[PATCH v4 1/6] mm, x86: Add ARCH_HAS_ZONE_DEVICE to Kconfig

@@ -61,6 +61,7 @@ config X86
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_ZONE_DEVICE		if X86_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT

@@ -668,12 +668,16 @@ config IDLE_PAGE_TRACKING
 
 	  See Documentation/vm/idle_page_tracking.txt for more details.
 
+# arch_add_memory() comprehends device memory
+config ARCH_HAS_ZONE_DEVICE
+	bool
+
 config ZONE_DEVICE
 	bool "Device memory (pmem, etc...) hotplug support"
 	depends on MEMORY_HOTPLUG
 	depends on MEMORY_HOTREMOVE
 	depends on SPARSEMEM_VMEMMAP
-	depends on X86_64 #arch_add_memory() comprehends device memory
+	depends on ARCH_HAS_ZONE_DEVICE
 
 	help
 	  Device memory hotplug support allows for establishing pmem,

@@ -234,13 +234,15 @@ static unsigned long vmemmap_list_free(unsigned long start)
 void __ref vmemmap_free(unsigned long start, unsigned long end)
 {
 	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+	unsigned long page_order = get_order(page_size);
 
 	start = _ALIGN_DOWN(start, page_size);
 
 	pr_debug("vmemmap_free %lx...%lx\n", start, end);
 
 	for (; start < end; start += page_size) {
-		unsigned long addr;
+		unsigned long nr_pages, addr;
+		struct page *page;
 
 		/*
 		 * the section has already be marked as invalid, so

@@ -251,29 +253,29 @@ void __ref vmemmap_free(unsigned long start, unsigned long end)
 			continue;
 
 		addr = vmemmap_list_free(start);
-		if (addr) {
-			struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
-
-			if (PageReserved(page)) {
-				/* allocated from bootmem */
-				if (page_size < PAGE_SIZE) {
-					/*
-					 * this shouldn't happen, but if it is
-					 * the case, leave the memory there
-					 */
-					WARN_ON_ONCE(1);
-				} else {
-					unsigned int nr_pages =
-						1 << get_order(page_size);
-					while (nr_pages--)
-						free_reserved_page(page++);
-				}
-			} else
-				free_pages((unsigned long)(__va(addr)),
-							get_order(page_size));
-
-			vmemmap_remove_mapping(start, page_size);
+		if (!addr)
+			continue;
+
+		page = pfn_to_page(addr >> PAGE_SHIFT);
+		nr_pages = 1 << page_order;
+
+		if (PageReserved(page)) {
+			/* allocated from bootmem */
+			if (page_size < PAGE_SIZE) {
+				/*
+				 * this shouldn't happen, but if it is
+				 * the case, leave the memory there
+				 */
+				WARN_ON_ONCE(1);
+			} else {
+				while (nr_pages--)
+					free_reserved_page(page++);
+			}
+		} else {
+			free_pages((unsigned long)(__va(addr)), page_order);
 		}
+
+		vmemmap_remove_mapping(start, page_size);
 	}
 }
 #endif

@@ -44,6 +44,7 @@
 #include <linux/slab.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
+#include <linux/memremap.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>

@@ -171,13 +172,17 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
 	pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
 
 	for (; start < end; start += page_size) {
+		struct vmem_altmap *altmap;
 		void *p;
 		int rc;
 
 		if (vmemmap_populated(start, page_size))
 			continue;
 
-		p = vmemmap_alloc_block(page_size, node);
+		/* altmap lookups only work at section boundaries */
+		altmap = to_vmem_altmap(SECTION_ALIGN_DOWN(start));
+
+		p =  __vmemmap_alloc_block_buf(page_size, node, altmap);
 		if (!p)
 			return -ENOMEM;
 

@@ -242,6 +247,8 @@ void __ref vmemmap_free(unsigned long start, unsigned long end)
 
 	for (; start < end; start += page_size) {
 		unsigned long nr_pages, addr;
+		struct vmem_altmap *altmap;
+		struct page *section_base;
 		struct page *page;
 
