1 files changed, 173 insertions, 45 deletions

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 200aef686722..46ae542118c0 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -27,9 +27,9 @@
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
+
 #include <asm/dma.h>
 #include <asm/pgalloc.h>
-#include <asm/pgtable.h>
 
 /*
  * Allocate a block of memory to be used to back the virtual memory map
@@ -70,11 +70,19 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 				__pa(MAX_DMA_ADDRESS));
 }
 
+static void * __meminit altmap_alloc_block_buf(unsigned long size,
+					       struct vmem_altmap *altmap);
+
 /* need to make sure size is all the same during early stage */
-void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node)
+void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node,
+					 struct vmem_altmap *altmap)
 {
-	void *ptr = sparse_buffer_alloc(size);
+	void *ptr;
+
+	if (altmap)
+		return altmap_alloc_block_buf(size, altmap);
 
+	ptr = sparse_buffer_alloc(size);
 	if (!ptr)
 		ptr = vmemmap_alloc_block(size, node);
 	return ptr;
@@ -95,15 +103,8 @@ static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
 	return 0;
 }
 
-/**
- * altmap_alloc_block_buf - allocate pages from the device page map
- * @altmap:	device page map
- * @size:	size (in bytes) of the allocation
- *
- * Allocations are aligned to the size of the request.
- */
-void * __meminit altmap_alloc_block_buf(unsigned long size,
-		struct vmem_altmap *altmap)
+static void * __meminit altmap_alloc_block_buf(unsigned long size,
+					       struct vmem_altmap *altmap)
 {
 	unsigned long pfn, nr_pfns, nr_align;
 
@@ -136,18 +137,36 @@ void __meminit vmemmap_verify(pte_t *pte, int node,
 	int actual_node = early_pfn_to_nid(pfn);
 
 	if (node_distance(actual_node, node) > LOCAL_DISTANCE)
-		pr_warn("[%lx-%lx] potential offnode page_structs\n",
+		pr_warn_once("[%lx-%lx] potential offnode page_structs\n",
 			start, end - 1);
 }
 
-pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
+pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
+				       struct vmem_altmap *altmap,
+				       struct page *reuse)
 {
 	pte_t *pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte)) {
 		pte_t entry;
-		void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
-		if (!p)
-			return NULL;
+		void *p;
+
+		if (!reuse) {
+			p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
+			if (!p)
+				return NULL;
+		} else {
+			/*
+			 * When a PTE/PMD entry is freed from the init_mm
+			 * there's a free_pages() call to this page allocated
+			 * above. Thus this get_page() is paired with the
+			 * put_page_testzero() on the freeing path.
+			 * This can only called by certain ZONE_DEVICE path,
+			 * and through vmemmap_populate_compound_pages() when
+			 * slab is available.
+			 */
+			get_page(reuse);
+			p = page_to_virt(reuse);
+		}
 		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
 	}
@@ -213,57 +232,166 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 	return pgd;
 }
 
