1 files changed, 273 insertions, 49 deletions

diff --git a/drivers/staging/zsmalloc/zsmalloc-main.c b/drivers/staging/zsmalloc/zsmalloc-main.c
index 8b0bcb626a7..09a9d35d436 100644
--- a/drivers/staging/zsmalloc/zsmalloc-main.c
+++ b/drivers/staging/zsmalloc/zsmalloc-main.c
@@ -75,9 +75,140 @@
 #include <linux/cpumask.h>
 #include <linux/cpu.h>
 #include <linux/vmalloc.h>
+#include <linux/hardirq.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
 
 #include "zsmalloc.h"
-#include "zsmalloc_int.h"
+
+/*
+ * This must be power of 2 and greater than of equal to sizeof(link_free).
+ * These two conditions ensure that any 'struct link_free' itself doesn't
+ * span more than 1 page which avoids complex case of mapping 2 pages simply
+ * to restore link_free pointer values.
+ */
+#define ZS_ALIGN		8
+
+/*
+ * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
+ * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
+ */
+#define ZS_MAX_ZSPAGE_ORDER 2
+#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)
+
+/*
+ * Object location (<PFN>, <obj_idx>) is encoded as
+ * as single (void *) handle value.
+ *
+ * Note that object index <obj_idx> is relative to system
+ * page <PFN> it is stored in, so for each sub-page belonging
+ * to a zspage, obj_idx starts with 0.
+ *
+ * This is made more complicated by various memory models and PAE.
+ */
+
+#ifndef MAX_PHYSMEM_BITS
+#ifdef CONFIG_HIGHMEM64G
+#define MAX_PHYSMEM_BITS 36
+#else /* !CONFIG_HIGHMEM64G */
+/*
+ * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
+ * be PAGE_SHIFT
+ */
+#define MAX_PHYSMEM_BITS BITS_PER_LONG
+#endif
+#endif
+#define _PFN_BITS		(MAX_PHYSMEM_BITS - PAGE_SHIFT)
+#define OBJ_INDEX_BITS	(BITS_PER_LONG - _PFN_BITS)
+#define OBJ_INDEX_MASK	((_AC(1, UL) << OBJ_INDEX_BITS) - 1)
+
+#define MAX(a, b) ((a) >= (b) ? (a) : (b))
+/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
+#define ZS_MIN_ALLOC_SIZE \
+	MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
+#define ZS_MAX_ALLOC_SIZE	PAGE_SIZE
+
+/*
+ * On systems with 4K page size, this gives 254 size classes! There is a
+ * trader-off here:
+ *  - Large number of size classes is potentially wasteful as free page are
+ *    spread across these classes
+ *  - Small number of size classes causes large internal fragmentation
+ *  - Probably its better to use specific size classes (empirically
+ *    determined). NOTE: all those class sizes must be set as multiple of
+ *    ZS_ALIGN to make sure link_free itself never has to span 2 pages.
+ *
+ *  ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
+ *  (reason above)
+ */
+#define ZS_SIZE_CLASS_DELTA	16
+#define ZS_SIZE_CLASSES		((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \
+					ZS_SIZE_CLASS_DELTA + 1)
+
+/*
+ * We do not maintain any list for completely empty or full pages
+ */
+enum fullness_group {
+	ZS_ALMOST_FULL,
+	ZS_ALMOST_EMPTY,
+	_ZS_NR_FULLNESS_GROUPS,
+
+	ZS_EMPTY,
+	ZS_FULL
+};
+
+/*
+ * We assign a page to ZS_ALMOST_EMPTY fullness group when:
+ *	n <= N / f, where
+ * n = number of allocated objects
+ * N = total number of objects zspage can store
+ * f = 1/fullness_threshold_frac
+ *
+ * Similarly, we assign zspage to:
+ *	ZS_ALMOST_FULL	when n > N / f
+ *	ZS_EMPTY	when n == 0
+ *	ZS_FULL		when n == N
+ *
+ * (see: fix_fullness_group())
+ */
+static const int fullness_threshold_frac = 4;
+
+struct size_class {
+	/*
+	 * Size of objects stored in this class. Must be multiple
+	 * of ZS_ALIGN.
+	 */
+	int size;
+	unsigned int index;
+
+	/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
+	int pages_per_zspage;
+
+	spinlock_t lock;
+
+	/* stats */
+	u64 pages_allocated;
+
+	struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS];
+};
+
+/*
+ * Placed within free objects to form a singly linked list.
+ * For every zspage, first_page->freelist gives head of this list.
+ *
+ * This must be power of 2 and less than or equal to ZS_ALIGN
+ */
+struct link_free {
+	/* Handle of next free chunk (encodes <PFN, obj_idx>) */
+	void *next;
+};
+
+struct zs_pool {
+	struct size_class size_class[ZS_SIZE_CLASSES];
+
+	gfp_t flags;	/* allocation flags used when growing pool */
+	const char *name;
+};
 
 /*
  * A zspage's class index and fullness group
@@ -88,6 +219,30 @@
 #define CLASS_IDX_MASK	((1 << CLASS_IDX_BITS) - 1)
 #define FULLNESS_MASK	((1 << FULLNESS_BITS) - 1)
 
+/*
+ * By default, zsmalloc uses a copy-based object mapping method to access
+ * allocations that span two pages. However, if a particular architecture
+ * 1) Implements local_flush_tlb_kernel_range() and 2) Performs VM mapping
+ * faster than copying, then it should be added here so that
+ * USE_PGTABLE_MAPPING is defined. This causes zsmalloc to use page table
+ * mapping rather than copying
+ * for object mapping.
+*/
+#if defined(CONFIG_ARM)
+#define USE_PGTABLE_MAPPING
+#endif
+
+struct mapping_area {
+#ifdef USE_PGTABLE_MAPPING
+	struct vm_struct *vm; /* vm area for mapping object that span pages */
+#else
+	char *vm_buf; /* copy buffer for objects that span pages */
+#endif
+	char *vm_addr; /* address of kmap_atomic()'ed pages */
+	enum zs_mapmode vm_mm; /* mapping mode */
+};
+
+
 /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
 static DEFINE_PER_CPU(struct mapping_area, zs_map_area);
 
@@ -470,16 +625,83 @@ static struct page *find_get_zspage(struct size_class *class)
 	return page;
 }
 
-static void zs_copy_map_object(char *buf, struct page *firstpage,
-				int off, int size)
+#ifdef USE_PGTABLE_MAPPING
+static inline int __zs_cpu_up(struct mapping_area *area)
+{
+	/*
+	 * Make sure we don't leak memory if a cpu UP notification
+	 * and zs_init() race and both call zs_cpu_up() on the same cpu
+	 */
+	if (area->vm)
+		return 0;
+	area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL);
+	if (!area->vm)
+		return -ENOMEM;
+	return 0;
+}
+
+static inline void __zs_cpu_down(struct mapping_area *area)
+{
+	if (area->vm)
+		free_vm_area(area->vm);
+	area->vm = NULL;
+}
+
+static inline void *__zs_map_object(struct mapping_area *area,
+				struct page *pages[2], int off, int size)
+{
+	BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, &pages));
+	area->vm_addr = area->vm->addr;
+	return area->vm_addr + off;
+}
+
+static inline void __zs_unmap_object(struct mapping_area *area,
+				struct page *pages[2], int off, int size)
+{
+	unsigned long addr = (unsigned long)area->vm_addr;
+	unsigned long end = addr + (PAGE_SIZE * 2);
+
+	flush_cache_vunmap(addr, end);
+	unmap_kernel_range_noflush(addr, PAGE_SIZE * 2);
+	local_flush_tlb_kernel_range(addr, end);
+}
+
+#else /* USE_PGTABLE_MAPPING */
+
+static inline int __zs_cpu_up(struct mapping_area *area)
+{
+	/*
+	 * Make sure we don't leak memory if a cpu UP notification
+	 * and zs_init() race and both call zs_cpu_up() on the same cpu
+	 */
+	if (area->vm_buf)
+		return 0;
+	area->vm_buf = (char *)__get_free_page(GFP_KERNEL);
+	if (!area->vm_buf)
+		return -ENOMEM;
+	return 0;
+}
+
+static inline void __zs_cpu_down(struct mapping_area *area)
+{
+	if (area->vm_buf)
+		free_page((unsigned long)area->vm_buf);
+	area->vm_buf = NULL;
+}
+
+static void *__zs_map_object(struct mapping_area *area,
+			struct page *pages[2], int off, int size)
 {
-	struct page *pages[2];
 	int sizes[2];
 	void *addr;
+	char *buf = area->vm_buf;
 
-	pages[0] = firstpage;
-	pages[1] = get_next_page(firstpage);
-	BUG_ON(!pages[1]);
+	/* disable page faults to match kmap_atomic() return conditions */
+	pagefault_disable();
+
+	/* no read fastpath */
+	if (area->vm_mm == ZS_MM_WO)
+		goto out;
 
 	sizes[0] = PAGE_SIZE - off;
 	sizes[1] = size - sizes[0];
@@ -491,18 +713,20 @@ static void zs_copy_map_object(char *buf, struct page *firstpage,
 	addr = kmap_atomic(pages[1]);
 	memcpy(buf + sizes[0], addr, sizes[1]);
 	kunmap_atomic(addr);
+out:
+	return area->vm_buf;
 }
 
-static void zs_copy_unmap_object(char *buf, struct page *firstpage,
-				int off, int size)
+static void __zs_unmap_object(struct mapping_area *area,
+			struct page *pages[2], int off, int size)
 {
-	struct page *pages[2];
 	int sizes[2];
 	void *addr;
+	char *buf = area->vm_buf;
 
-	pages[0] = firstpage;
-	pages[1] = get_next_page(firstpage);
-	BUG_ON(!pages[1]);
+	/* no write fastpath */
+	if (area->vm_mm == ZS_MM_RO)
+		goto out;
 
 	sizes[0] = PAGE_SIZE - off;
 	sizes[1] = size - sizes[0];
@@ -514,34 +738,31 @@ static void zs_copy_unmap_object(char *buf, struct page *firstpage,
 	addr = kmap_atomic(pages[1]);
 	memcpy(addr, buf + sizes[0], sizes[1]);
 	kunmap_atomic(addr);
+
+out:
+	/* enable page faults to match kunmap_atomic() return conditions */
+	pagefault_enable();
 }
 
+#endif /* USE_PGTABLE_MAPPING */
+
 static int zs_cpu_notifier(struct notifier_block *nb, unsigned long action,
 				void *pcpu)
 {
-	int cpu = (long)pcpu;
+	int ret, cpu = (long)pcpu;
 	struct mapping_area *area;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 		area = &per_cpu(zs_map_area, cpu);
-		/*
-		 * Make sure we don't leak memory if a cpu UP notification
-		 * and zs_init() race and both call zs_cpu_up() on the same cpu
-		 */
-		if (area->vm_buf)
-			return 0;
-		area->vm_buf = (char *)__get_free_page(GFP_KERNEL);
-		if (!area->vm_buf)
-			return -ENOMEM;
-		return 0;
+		ret = __zs_cpu_up(area);
+		if (ret)
+			return notifier_from_errno(ret);
 		break;
 	case CPU_DEAD:
 	case CPU_UP_CANCELED:
 		area = &per_cpu(zs_map_area, cpu);
-		if (area->vm_buf)
-			free_page((unsigned long)area->vm_buf);
-		area->vm_buf = NULL;
+		__zs_cpu_down(area);
 		break;
 	}
 
@@ -758,28 +979,36 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 	enum fullness_group fg;
 	struct size_class *class;
 	struct mapping_area *area;
+	struct page *pages[2];
 
 	BUG_ON(!handle);
 
+	/*
+	 * Because we use per-cpu mapping areas shared among the
+	 * pools/users, we can't allow mapping in interrupt context
+	 * because it can corrupt another users mappings.
+	 */
+	BUG_ON(in_interrupt());
+
 	obj_handle_to_location(handle, &page, &obj_idx);
 	get_zspage_mapping(get_first_page(page), &class_idx, &fg);
 	class = &pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
 	area = &get_cpu_var(zs_map_area);
+	area->vm_mm = mm;
 	if (off + class->size <= PAGE_SIZE) {
 		/* this object is contained entirely within a page */
 		area->vm_addr = kmap_atomic(page);
 		return area->vm_addr + off;
 	}
 
-	/* disable page faults to match kmap_atomic() return conditions */
-	pagefault_disable();
+	/* this object spans two pages */
+	pages[0] = page;
+	pages[1] = get_next_page(page);
+	BUG_ON(!pages[1]);
 
-	if (mm != ZS_MM_WO)
-		zs_copy_map_object(area->vm_buf, page, off, class->size);
-	area->vm_addr = NULL;
-	return area->vm_buf;
+	return __zs_map_object(area, pages, off, class->size);
 }
 EXPORT_SYMBOL_GPL(zs_map_object);
 
@@ -793,17 +1022,6 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 	struct size_class *class;
 	struct mapping_area *area;
 
-	area = &__get_cpu_var(zs_map_area);
-	/* single-page object fastpath */
-	if (area->vm_addr) {
-		kunmap_atomic(area->vm_addr);
-		goto out;
-	}
-
-	/* no write fastpath */
-	if (area->vm_mm == ZS_MM_RO)
-		goto pfenable;
-
 	BUG_ON(!handle);
 
 	obj_handle_to_location(handle, &page, &obj_idx);
@@ -811,12 +1029,18 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 	class = &pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
-	zs_copy_unmap_object(area->vm_buf, page, off, class->size);
+	area = &__get_cpu_var(zs_map_area);
+	if (off + class->size <= PAGE_SIZE)
+		kunmap_atomic(area->vm_addr);
+	else {
+		struct page *pages[2];
 
-pfenable:
-	/* enable page faults to match kunmap_atomic() return conditions */
-	pagefault_enable();
-out:
+		pages[0] = page;
+		pages[1] = get_next_page(page);
+		BUG_ON(!pages[1]);
+
+		__zs_unmap_object(area, pages, off, class->size);
+	}
 	put_cpu_var(zs_map_area);
 }
 EXPORT_SYMBOL_GPL(zs_unmap_object);