARGE);
-				set_pmd(pmd, __pmd(pte_val(entry)));
-
-				/* check to see if we have contiguous blocks */
-				if (p_end != p || node_start != node) {
-					if (p_start)
-						pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
-						       addr_start, addr_end-1, p_start, p_end-1, node_start);
-					addr_start = addr;
-					node_start = node;
-					p_start = p;
-				}
-
-				addr_end = addr + PMD_SIZE;
-				p_end = p + PMD_SIZE;
-
-				if (!IS_ALIGNED(addr, PMD_SIZE) ||
-				    !IS_ALIGNED(next, PMD_SIZE))
-					vmemmap_use_new_sub_pmd(addr, next);
-
-				continue;
-			} else if (altmap)
-				return -ENOMEM; /* no fallback */
-		} else if (pmd_large(*pmd)) {
-			vmemmap_verify((pte_t *)pmd, node, addr, next);
-			vmemmap_use_sub_pmd(addr, next);
-			continue;
-		}
-		if (vmemmap_populate_basepages(addr, next, node, NULL))
-			return -ENOMEM;
 	}
-	return 0;
+
+	addr_end = addr + PMD_SIZE;
+	p_end = p + PMD_SIZE;
+
+	if (!IS_ALIGNED(addr, PMD_SIZE) ||
+		!IS_ALIGNED(next, PMD_SIZE))
+		vmemmap_use_new_sub_pmd(addr, next);
+}
+
+int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
+				unsigned long addr, unsigned long next)
+{
+	int large = pmd_large(*pmd);
+
+	if (pmd_large(*pmd)) {
+		vmemmap_verify((pte_t *)pmd, node, addr, next);
+		vmemmap_use_sub_pmd(addr, next);
+	}
+
+	return large;
 }
 
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,

include/linux/mm.h

@@ -3373,8 +3373,14 @@ struct vmem_altmap;
 void *vmemmap_alloc_block_buf(unsigned long size, int node,
 			      struct vmem_altmap *altmap);
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
+void vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+		     unsigned long addr, unsigned long next);
+int vmemmap_check_pmd(pmd_t *pmd, int node,
+		      unsigned long addr, unsigned long next);
 int vmemmap_populate_basepages(unsigned long start, unsigned long end,
 			       int node, struct vmem_altmap *altmap);
+int vmemmap_populate_hugepages(unsigned long start, unsigned long end,
+			       int node, struct vmem_altmap *altmap);
 int vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap);
 void vmemmap_populate_print_last(void);

mm/sparse-vmemmap.c

@@ -295,6 +295,69 @@ int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
 	return vmemmap_populate_range(start, end, node, altmap, NULL);
 }
 
+void __weak __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+				      unsigned long addr, unsigned long next)
+{
+}
+
+int __weak __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
+				       unsigned long addr, unsigned long next)
+{
+	return 0;
+}
+
+int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
+					 int node, struct vmem_altmap *altmap)
+{
+	unsigned long addr;
+	unsigned long next;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	for (addr = start; addr < end; addr = next) {
+		next = pmd_addr_end(addr, end);
+
+		pgd = vmemmap_pgd_populate(addr, node);
+		if (!pgd)
+			return -ENOMEM;
+
+		p4d = vmemmap_p4d_populate(pgd, addr, node);
+		if (!p4d)
+			return -ENOMEM;
+
+		pud = vmemmap_pud_populate(p4d, addr, node);
+		if (!pud)
+			return -ENOMEM;
+
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(READ_ONCE(*pmd))) {
+			void *p;
+
+			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
+			if (p) {
+				vmemmap_set_pmd(pmd, p, node, addr, next);
+				continue;
+			} else if (altmap) {
+				/*
+				 * No fallback: In any case we care about, the
+				 * altmap should be reasonably sized and aligned
+				 * such that vmemmap_alloc_block_buf() will always
+				 * succeed. For consistency with the PTE case,
+				 * return an error here as failure could indicate
+				 * a configuration issue with the size of the altmap.
+				 */
+				return -ENOMEM;
+			}
+		} else if (vmemmap_check_pmd(pmd, node, addr, next))
+			continue;
+		if (vmemmap_populate_basepages(addr, next, node, altmap))
+			return -ENOMEM;
+	}
+	return 0;
+}
+
 /*
  * For compound pages bigger than section size (e.g. x86 1G compound
  * pages with 2M subsection size) fill the rest of sections as tail