1 files changed, 37 insertions, 29 deletions

diff --git a/mm/sparse.c b/mm/sparse.c
index 72f010d9bff5..c184b69460b7 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -11,6 +11,8 @@
 #include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 
 #include "internal.h"
 #include <asm/dma.h>
@@ -196,16 +198,6 @@ static void section_mark_present(struct mem_section *ms)
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 }
 
-static inline unsigned long next_present_section_nr(unsigned long section_nr)
-{
-	do {
-		section_nr++;
-		if (present_section_nr(section_nr))
-			return section_nr;
-	} while ((section_nr <= __highest_present_section_nr));
-
-	return -1;
-}
 #define for_each_present_section_nr(start, section_nr)		\
 	for (section_nr = next_present_section_nr(start-1);	\
 	     ((section_nr != -1) &&				\
@@ -217,7 +209,7 @@ static inline unsigned long first_present_section_nr(void)
 	return next_present_section_nr(-1);
 }
 
-void subsection_mask_set(unsigned long *map, unsigned long pfn,
+static void subsection_mask_set(unsigned long *map, unsigned long pfn,
 		unsigned long nr_pages)
 {
 	int idx = subsection_map_index(pfn);
@@ -456,8 +448,7 @@ struct page __init *__populate_section_memmap(unsigned long pfn,
 	if (map)
 		return map;
 
-	map = memblock_alloc_try_nid(size,
-					  PAGE_SIZE, addr,
+	map = memblock_alloc_try_nid_raw(size, size, addr,
 					  MEMBLOCK_ALLOC_ACCESSIBLE, nid);
 	if (!map)
 		panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa\n",
@@ -470,14 +461,23 @@ struct page __init *__populate_section_memmap(unsigned long pfn,
 static void *sparsemap_buf __meminitdata;
 static void *sparsemap_buf_end __meminitdata;
 
+static inline void __meminit sparse_buffer_free(unsigned long size)
+{
+	WARN_ON(!sparsemap_buf || size == 0);
+	memblock_free_early(__pa(sparsemap_buf), size);
+}
+
 static void __init sparse_buffer_init(unsigned long size, int nid)
 {
 	phys_addr_t addr = __pa(MAX_DMA_ADDRESS);
 	WARN_ON(sparsemap_buf);	/* forgot to call sparse_buffer_fini()? */
-	sparsemap_buf =
-		memblock_alloc_try_nid_raw(size, PAGE_SIZE,
-						addr,
-						MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+	/*
+	 * Pre-allocated buffer is mainly used by __populate_section_memmap
+	 * and we want it to be properly aligned to the section size - this is
+	 * especially the case for VMEMMAP which maps memmap to PMDs
+	 */
+	sparsemap_buf = memblock_alloc_exact_nid_raw(size, section_map_size(),
+					addr, MEMBLOCK_ALLOC_ACCESSIBLE, nid);
 	sparsemap_buf_end = sparsemap_buf + size;
 }
 
@@ -486,7 +486,7 @@ static void __init sparse_buffer_fini(void)
 	unsigned long size = sparsemap_buf_end - sparsemap_buf;
 
 	if (sparsemap_buf && size > 0)
-		memblock_free_early(__pa(sparsemap_buf), size);
+		sparse_buffer_free(size);
 	sparsemap_buf = NULL;
 }
 
@@ -495,11 +495,15 @@ void * __meminit sparse_buffer_alloc(unsigned long size)
 	void *ptr = NULL;
 
 	if (sparsemap_buf) {
-		ptr = PTR_ALIGN(sparsemap_buf, size);
+		ptr = (void *) roundup((unsigned long)sparsemap_buf, size);
 		if (ptr + size > sparsemap_buf_end)
 			ptr = NULL;
-		else
+		else {
+			/* Free redundant aligned space */
+			if ((unsigned long)(ptr - sparsemap_buf) > 0)
+				sparse_buffer_free((unsigned long)(ptr - sparsemap_buf));
 			sparsemap_buf = ptr + size;
+		}
 	}
 	return ptr;
 }
@@ -635,7 +639,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 #endif
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-static struct page *populate_section_memmap(unsigned long pfn,
+static struct page * __meminit populate_section_memmap(unsigned long pfn,
 		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
 {
 	return __populate_section_memmap(pfn, nr_pages, nid, altmap);
@@ -657,7 +661,7 @@ static void free_map_bootmem(struct page *memmap)
 	vmemmap_free(start, end, NULL);
 }
 #else
-struct page *populate_section_memmap(unsigned long pfn,
+struct page * __meminit populate_section_memmap(unsigned long pfn,
 		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
 {
 	struct page *page, *ret;
@@ -763,12 +767,19 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	if (bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION)) {
 		unsigned long section_nr = pfn_to_section_nr(pfn);
 
-		if (!section_is_early) {
+		/*
+		 * When removing an early section, the usage map is kept (as the
+		 * usage maps of other sections fall into the same page). It
+		 * will be re-used when re-adding the section - which is then no
+		 * longer an early section. If the usage map is PageReserved, it
+		 * was allocated during boot.
+		 */
+		if (!PageReserved(virt_to_page(ms->usage))) {
 			kfree(ms->usage);
 			ms->usage = NULL;
 		}
 		memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-		ms->section_mem_map = sparse_encode_mem_map(NULL, section_nr);
+		ms->section_mem_map = (unsigned long)NULL;
 	}
 
 	if (section_is_early && memmap)
@@ -867,7 +878,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 	 */
 	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
 
-	ms = __pfn_to_section(start_pfn);
+	ms = __nr_to_section(section_nr);
 	set_section_nid(section_nr, nid);
 	section_mark_present(ms);
 
@@ -884,9 +895,6 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 {
 	int i;
 
-	if (!memmap)
-		return;
-
 	/*
 	 * A further optimization is to have per section refcounted
 	 * num_poisoned_pages.  But that would need more space per memmap, so
@@ -898,7 +906,7 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
 
 	for (i = 0; i < nr_pages; i++) {
 		if (PageHWPoison(&memmap[i])) {
-			atomic_long_sub(1, &num_poisoned_pages);
+			num_poisoned_pages_dec();
 			ClearPageHWPoison(&memmap[i]);
 		}
 	}