-int __meminit vmemmap_populate_basepages(unsigned long start,
-					 unsigned long end, int node)
+static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
+					      struct vmem_altmap *altmap,
+					      struct page *reuse)
 {
-	unsigned long addr = start;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
+	pgd = vmemmap_pgd_populate(addr, node);
+	if (!pgd)
+		return NULL;
+	p4d = vmemmap_p4d_populate(pgd, addr, node);
+	if (!p4d)
+		return NULL;
+	pud = vmemmap_pud_populate(p4d, addr, node);
+	if (!pud)
+		return NULL;
+	pmd = vmemmap_pmd_populate(pud, addr, node);
+	if (!pmd)
+		return NULL;
+	pte = vmemmap_pte_populate(pmd, addr, node, altmap, reuse);
+	if (!pte)
+		return NULL;
+	vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+	return pte;
+}
+
+static int __meminit vmemmap_populate_range(unsigned long start,
+					    unsigned long end, int node,
+					    struct vmem_altmap *altmap,
+					    struct page *reuse)
+{
+	unsigned long addr = start;
+	pte_t *pte;
+
 	for (; addr < end; addr += PAGE_SIZE) {
-		pgd = vmemmap_pgd_populate(addr, node);
-		if (!pgd)
-			return -ENOMEM;
-		p4d = vmemmap_p4d_populate(pgd, addr, node);
-		if (!p4d)
+		pte = vmemmap_populate_address(addr, node, altmap, reuse);
+		if (!pte)
 			return -ENOMEM;
-		pud = vmemmap_pud_populate(p4d, addr, node);
-		if (!pud)
+	}
+
+	return 0;
+}
+
+int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
+					 int node, struct vmem_altmap *altmap)
+{
+	return vmemmap_populate_range(start, end, node, altmap, NULL);
+}
+
+/*
+ * For compound pages bigger than section size (e.g. x86 1G compound
+ * pages with 2M subsection size) fill the rest of sections as tail
+ * pages.
+ *
+ * Note that memremap_pages() resets @nr_range value and will increment
+ * it after each range successful onlining. Thus the value or @nr_range
+ * at section memmap populate corresponds to the in-progress range
+ * being onlined here.
+ */
+static bool __meminit reuse_compound_section(unsigned long start_pfn,
+					     struct dev_pagemap *pgmap)
+{
+	unsigned long nr_pages = pgmap_vmemmap_nr(pgmap);
+	unsigned long offset = start_pfn -
+		PHYS_PFN(pgmap->ranges[pgmap->nr_range].start);
+
+	return !IS_ALIGNED(offset, nr_pages) && nr_pages > PAGES_PER_SUBSECTION;
+}
+
+static pte_t * __meminit compound_section_tail_page(unsigned long addr)
+{
+	pte_t *pte;
+
+	addr -= PAGE_SIZE;
+
+	/*
+	 * Assuming sections are populated sequentially, the previous section's
+	 * page data can be reused.
+	 */
+	pte = pte_offset_kernel(pmd_off_k(addr), addr);
+	if (!pte)
+		return NULL;
+
+	return pte;
+}
+
+static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
+						     unsigned long start,
+						     unsigned long end, int node,
+						     struct dev_pagemap *pgmap)
+{
+	unsigned long size, addr;
+	pte_t *pte;
+	int rc;
+
+	if (reuse_compound_section(start_pfn, pgmap)) {
+		pte = compound_section_tail_page(start);
+		if (!pte)
 			return -ENOMEM;
-		pmd = vmemmap_pmd_populate(pud, addr, node);
-		if (!pmd)
+
+		/*
+		 * Reuse the page that was populated in the prior iteration
+		 * with just tail struct pages.
+		 */
+		return vmemmap_populate_range(start, end, node, NULL,
+					      pte_page(*pte));
+	}
+
+	size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page));
+	for (addr = start; addr < end; addr += size) {
+		unsigned long next, last = addr + size;
+
+		/* Populate the head page vmemmap page */
+		pte = vmemmap_populate_address(addr, node, NULL, NULL);
+		if (!pte)
 			return -ENOMEM;
-		pte = vmemmap_pte_populate(pmd, addr, node);
+
+		/* Populate the tail pages vmemmap page */
+		next = addr + PAGE_SIZE;
+		pte = vmemmap_populate_address(next, node, NULL, NULL);
 		if (!pte)
 			return -ENOMEM;
-		vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
+
+		/*
+		 * Reuse the previous page for the rest of tail pages
+		 * See layout diagram in Documentation/mm/vmemmap_dedup.rst
+		 */
+		next += PAGE_SIZE;
+		rc = vmemmap_populate_range(next, last, node, NULL,
+					    pte_page(*pte));
+		if (rc)
+			return -ENOMEM;
 	}
 
 	return 0;
 }
 
 struct page * __meminit __populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
-	unsigned long start;
-	unsigned long end;
+	unsigned long start = (unsigned long) pfn_to_page(pfn);
+	unsigned long end = start + nr_pages * sizeof(struct page);
+	int r;
 
-	/*
-	 * The minimum granularity of memmap extensions is
-	 * PAGES_PER_SUBSECTION as allocations are tracked in the
-	 * 'subsection_map' bitmap of the section.
-	 */
-	end = ALIGN(pfn + nr_pages, PAGES_PER_SUBSECTION);
-	pfn &= PAGE_SUBSECTION_MASK;
-	nr_pages = end - pfn;
+	if (WARN_ON_ONCE(!IS_ALIGNED(pfn, PAGES_PER_SUBSECTION) ||
+		!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
+		return NULL;
 
-	start = (unsigned long) pfn_to_page(pfn);
-	end = start + nr_pages * sizeof(struct page);
+	if (is_power_of_2(sizeof(struct page)) &&
+	    pgmap && pgmap_vmemmap_nr(pgmap) > 1 && !altmap)
+		r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
+	else
+		r = vmemmap_populate(start, end, nid, altmap);
 
-	if (vmemmap_populate(start, end, nid, altmap))
+	if (r < 0)
 		return NULL;
 
 	return pfn_to_page(pfn);