Merge branch 'akpm' (patches from Andrew Morton)

Merge more patches from Andrew Morton:
 "The rest of MM"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: remove free_area_cache
  zswap: add documentation
  zswap: add to mm/
  zbud: add to mm/

Documentation/vm/zswap.txt

+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.

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;
 	}
 }
 

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);

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;
 	}
 }
 

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;
 	}
 }

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;
 	}
 }
 

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;
 	}
 }
 

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;
 	}
 }

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) {

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;
 	}
 }

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) {

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) {

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? */

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

include/linux/zbud.h

+#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_ */

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);
 

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

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

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. */
 }
 

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)

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