 		/*

@@ -257,9 +264,13 @@ void __ref vmemmap_free(unsigned long start, unsigned long end)
 			continue;
 
 		page = pfn_to_page(addr >> PAGE_SHIFT);
+		section_base = pfn_to_page(vmemmap_section_start(start));
 		nr_pages = 1 << page_order;
 
-		if (PageReserved(page)) {
+		altmap = to_vmem_altmap((unsigned long) section_base);
+		if (altmap) {
+			vmem_altmap_free(altmap, nr_pages);
+		} else if (PageReserved(page)) {
 			/* allocated from bootmem */
 			if (page_size < PAGE_SIZE) {
 				/*

@@ -36,6 +36,7 @@
 #include <linux/hugetlb.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/memremap.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>

@@ -151,11 +152,20 @@ int arch_remove_memory(u64 start, u64 size)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct zone *zone;
+	struct vmem_altmap *altmap;
+	struct page *page;
 	int ret;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-	ret = __remove_pages(zone, start_pfn, nr_pages);
+	/*
+	 * If we have an altmap then we need to skip over any reserved PFNs
+	 * when querying the zone.
+	 */
+	page = pfn_to_page(start_pfn);
+	altmap = to_vmem_altmap((unsigned long) page);
+	if (altmap)
+		page += vmem_altmap_offset(altmap);
+
+	ret = __remove_pages(page_zone(page), start_pfn, nr_pages);
 	if (ret)
 		return ret;
 

@@ -5,6 +5,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/mmdebug.h>
+#include <linux/bug.h>
 #endif
 
 /*

@@ -79,6 +80,9 @@
 
 #define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
 #define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
+#define _PAGE_DEVMAP		_RPAGE_SW1 /* software: ZONE_DEVICE page */
+#define __HAVE_ARCH_PTE_DEVMAP
+
 /*
  * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
  * Instead of fixing all of them, add an alternate define which

@@ -599,6 +603,16 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
+static inline pte_t pte_mkdevmap(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP);
+}
+
+static inline int pte_devmap(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DEVMAP));
+}
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	/* FIXME!! check whether this need to be a conditional */

@@ -1146,6 +1160,37 @@ static inline bool arch_needs_pgtable_deposit(void)
 	return true;
 }
 
+
+static inline pmd_t pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+}
+
+static inline int pmd_devmap(pmd_t pmd)
+{
+	return pte_devmap(pmd_pte(pmd));
+}
+
+static inline int pud_devmap(pud_t pud)
+{
+	return 0;
+}
+
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline const int pud_pfn(pud_t pud)
+{
+	/*
+	 * Currently all calls to pud_pfn() are gated around a pud_devmap()
+	 * check so this should never be used. If it grows another user we
+	 * want to know about it.
+	 */
+	BUILD_BUG();
+	return 0;
+}
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */

@@ -252,7 +252,7 @@ static inline int radix__pgd_bad(pgd_t pgd)
 
 static inline int radix__pmd_trans_huge(pmd_t pmd)
 {
-	return !!(pmd_val(pmd) & _PAGE_PTE);
+	return (pmd_val(pmd) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE;
 }
 
 static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)

@@ -945,7 +945,7 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 			if (pmd_none(pmd))
 				return NULL;
 
-			if (pmd_trans_huge(pmd)) {
+			if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
 				if (is_thp)
 					*is_thp = true;
 				ret_pte = (pte_t *) pmdp;

@@ -32,7 +32,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 {
 	int changed;
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!pmd_trans_huge(*pmdp));
+	WARN_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
 	assert_spin_locked(&vma->vm_mm->page_table_lock);
 #endif
 	changed = !pmd_same(*(pmdp), entry);

