[4/7] riscv: mm: Add memory hot add/remove support

Commit Message

Björn Töpel May 12, 2023, 2:57 p.m. UTC

From: Björn Töpel <[e-mail]>

From an arch perspective, a couple of callbacks needs to be
implemented to support hotplugging:

arch_add_memory() This callback is responsible for updating the
linear/direct map, and call into the memory hotplugging generic code
via __add_pages().

arch_remove_memory() In this callback the linear/direct map is tore
down.

vmemmap_free() The function tears down the vmemmap mappings (if
CONFIG_SPARSEMEM_VMEMMAP is in-use), and also deallocates the backing
vmemmap pages. Note that for persistent memory, an alternative
allocator for the backing pages can be used -- the vmem_altmap. This
means that when the backing pages are cleared, extra care is needed so
that the correct deallocation method is used. Note that RISC-V
populates the vmemmap using vmemmap_populate_basepages(), so currently
no hugepages are used for the backing store.

The page table unmap/teardown functions are heavily based (copied!)
from the x86 tree. The same remove_pgd_mapping() is used in both
vmemmap_free() and arch_remove_memory(), but in the latter function
the backing pages are not removed.

Signed-off-by: Björn Töpel <[e-mail]>
---
 arch/riscv/mm/init.c | 233 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 233 insertions(+)

