[PATCH V8 2/2] arm64/mm: Enable memory hot remove

[Anshuman Khandual]

The arch code for hot-remove must tear down portions of the linear map and
vmemmap corresponding to memory being removed. In both cases the page
tables mapping these regions must be freed, and when sparse vmemmap is in
use the memory backing the vmemmap must also be freed.

This patch adds unmap_hotplug_range() and free_empty_tables() helpers which
can be used to tear down either region and calls it from vmemmap_free() and
___remove_pgd_mapping(). The sparse_vmap argument determines whether the
backing memory will be freed.

It makes two distinct passes over the kernel page table. In the first pass
with unmap_hotplug_range() it unmaps, invalidates applicable TLB cache and
frees backing memory if required (vmemmap) for each mapped leaf entry. In
the second pass with free_empty_tables() it looks for empty page table
sections whose page table page can be unmapped, TLB invalidated and freed.

While freeing intermediate level page table pages bail out if any of its
entries are still valid. This can happen for partially filled kernel page
table either from a previously attempted failed memory hot add or while
removing an address range which does not span the entire page table page
range.

The vmemmap region may share levels of table with the vmalloc region.
There can be conflicts between hot remove freeing page table pages with
a concurrent vmalloc() walking the kernel page table. This conflict can
not just be solved by taking the init_mm ptl because of existing locking
scheme in vmalloc(). So free_empty_tables() implements a floor and ceiling
method which is borrowed from user page table tear with free_pgd_range()
which skips freeing page table pages if intermediate address range is not
aligned or maximum floor-ceiling might not own the entire page table page.

While here update arch_add_memory() to handle __add_pages() failures by
just unmapping recently added kernel linear mapping. Now enable memory hot
remove on arm64 platforms by default with ARCH_ENABLE_MEMORY_HOTREMOVE.

This implementation is overall inspired from kernel page table tear down
procedure on X86 architecture and user page table tear down method.

Acked-by: Steve Capper <steve.capper@xxxxxxx>
Acked-by: David Hildenbrand <david@xxxxxxxxxx>
Signed-off-by: Anshuman Khandual <anshuman.khandual@xxxxxxx>
---
 arch/arm64/Kconfig              |   3 +
 arch/arm64/include/asm/memory.h |   1 +
 arch/arm64/mm/mmu.c             | 305 ++++++++++++++++++++++++++++++++++++++--
 3 files changed, 300 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 41a9b42..511249f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -274,6 +274,9 @@ config ZONE_DMA32
 config ARCH_ENABLE_MEMORY_HOTPLUG
 	def_bool y
 
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+	def_bool y
+
 config SMP
 	def_bool y
 
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index b61b50b..615dcd0 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -54,6 +54,7 @@
 #define MODULES_VADDR		(BPF_JIT_REGION_END)
 #define MODULES_VSIZE		(SZ_128M)
 #define VMEMMAP_START		(-VMEMMAP_SIZE - SZ_2M)
+#define VMEMMAP_END		(VMEMMAP_START + VMEMMAP_SIZE)
 #define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 60c929f..6178837 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -725,6 +725,277 @@ int kern_addr_valid(unsigned long addr)
 
 	return pfn_valid(pte_pfn(pte));
 }
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void free_hotplug_page_range(struct page *page, size_t size)
+{
+	WARN_ON(!page || PageReserved(page));
+	free_pages((unsigned long)page_address(page), get_order(size));
+}
+
+static void free_hotplug_pgtable_page(struct page *page)
+{
+	free_hotplug_page_range(page, PAGE_SIZE);
+}
+
+static bool pgtable_range_aligned(unsigned long start, unsigned long end,
+				  unsigned long floor, unsigned long ceiling,
+				  unsigned long mask)
+{
+	start &= mask;
+	if (start < floor)
+		return false;
+
+	if (ceiling) {
+		ceiling &= mask;
+		if (!ceiling)
+			return false;
+	}
+
+	if (end - 1 > ceiling - 1)
+		return false;
+	return true;
+}
+
+static void free_pte_table(pmd_t *pmdp, unsigned long addr, unsigned long end,
+			   unsigned long floor, unsigned long ceiling)
+{
+	struct page *page;
+	pte_t *ptep;
+	int i;
+
+	if (!pgtable_range_aligned(addr, end, floor, ceiling, PMD_MASK))
+		return;
+
+	ptep = pte_offset_kernel(pmdp, 0UL);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		if (!pte_none(READ_ONCE(ptep[i])))
+			return;
+	}
+
+	page = pmd_page(READ_ONCE(*pmdp));
+	pmd_clear(pmdp);
+	__flush_tlb_kernel_pgtable(addr);
+	free_hotplug_pgtable_page(page);
+}
+
+static void free_pmd_table(pud_t *pudp, unsigned long addr, unsigned long end,
+			   unsigned long floor, unsigned long ceiling)
+{
+	struct page *page;
+	pmd_t *pmdp;
+	int i;
+
+	if (CONFIG_PGTABLE_LEVELS <= 2)
+		return;
+
+	if (!pgtable_range_aligned(addr, end, floor, ceiling, PUD_MASK))
+		return;
+
+	pmdp = pmd_offset(pudp, 0UL);
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(READ_ONCE(pmdp[i])))
+			return;
+	}
+
+	page = pud_page(READ_ONCE(*pudp));
+	pud_clear(pudp);
+	__flush_tlb_kernel_pgtable(addr);
+	free_hotplug_pgtable_page(page);
+}
+
+static void free_pud_table(pgd_t *pgdp, unsigned long addr, unsigned  long end,
+			   unsigned long floor, unsigned long ceiling)
+{
+	struct page *page;
+	pud_t *pudp;
+	int i;
+
+	if (CONFIG_PGTABLE_LEVELS <= 3)
+		return;
+
+	if (!pgtable_range_aligned(addr, end, floor, ceiling, PGDIR_MASK))
+		return;
+
+	pudp = pud_offset(pgdp, 0UL);
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		if (!pud_none(READ_ONCE(pudp[i])))
+			return;
+	}
+
+	page = pgd_page(READ_ONCE(*pgdp));
+	pgd_clear(pgdp);
+	__flush_tlb_kernel_pgtable(addr);
+	free_hotplug_pgtable_page(page);
+}
+
+static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
+				    unsigned long end, bool sparse_vmap)
+{
+	struct page *page;
+	pte_t *ptep, pte;
+
+	do {
+		ptep = pte_offset_kernel(pmdp, addr);
+		pte = READ_ONCE(*ptep);
+		if (pte_none(pte))
+			continue;
+
+		WARN_ON(!pte_present(pte));
+		page = sparse_vmap ? pte_page(pte) : NULL;
+		pte_clear(&init_mm, addr, ptep);
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+		if (sparse_vmap)
+			free_hotplug_page_range(page, PAGE_SIZE);
+	} while (addr += PAGE_SIZE, addr < end);
+}
+
+static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
+				    unsigned long end, bool sparse_vmap)
+{
+	unsigned long next;
+	struct page *page;
+	pmd_t *pmdp, pmd;
+
+	do {
+		next = pmd_addr_end(addr, end);
+		pmdp = pmd_offset(pudp, addr);
+		pmd = READ_ONCE(*pmdp);
+		if (pmd_none(pmd))
+			continue;
+
+		WARN_ON(!pmd_present(pmd));
+		if (pmd_sect(pmd)) {
+			page = sparse_vmap ? pmd_page(pmd) : NULL;
+			pmd_clear(pmdp);
+			flush_tlb_kernel_range(addr, next);
+			if (sparse_vmap)
+				free_hotplug_page_range(page, PMD_SIZE);
+			continue;
+		}
+		WARN_ON(!pmd_table(pmd));
+		unmap_hotplug_pte_range(pmdp, addr, next, sparse_vmap);
+	} while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_pud_range(pgd_t *pgdp, unsigned long addr,
+				    unsigned long end, bool sparse_vmap)
+{
+	unsigned long next;
+	struct page *page;
+	pud_t *pudp, pud;
+
+	do {
+		next = pud_addr_end(addr, end);
+		pudp = pud_offset(pgdp, addr);
+		pud = READ_ONCE(*pudp);
+		if (pud_none(pud))
+			continue;
+
+		WARN_ON(!pud_present(pud));
+		if (pud_sect(pud)) {
+			page = sparse_vmap ? pud_page(pud) : NULL;
+			pud_clear(pudp);
+			flush_tlb_kernel_range(addr, next);
+			if (sparse_vmap)
+				free_hotplug_page_range(page, PUD_SIZE);
+			continue;
+		}
+		WARN_ON(!pud_table(pud));
+		unmap_hotplug_pmd_range(pudp, addr, next, sparse_vmap);
+	} while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_range(unsigned long addr, unsigned long end,
+				bool sparse_vmap)
+{
+	unsigned long next;
+	pgd_t *pgdp, pgd;
+
+	do {
+		next = pgd_addr_end(addr, end);
+		pgdp = pgd_offset_k(addr);
+		pgd = READ_ONCE(*pgdp);
+		if (pgd_none(pgd))
+			continue;
+
+		WARN_ON(!pgd_present(pgd));
+		unmap_hotplug_pud_range(pgdp, addr, next, sparse_vmap);
+	} while (addr = next, addr < end);
+}
+
+static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
+				 unsigned long end)
+{
+	pte_t *ptep, pte;
+
+	do {
+		ptep = pte_offset_kernel(pmdp, addr);
+		pte = READ_ONCE(*ptep);
+		WARN_ON(!pte_none(pte));
+	} while (addr += PAGE_SIZE, addr < end);
+}
+
+static void free_empty_pmd_table(pud_t *pudp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
+{
+	unsigned long next;
+	pmd_t *pmdp, pmd;
+
+	do {
+		next = pmd_addr_end(addr, end);
+		pmdp = pmd_offset(pudp, addr);
+		pmd = READ_ONCE(*pmdp);
+		if (pmd_none(pmd))
+			continue;
+
+		WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd));
+		free_empty_pte_table(pmdp, addr, next);
+		free_pte_table(pmdp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
+}
+
+static void free_empty_pud_table(pgd_t *pgdp, unsigned long addr,
+				 unsigned long end, unsigned long floor,
+				 unsigned long ceiling)
+{
+	unsigned long next;
+	pud_t *pudp, pud;
+
+	do {
+		next = pud_addr_end(addr, end);
+		pudp = pud_offset(pgdp, addr);
+		pud = READ_ONCE(*pudp);
+		if (pud_none(pud))
+			continue;
+
+		WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud));
+		free_empty_pmd_table(pudp, addr, next, floor, ceiling);
+		free_pmd_table(pudp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
+}
+
+static void free_empty_tables(unsigned long addr, unsigned long end,
+				unsigned long floor, unsigned long ceiling)
+{
+	unsigned long next;
+	pgd_t *pgdp, pgd;
+
+	do {
+		next = pgd_addr_end(addr, end);
+		pgdp = pgd_offset_k(addr);
+		pgd = READ_ONCE(*pgdp);
+		if (pgd_none(pgd))
+			continue;
+
+		WARN_ON(!pgd_present(pgd));
+		free_empty_pud_table(pgdp, addr, next, floor, ceiling);
+		free_pud_table(pgdp, addr, next, floor, ceiling);
+	} while (addr = next, addr < end);
+}
+#endif
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #if !ARM64_SWAPPER_USES_SECTION_MAPS
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
@@ -772,6 +1043,12 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap)
 {
+#ifdef CONFIG_MEMORY_HOTPLUG
+	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+
+	unmap_hotplug_range(start, end, true);
+	free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
+#endif
 }
 #endif	/* CONFIG_SPARSEMEM_VMEMMAP */
 
@@ -1050,10 +1327,21 @@ int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
+{
+	unsigned long end = start + size;
+
+	WARN_ON(pgdir != init_mm.pgd);
+	WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END));
+
+	unmap_hotplug_range(start, end, false);
+	free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
+}
+
 int arch_add_memory(int nid, u64 start, u64 size,
 			struct mhp_restrictions *restrictions)
 {
-	int flags = 0;
+	int ret, flags = 0;
 
 	if (rodata_full || debug_pagealloc_enabled())
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
@@ -1061,9 +1349,14 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
 			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
 
-	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
+	ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
 			   restrictions);
+	if (ret)
+		__remove_pgd_mapping(swapper_pg_dir,
+				     __phys_to_virt(start), size);
+	return ret;
 }
+
 void arch_remove_memory(int nid, u64 start, u64 size,
 			struct vmem_altmap *altmap)
 {
@@ -1071,14 +1364,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct zone *zone;
 
-	/*
-	 * FIXME: Cleanup page tables (also in arch_add_memory() in case
-	 * adding fails). Until then, this function should only be used
-	 * during memory hotplug (adding memory), not for memory
-	 * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
-	 * unlocked yet.
-	 */
 	zone = page_zone(pfn_to_page(start_pfn));
 	__remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
 }
 #endif
-- 
2.7.4