@@ -59,7 +59,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 #ifdef CONFIG_DEBUG_VM
 	WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
 	assert_spin_locked(&mm->page_table_lock);
-	WARN_ON(!pmd_trans_huge(pmd));
+	WARN_ON(!(pmd_trans_huge(pmd) || pmd_devmap(pmd)));
 #endif
 	trace_hugepage_set_pmd(addr, pmd_val(pmd));
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));

@@ -109,7 +109,7 @@ unsigned long hash__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr
 	unsigned long old;
 
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!pmd_trans_huge(*pmdp));
+	WARN_ON(!hash__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
 	assert_spin_locked(&mm->page_table_lock);
 #endif
 

@@ -141,6 +141,7 @@ pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addres
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(pmd_trans_huge(*pmdp));
+	VM_BUG_ON(pmd_devmap(*pmdp));
 
 	pmd = *pmdp;
 	pmd_clear(pmdp);

@@ -221,6 +222,7 @@ void hash__pmdp_huge_split_prepare(struct vm_area_struct *vma,
 {
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);
+	VM_BUG_ON(pmd_devmap(*pmdp));
 
 	/*
 	 * We can't mark the pmd none here, because that will cause a race

@@ -691,7 +691,7 @@ unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long add
 	unsigned long old;
 
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(!radix__pmd_trans_huge(*pmdp));
+	WARN_ON(!radix__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
 	assert_spin_locked(&mm->page_table_lock);
 #endif
 

@@ -709,6 +709,7 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 	VM_BUG_ON(radix__pmd_trans_huge(*pmdp));
+	VM_BUG_ON(pmd_devmap(*pmdp));
 	/*
 	 * khugepaged calls this for normal pmd
 	 */

@@ -323,7 +323,7 @@ struct page *pud_page(pud_t pud)
  */
 struct page *pmd_page(pmd_t pmd)
 {
-	if (pmd_trans_huge(pmd) || pmd_huge(pmd))
+	if (pmd_trans_huge(pmd) || pmd_huge(pmd) || pmd_devmap(pmd))
 		return pte_page(pmd_pte(pmd));
 	return virt_to_page(pmd_page_vaddr(pmd));
 }

@@ -407,6 +407,38 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	tlbie(vpn, psize, psize, ssize, 0);
 }
 
+/*
+ * Remove a bolted kernel entry. Memory hotplug uses this.
+ *
+ * No need to lock here because we should be the only user.
+ */
+static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
+{
+	unsigned long vpn;
+	unsigned long vsid;
+	long slot;
+	struct hash_pte *hptep;
+
+	vsid = get_kernel_vsid(ea, ssize);
+	vpn = hpt_vpn(ea, vsid, ssize);
+
+	slot = native_hpte_find(vpn, psize, ssize);
+	if (slot == -1)
+		return -ENOENT;
+
+	hptep = htab_address + slot;
+
+	VM_WARN_ON(!(be64_to_cpu(hptep->v) & HPTE_V_BOLTED));
+
+	/* Invalidate the hpte */
+	hptep->v = 0;
+
+	/* Invalidate the TLB */
+	tlbie(vpn, psize, psize, ssize, 0);
+	return 0;
+}
+
+
 static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 				   int bpsize, int apsize, int ssize, int local)
 {

@@ -725,6 +757,7 @@ void __init hpte_init_native(void)
 	mmu_hash_ops.hpte_invalidate	= native_hpte_invalidate;
 	mmu_hash_ops.hpte_updatepp	= native_hpte_updatepp;
 	mmu_hash_ops.hpte_updateboltedpp = native_hpte_updateboltedpp;
+	mmu_hash_ops.hpte_removebolted = native_hpte_removebolted;
 	mmu_hash_ops.hpte_insert	= native_hpte_insert;
 	mmu_hash_ops.hpte_remove	= native_hpte_remove;
 	mmu_hash_ops.hpte_clear_all	= native_hpte_clear;

@@ -131,6 +131,7 @@ config PPC
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAS_ZONE_DEVICE		if PPC_BOOK3S_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO