23 files changed, 1592 insertions, 66 deletions

diff --git a/Documentation/vm/zswap.txt b/Documentation/vm/zswap.txt
new file mode 100644
index 00000000000..7e492d8aaea
--- /dev/null
+++ b/Documentation/vm/zswap.txt
@@ -0,0 +1,68 @@
+Overview:
+
+Zswap is a lightweight compressed cache for swap pages. It takes pages that are
+in the process of being swapped out and attempts to compress them into a
+dynamically allocated RAM-based memory pool.  zswap basically trades CPU cycles
+for potentially reduced swap I/O.  This trade-off can also result in a
+significant performance improvement if reads from the compressed cache are
+faster than reads from a swap device.
+
+NOTE: Zswap is a new feature as of v3.11 and interacts heavily with memory
+reclaim.  This interaction has not be fully explored on the large set of
+potential configurations and workloads that exist.  For this reason, zswap
+is a work in progress and should be considered experimental.
+
+Some potential benefits:
+* Desktop/laptop users with limited RAM capacities can mitigate the
+    performance impact of swapping.
+* Overcommitted guests that share a common I/O resource can
+    dramatically reduce their swap I/O pressure, avoiding heavy handed I/O
+    throttling by the hypervisor. This allows more work to get done with less
+    impact to the guest workload and guests sharing the I/O subsystem
+* Users with SSDs as swap devices can extend the life of the device by
+    drastically reducing life-shortening writes.
+
+Zswap evicts pages from compressed cache on an LRU basis to the backing swap
+device when the compressed pool reaches it size limit.  This requirement had
+been identified in prior community discussions.
+
+To enabled zswap, the "enabled" attribute must be set to 1 at boot time.  e.g.
+zswap.enabled=1
+
+Design:
+
+Zswap receives pages for compression through the Frontswap API and is able to
+evict pages from its own compressed pool on an LRU basis and write them back to
+the backing swap device in the case that the compressed pool is full.
+
+Zswap makes use of zbud for the managing the compressed memory pool.  Each
+allocation in zbud is not directly accessible by address.  Rather, a handle is
+return by the allocation routine and that handle must be mapped before being
+accessed.  The compressed memory pool grows on demand and shrinks as compressed
+pages are freed.  The pool is not preallocated.
+
+When a swap page is passed from frontswap to zswap, zswap maintains a mapping
+of the swap entry, a combination of the swap type and swap offset, to the zbud
+handle that references that compressed swap page.  This mapping is achieved
+with a red-black tree per swap type.  The swap offset is the search key for the
+tree nodes.
+
+During a page fault on a PTE that is a swap entry, frontswap calls the zswap
+load function to decompress the page into the page allocated by the page fault
+handler.
+
+Once there are no PTEs referencing a swap page stored in zswap (i.e. the count
+in the swap_map goes to 0) the swap code calls the zswap invalidate function,
+via frontswap, to free the compressed entry.
+
+Zswap seeks to be simple in its policies.  Sysfs attributes allow for one user
+controlled policies:
+* max_pool_percent - The maximum percentage of memory that the compressed
+    pool can occupy.
+
+Zswap allows the compressor to be selected at kernel boot time by setting the
+“compressor” attribute.  The default compressor is lzo.  e.g.
+zswap.compressor=deflate
+
+A debugfs interface is provided for various statistic about pool size, number
+of pages stored, and various counters for the reasons pages are rejected.
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 10062ceadd1..0c6356255fe 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -181,11 +181,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (mmap_is_legacy()) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
 
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 7c7be785563..8ed6cb1a900 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -90,11 +90,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (mmap_is_legacy()) {
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base();
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
 EXPORT_SYMBOL_GPL(arch_pick_mmap_layout);
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 7e5fe2790d8..f1baadd56e8 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -158,11 +158,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (mmap_is_legacy()) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
 
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index 67a42ed0d2f..cb8bdbe4972 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -92,10 +92,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (mmap_is_legacy()) {
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base();
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 06bafec0027..40023290ee5 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -91,11 +91,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (mmap_is_legacy()) {
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base();
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
 
@@ -176,11 +174,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (mmap_is_legacy()) {
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = s390_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base();
 		mm->get_unmapped_area = s390_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
 