Patch

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index aea8ccb3f4ae..a468708d1e1c 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1444,3 +1444,236 @@  int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	return vmemmap_populate_basepages(start, end, node, NULL);
 }
 #endif
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
+{
+	pte_t *pte;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte = pte_start + i;
+		if (!pte_none(*pte))
+			return;
+	}
+
+	free_pages((unsigned long)page_address(pmd_page(*pmd)), 0);
+	pmd_clear(pmd);
+}
+
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
+{
+	pmd_t *pmd;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd = pmd_start + i;
+		if (!pmd_none(*pmd))
+			return;
+	}
+
+	free_pages((unsigned long)page_address(pud_page(*pud)), 0);
+	pud_clear(pud);
+}
+
+static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
+{
+	pud_t *pud;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		pud = pud_start + i;
+		if (!pud_none(*pud))
+			return;
+	}
+
+	free_pages((unsigned long)page_address(p4d_page(*p4d)), 0);
+	p4d_clear(p4d);
+}
+
+static void __meminit free_vmemmap_storage(struct page *page, size_t size,
+					   struct vmem_altmap *altmap)
+{
+	if (altmap)
+		vmem_altmap_free(altmap, size >> PAGE_SHIFT);
+	else
+		free_pages((unsigned long)page_address(page), get_order(size));
+}
+
+static void __meminit remove_pte_mapping(pte_t *pte_base, unsigned long addr, unsigned long end,
+					 bool is_vmemmap, struct vmem_altmap *altmap)
+{
+	unsigned long next;
+	pte_t *ptep, pte;
+
+	for (; addr < end; addr = next) {
+		next = (addr + PAGE_SIZE) & PAGE_MASK;
+		if (next > end)
+			next = end;
+
+		ptep = pte_base + pte_index(addr);
+		pte = READ_ONCE(*ptep);
+
+		if (!pte_present(*ptep))
+			continue;
+
+		pte_clear(&init_mm, addr, ptep);
+		if (is_vmemmap)
+			free_vmemmap_storage(pte_page(pte), PAGE_SIZE, altmap);
+	}
+}
+
+static void __meminit remove_pmd_mapping(pmd_t *pmd_base, unsigned long addr, unsigned long end,
+					 bool is_vmemmap, struct vmem_altmap *altmap)
+{
+	unsigned long next;
+	pte_t *pte_base;
+	pmd_t *pmdp, pmd;
+
+	for (; addr < end; addr = next) {
+		next = pmd_addr_end(addr, end);
+		pmdp = pmd_base + pmd_index(addr);
+		pmd = READ_ONCE(*pmdp);
+
+		if (!pmd_present(pmd))
+			continue;
+
+		if (pmd_leaf(pmd)) {
+			pmd_clear(pmdp);
+			if (is_vmemmap)
+				free_vmemmap_storage(pmd_page(pmd), PMD_SIZE, altmap);
+			continue;
+		}
+
+		pte_base = (pte_t *)pmd_page_vaddr(*pmdp);
+		remove_pte_mapping(pte_base, addr, next, is_vmemmap, altmap);
+		free_pte_table(pte_base, pmdp);
+	}
+}
+
+static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, unsigned long end,
+					 bool is_vmemmap, struct vmem_altmap *altmap)
+{
+	unsigned long next;
+	pud_t *pudp, pud;
+	pmd_t *pmd_base;
+
+	for (; addr < end; addr = next) {
+		next = pud_addr_end(addr, end);
+		pudp = pud_base + pud_index(addr);
+		pud = READ_ONCE(*pudp);
+
+		if (!pud_present(pud))
+			continue;
+
+		if (pud_leaf(pud)) {
+			if (pgtable_l4_enabled) {
+				pud_clear(pudp);
+				if (is_vmemmap)
+					free_vmemmap_storage(pud_page(pud), PUD_SIZE, altmap);
+			}
+			continue;
+		}
+
+		pmd_base = pmd_offset(pudp, 0);
+		remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap);
+
+		if (pgtable_l4_enabled)
+			free_pmd_table(pmd_base, pudp);
+	}
+}
+
+static void __meminit remove_p4d_mapping(p4d_t *p4d_base, unsigned long addr, unsigned long end,
+					 bool is_vmemmap, struct vmem_altmap *altmap)
+{
+	unsigned long next;
+	p4d_t *p4dp, p4d;
+	pud_t *pud_base;
+
+	for (; addr < end; addr = next) {
+		next = p4d_addr_end(addr, end);
+		p4dp = p4d_base + p4d_index(addr);
+		p4d = READ_ONCE(*p4dp);
+
+		if (!p4d_present(p4d))
+			continue;
+
+		if (p4d_leaf(p4d)) {
+			if (pgtable_l5_enabled) {
+				p4d_clear(p4dp);
+				if (is_vmemmap)
+					free_vmemmap_storage(p4d_page(p4d), P4D_SIZE, altmap);
+			}
+			continue;
+		}
+
+		pud_base = pud_offset(p4dp, 0);
+		remove_pud_mapping(pud_base, addr, next, is_vmemmap, altmap);
+
+		if (pgtable_l5_enabled)
+			free_pud_table(pud_base, p4dp);
+	}
+}
+
+static void __meminit remove_pgd_mapping(unsigned long va, unsigned long end, bool is_vmemmap,
+					 struct vmem_altmap *altmap)
+{
+	unsigned long addr, next;
+	p4d_t *p4d_base;
+	pgd_t *pgd;
+
+	for (addr = va; addr < end; addr = next) {
+		next = pgd_addr_end(addr, end);
+		pgd = pgd_offset_k(addr);
+
+		if (!pgd_present(*pgd))
+			continue;
+
+		if (pgd_leaf(*pgd))
+			continue;
+
+		p4d_base = p4d_offset(pgd, 0);
+		remove_p4d_mapping(p4d_base, addr, next, is_vmemmap, altmap);
+	}
+
+	flush_tlb_all();
+}
+
+static void __meminit remove_linear_mapping(phys_addr_t start, u64 size)
+{
+	unsigned long va = (unsigned long)__va(start);
+	unsigned long end = (unsigned long)__va(start + size);
+
+	remove_pgd_mapping(va, end, false, NULL);
+}
+
+int __ref arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params)
+{
+	int ret;
+
+	create_linear_mapping_range(start, start + size, params);
+	flush_tlb_all();
+	ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, params);
+	if (ret) {
+		remove_linear_mapping(start, size);
+		return ret;
+	}
+
+	max_pfn = PFN_UP(start + size);
+	max_low_pfn = max_pfn;
+	return 0;
+}
+
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+{
+	__remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap);
+	remove_linear_mapping(start, size);
+}
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+void __ref vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap)
+{
+	remove_pgd_mapping(start, end, true, altmap);
+}
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+#endif /* CONFIG_MEMORY_HOTPLUG */