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 2daaaa6eda2..51561b8b15b 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -290,7 +290,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	    sysctl_legacy_va_layout) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		/* We know it's 32-bit */
 		unsigned long task_size = STACK_TOP32;
@@ -302,7 +301,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 
 		mm->mmap_base = PAGE_ALIGN(task_size - gap - random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
 
diff --git a/arch/tile/mm/mmap.c b/arch/tile/mm/mmap.c
index f96f4cec602..d67d91ebf63 100644
--- a/arch/tile/mm/mmap.c
+++ b/arch/tile/mm/mmap.c
@@ -66,10 +66,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (!is_32bit || rlimit(RLIMIT_STACK) == RLIM_INFINITY) {
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base(mm);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 52ff81cce00..bae3aba95b1 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -308,8 +308,6 @@ static int load_aout_binary(struct linux_binprm *bprm)
 		(current->mm->start_data = N_DATADDR(ex));
 	current->mm->brk = ex.a_bss +
 		(current->mm->start_brk = N_BSSADDR(ex));
-	current->mm->free_area_cache = TASK_UNMAPPED_BASE;
-	current->mm->cached_hole_size = 0;
 
 	retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
 	if (retval < 0) {
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 845df6835f9..62c29a5bfe2 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -115,10 +115,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (mmap_is_legacy()) {
 		mm->mmap_base = mmap_legacy_base();
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base();
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index bce87694f7b..89dec7f789a 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -255,8 +255,6 @@ static int load_aout_binary(struct linux_binprm * bprm)
 		(current->mm->start_data = N_DATADDR(ex));
 	current->mm->brk = ex.a_bss +
 		(current->mm->start_brk = N_BSSADDR(ex));
-	current->mm->free_area_cache = current->mm->mmap_base;
-	current->mm->cached_hole_size = 0;
 
 	retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
 	if (retval < 0) {
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index f8a0b0efda4..100edcc5e31 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -738,8 +738,6 @@ static int load_elf_binary(struct linux_binprm *bprm)
 
 	/* Do this so that we can load the interpreter, if need be.  We will
 	   change some of these later */
-	current->mm->free_area_cache = current->mm->mmap_base;
-	current->mm->cached_hole_size = 0;
 	retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP),
 				 executable_stack);
 	if (retval < 0) {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ace9a5f01c6..fb425aa16c0 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -330,12 +330,9 @@ struct mm_struct {
 	unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
 				unsigned long pgoff, unsigned long flags);
-	void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
 #endif
 	unsigned long mmap_base;		/* base of mmap area */
 	unsigned long task_size;		/* size of task vm space */
-	unsigned long cached_hole_size; 	/* if non-zero, the largest hole below free_area_cache */
-	unsigned long free_area_cache;		/* first hole of size cached_hole_size or larger */
 	unsigned long highest_vm_end;		/* highest vma end address */
 	pgd_t * pgd;
 	atomic_t mm_users;			/* How many users with user space? */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f99d57e0ae4..50d04b92ced 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -322,8 +322,6 @@ extern unsigned long
 arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 			  unsigned long len, unsigned long pgoff,
 			  unsigned long flags);
-extern void arch_unmap_area(struct mm_struct *, unsigned long);
-extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 #else
 static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
 #endif
diff --git a/include/linux/zbud.h b/include/linux/zbud.h
new file mode 100644
index 00000000000..2571a5cfa5f
--- /dev/null
+++ b/include/linux/zbud.h
@@ -0,0 +1,22 @@
+#ifndef _ZBUD_H_
+#define _ZBUD_H_
+
+#include <linux/types.h>
+
+struct zbud_pool;
+
+struct zbud_ops {
+	int (*evict)(struct zbud_pool *pool, unsigned long handle);
+};
+
+struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops);
+void zbud_destroy_pool(struct zbud_pool *pool);
+int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp,
+	unsigned long *handle);
+void zbud_free(struct zbud_pool *pool, unsigned long handle);
+int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries);
+void *zbud_map(struct zbud_pool *pool, unsigned long handle);
+void zbud_unmap(struct zbud_pool *pool, unsigned long handle);
+u64 zbud_get_pool_size(struct zbud_pool *pool);
+
+#endif /* _ZBUD_H_ */
diff --git a/kernel/fork.c b/kernel/fork.c
index 6e6a1c11b3e..66635c80a81 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -365,8 +365,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 	mm->locked_vm = 0;
 	mm->mmap = NULL;
 	mm->mmap_cache = NULL;
-	mm->free_area_cache = oldmm->mmap_base;
-	mm->cached_hole_size = ~0UL;
 	mm->map_count = 0;
 	cpumask_clear(mm_cpumask(mm));
 	mm->mm_rb = RB_ROOT;
@@ -540,8 +538,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	mm->nr_ptes = 0;
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
-	mm->free_area_cache = TASK_UNMAPPED_BASE;
-	mm->cached_hole_size = ~0UL;
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 7e28ecfa8aa..8028dcc6615 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -478,6 +478,36 @@ config FRONTSWAP
 
 	  If unsure, say Y to enable frontswap.
 
+config ZBUD
+	tristate
+	default n
+	help
+	  A special purpose allocator for storing compressed pages.
+	  It is designed to store up to two compressed pages per physical
+	  page.  While this design limits storage density, it has simple and
+	  deterministic reclaim properties that make it preferable to a higher
+	  density approach when reclaim will be used.
+
+config ZSWAP
+	bool "Compressed cache for swap pages (EXPERIMENTAL)"
+	depends on FRONTSWAP && CRYPTO=y
+	select CRYPTO_LZO
+	select ZBUD
+	default n
+	help
+	  A lightweight compressed cache for swap pages.  It takes
+	  pages that are in the process of being swapped out and attempts to
+	  compress them into a dynamically allocated RAM-based memory pool.
+	  This can result in a significant I/O reduction on swap device and,
+	  in the case where decompressing from RAM is faster that swap device
+	  reads, can also improve workload performance.
+
+	  This is marked experimental because it is a new feature (as of
+	  v3.11) that interacts heavily with memory reclaim.  While these
+	  interactions don't cause any known issues on simple memory setups,
+	  they have not be fully explored on the large set of potential
+	  configurations and workloads that exist.
+
 config MEM_SOFT_DIRTY
 	bool "Track memory changes"
 	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
diff --git a/mm/Makefile b/mm/Makefile
index 72c5acb9345..f00803386a6 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
 obj-$(CONFIG_BOUNCE)	+= bounce.o
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
 obj-$(CONFIG_FRONTSWAP)	+= frontswap.o
+obj-$(CONFIG_ZSWAP)	+= zswap.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
@@ -58,3 +59,4 @@ obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
 obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
 obj-$(CONFIG_CLEANCACHE) += cleancache.o
 obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
+obj-$(CONFIG_ZBUD)	+= zbud.o
diff --git a/mm/mmap.c b/mm/mmap.c
index f81311173b4..fbad7b09109 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1878,15 +1878,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 }
 #endif	
 
-void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
-{
-	/*
-	 * Is this a new hole at the lowest possible address?
-	 */
-	if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache)
-		mm->free_area_cache = addr;
-}
-
 /*
  * This mmap-allocator allocates new areas top-down from below the
  * stack's low limit (the base):
@@ -1943,19 +1934,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 }
 #endif
 
-void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr)
-{
-	/*
-	 * Is this a new hole at the highest possible address?
-	 */
-	if (addr > mm->free_area_cache)
-		mm->free_area_cache = addr;
-
-	/* dont allow allocations above current base */
-	if (mm->free_area_cache > mm->mmap_base)
-		mm->free_area_cache = mm->mmap_base;
-}
-
 unsigned long
 get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
@@ -2376,7 +2354,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct vm_area_struct **insertion_point;
 	struct vm_area_struct *tail_vma = NULL;
-	unsigned long addr;
 
 	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
 	vma->vm_prev = NULL;
@@ -2393,11 +2370,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else
 		mm->highest_vm_end = prev ? prev->vm_end : 0;
 	tail_vma->vm_next = NULL;
-	if (mm->unmap_area == arch_unmap_area)
-		addr = prev ? prev->vm_end : mm->mmap_base;
-	else
-		addr = vma ?  vma->vm_start : mm->mmap_base;
-	mm->unmap_area(mm, addr);
 	mm->mmap_cache = NULL;		/* Kill the cache. */
 }
 
diff --git a/mm/nommu.c b/mm/nommu.c
index e44e6e0a125..ecd1f158548 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1871,10 +1871,6 @@ unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr,
 	return -ENOMEM;
 }
 
-void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
-{
-}
-
 void unmap_mapping_range(struct address_space *mapping,
 			 loff_t const holebegin, loff_t const holelen,
 			 int even_cows)
diff --git a/mm/util.c b/mm/util.c
index ab1424dbe2e..7441c41d00f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -295,7 +295,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 {
 	mm->mmap_base = TASK_UNMAPPED_BASE;
 	mm->get_unmapped_area = arch_get_unmapped_area;
-	mm->unmap_area = arch_unmap_area;
 }
 #endif
 
diff --git a/mm/zbud.c b/mm/zbud.c
new file mode 100644
index 00000000000..9bb4710e358
--- /dev/null
+++ b/mm/zbud.c
@@ -0,0 +1,527 @@
+/*
+ * zbud.c
+ *
+ * Copyright (C) 2013, Seth Jennings, IBM
+ *
+ * Concepts based on zcache internal zbud allocator by Dan Magenheimer.
+ *
+ * zbud is an special purpose allocator for storing compressed pages.  Contrary
+ * to what its name may suggest, zbud is not a buddy allocator, but rather an
+ * allocator that "buddies" two compressed pages together in a single memory
+ * page.
+ *
+ * While this design limits storage density, it has simple and deterministic
+ * reclaim properties that make it preferable to a higher density approach when
+ * reclaim will be used.
+ *
+ * zbud works by storing compressed pages, or "zpages", together in pairs in a
+ * single memory page called a "zbud page".  The first buddy is "left
+ * justifed" at the beginning of the zbud page, and the last buddy is "right
+ * justified" at the end of the zbud page.  The benefit is that if either
+ * buddy is freed, the freed buddy space, coalesced with whatever slack space
+ * that existed between the buddies, results in the largest possible free region
+ * within the zbud page.
+ *
+ * zbud also provides an attractive lower bound on density. The ratio of zpages
+ * to zbud pages can not be less than 1.  This ensures that zbud can never "do
+ * harm" by using more pages to store zpages than the uncompressed zpages would
+ * have used on their own.
+ *
+ * zbud pages are divided into "chunks".  The size of the chunks is fixed at
+ * compile time and determined by NCHUNKS_ORDER below.  Dividing zbud pages
+ * into chunks allows organizing unbuddied zbud pages into a manageable number
+ * of unbuddied lists according to the number of free chunks available in the
+ * zbud page.
+ *
+ * The zbud API differs from that of conventional allocators in that the
+ * allocation function, zbud_alloc(), returns an opaque handle to the user,
+ * not a dereferenceable pointer.  The user must map the handle using
+ * zbud_map() in order to get a usable pointer by which to access the
+ * allocation data and unmap the handle with zbud_unmap() when operations
+ * on the allocation data are complete.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/atomic.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/preempt.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/zbud.h>
+
+/*****************
+ * Structures
+*****************/
+/*
+ * NCHUNKS_ORDER determines the internal allocation granularity, effectively
+ * adjusting internal fragmentation.  It also determines the number of
+ * freelists maintained in each pool. NCHUNKS_ORDER of 6 means that the
+ * allocation granularity will be in chunks of size PAGE_SIZE/64, and there
+ * will be 64 freelists per pool.
+ */
+#define NCHUNKS_ORDER	6
+
+#define CHUNK_SHIFT	(PAGE_SHIFT - NCHUNKS_ORDER)
+#define CHUNK_SIZE	(1 << CHUNK_SHIFT)
+#define NCHUNKS		(PAGE_SIZE >> CHUNK_SHIFT)
+#define ZHDR_SIZE_ALIGNED CHUNK_SIZE
+
+/**
+ * struct zbud_pool - stores metadata for each zbud pool
+ * @lock:	protects all pool fields and first|last_chunk fields of any
+ *		zbud page in the pool
+ * @unbuddied:	array of lists tracking zbud pages that only contain one buddy;
+ *		the lists each zbud page is added to depends on the size of
+ *		its free region.
+ * @buddied:	list tracking the zbud pages that contain two buddies;
+ *		these zbud pages are full
+ * @lru:	list tracking the zbud pages in LRU order by most recently
+ *		added buddy.
+ * @pages_nr:	number of zbud pages in the pool.
+ * @ops:	pointer to a structure of user defined operations specified at
+ *		pool creation time.
+ *
+ * This structure is allocated at pool creation time and maintains metadata
+ * pertaining to a particular zbud pool.
+ */
+struct zbud_pool {
+	spinlock_t lock;
+	struct list_head unbuddied[NCHUNKS];
+	struct list_head buddied;
+	struct list_head lru;
+	u64 pages_nr;
+	struct zbud_ops *ops;
+};
+
+/*
+ * struct zbud_header - zbud page metadata occupying the first chunk of each
+ *			zbud page.
+ * @buddy:	links the zbud page into the unbuddied/buddied lists in the pool
+ * @lru:	links the zbud page into the lru list in the pool
+ * @first_chunks:	the size of the first buddy in chunks, 0 if free
+ * @last_chunks:	the size of the last buddy in chunks, 0 if free
+ */
+struct zbud_header {
+	struct list_head buddy;
+	struct list_head lru;
+	unsigned int first_chunks;
+	unsigned int last_chunks;
+	bool under_reclaim;
+};
+
+/*****************
+ * Helpers
+*****************/
+/* Just to make the code easier to read */
+enum buddy {
+	FIRST,
+	LAST
+};
+
+/* Converts an allocation size in bytes to size in zbud chunks */
+static int size_to_chunks(int size)
+{
+	return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT;
+}
+
+#define for_each_unbuddied_list(_iter, _begin) \
+	for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++)
+
+/* Initializes the zbud header of a newly allocated zbud page */
+static struct zbud_header *init_zbud_page(struct page *page)
+{
+	struct zbud_header *zhdr = page_address(page);
+	zhdr->first_chunks = 0;
+	zhdr->last_chunks = 0;
+	INIT_LIST_HEAD(&zhdr->buddy);
+	INIT_LIST_HEAD(&zhdr->lru);
+	zhdr->under_reclaim = 0;
+	return zhdr;
+}
+
+/* Resets the struct page fields and frees the page */
+static void free_zbud_page(struct zbud_header *zhdr)
+{
+	__free_page(virt_to_page(zhdr));
+}
+
+/*
+ * Encodes the handle of a particular buddy within a zbud page
+ * Pool lock should be held as this function accesses first|last_chunks
+ */
+static unsigned long encode_handle(struct zbud_header *zhdr, enum buddy bud)
+{
+	unsigned long handle;
+
+	/*
+	 * For now, the encoded handle is actually just the pointer to the data
+	 * but this might not always be the case.  A little information hiding.
+	 * Add CHUNK_SIZE to the handle if it is the first allocation to jump
+	 * over the zbud header in the first chunk.
+	 */
+	handle = (unsigned long)zhdr;
+	if (bud == FIRST)
+		/* skip over zbud header */
+		handle += ZHDR_SIZE_ALIGNED;
+	else /* bud == LAST */
+		handle += PAGE_SIZE - (zhdr->last_chunks  << CHUNK_SHIFT);
+	return handle;
+}
+
+/* Returns the zbud page where a given handle is stored */
+static struct zbud_header *handle_to_zbud_header(unsigned long handle)
+{
+	return (struct zbud_header *)(handle & PAGE_MASK);
+}
+
+/* Returns the number of free chunks in a zbud page */
+static int num_free_chunks(struct zbud_header *zhdr)
+{
+	/*
+	 * Rather than branch for different situations, just use the fact that
+	 * free buddies have a length of zero to simplify everything. -1 at the
+	 * end for the zbud header.
+	 */
+	return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks - 1;
+}
+
+/*****************
+ * API Functions
+*****************/
+/**
+ * zbud_create_pool() - create a new zbud pool
+ * @gfp:	gfp flags when allocating the zbud pool structure
+ * @ops:	user-defined operations for the zbud pool
+ *
+ * Return: pointer to the new zbud pool or NULL if the metadata allocation
+ * failed.
+ */
+struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops)
+{
+	struct zbud_pool *pool;
+	int i;
+
+	pool = kmalloc(sizeof(struct zbud_pool), gfp);
+	if (!pool)
+		return NULL;
+	spin_lock_init(&pool->lock);
+	for_each_unbuddied_list(i, 0)
+		INIT_LIST_HEAD(&pool->unbuddied[i]);
+	INIT_LIST_HEAD(&pool->buddied);
+	INIT_LIST_HEAD(&pool->lru);
+	pool->pages_nr = 0;
+	pool->ops = ops;
+	return pool;
+}
+
+/**
+ * zbud_destroy_pool() - destroys an existing zbud pool
+ * @pool:	the zbud pool to be destroyed
+ *
+ * The pool should be emptied before this function is called.
+ */
+void zbud_destroy_pool(struct zbud_pool *pool)
+{
+	kfree(pool);
+}
+
+/**
+ * zbud_alloc() - allocates a region of a given size
+ * @pool:	zbud pool from which to allocate
+ * @size:	size in bytes of the desired allocation
+ * @gfp:	gfp flags used if the pool needs to grow
+ * @handle:	handle of the new allocation
+ *
+ * This function will attempt to find a free region in the pool large enough to
+ * satisfy the allocation request.  A search of the unbuddied lists is
+ * performed first. If no suitable free region is found, then a new page is
+ * allocated and added to the pool to satisfy the request.
+ *
+ * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used
+ * as zbud pool pages.
+ *
+ * Return: 0 if success and handle is set, otherwise -EINVAL is the size or
+ * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate
+ * a new page.
+ */
+int zbud_alloc(struct zbud_pool *pool, int size, gfp_t gfp,
+			unsigned long *handle)
+{
+	int chunks, i, freechunks;
+	struct zbud_header *zhdr = NULL;
+	enum buddy bud;
+	struct page *page;
+
+	if (size <= 0 || gfp & __GFP_HIGHMEM)
+		return -EINVAL;
+	if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED)
+		return -ENOSPC;
+	chunks = size_to_chunks(size);
+	spin_lock(&pool->lock);
+
+	/* First, try to find an unbuddied zbud page. */
+	zhdr = NULL;
+	for_each_unbuddied_list(i, chunks) {
+		if (!list_empty(&pool->unbuddied[i])) {
+			zhdr = list_first_entry(&pool->unbuddied[i],
+					struct zbud_header, buddy);
+			list_del(&zhdr->buddy);
+			if (zhdr->first_chunks == 0)
+				bud = FIRST;
+			else
+				bud = LAST;
+			goto found;
+		}
+	}
+
+	/* Couldn't find unbuddied zbud page, create new one */
+	spin_unlock(&pool->lock);
+	page = alloc_page(gfp);
+	if (!page)
+		return -ENOMEM;
+	spin_lock(&pool->lock);
+	pool->pages_nr++;
+	zhdr = init_zbud_page(page);
+	bud = FIRST;
+
+found:
+	if (bud == FIRST)
+		zhdr->first_chunks = chunks;
+	else
+		zhdr->last_chunks = chunks;
+
+	if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0) {
+		/* Add to unbuddied list */
+		freechunks = num_free_chunks(zhdr);
+		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+	} else {
+		/* Add to buddied list */
+		list_add(&zhdr->buddy, &pool->buddied);
+	}
+
+	/* Add/move zbud page to beginning of LRU */
+	if (!list_empty(&zhdr->lru))
+		list_del(&zhdr->lru);
+	list_add(&zhdr->lru, &pool->lru);
+
+	*handle = encode_handle(zhdr, bud);
+	spin_unlock(&pool->lock);
+
+	return 0;
+}
+
+/**
+ * zbud_free() - frees the allocation associated with the given handle
+ * @pool:	pool in which the allocation resided
+ * @handle:	handle associated with the allocation returned by zbud_alloc()
+ *
+ * In the case that the zbud page in which the allocation resides is under
+ * reclaim, as indicated by the PG_reclaim flag being set, this function
+ * only sets the first|last_chunks to 0.  The page is actually freed
+ * once both buddies are evicted (see zbud_reclaim_page() below).
+ */
+void zbud_free(struct zbud_pool *pool, unsigned long handle)
+{
+	struct zbud_header *zhdr;
+	int freechunks;
+
+	spin_lock(&pool->lock);
+	zhdr = handle_to_zbud_header(handle);
+
+	/* If first buddy, handle will be page aligned */
+	if ((handle - ZHDR_SIZE_ALIGNED) & ~PAGE_MASK)
+		zhdr->last_chunks = 0;
+	else
+		zhdr->first_chunks = 0;
+
+	if (zhdr->under_reclaim) {
+		/* zbud page is under reclaim, reclaim will free */
+		spin_unlock(&pool->lock);
+		return;
+	}
+
+	/* Remove from existing buddy list */
+	list_del(&zhdr->buddy);
+
+	if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) {
+		/* zbud page is empty, free */
+		list_del(&zhdr->lru);
+		free_zbud_page(zhdr);
+		pool->pages_nr--;
+	} else {
+		/* Add to unbuddied list */
+		freechunks = num_free_chunks(zhdr);
+		list_add(&zhdr->buddy, &pool->unbuddied[freechunks]);
+	}
+
+	spin