Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - almost all of the rest of MM

 - misc bits

 - KASAN updates

 - procfs

 - lib/ updates

 - checkpatch updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (124 commits)
  checkpatch: remove false unbalanced braces warning
  checkpatch: notice unbalanced else braces in a patch
  checkpatch: add another old address for the FSF
  checkpatch: update $logFunctions
  checkpatch: warn on logging continuations
  checkpatch: warn on embedded function names
  lib/lz4: remove back-compat wrappers
  fs/pstore: fs/squashfs: change usage of LZ4 to work with new LZ4 version
  crypto: change LZ4 modules to work with new LZ4 module version
  lib/decompress_unlz4: change module to work with new LZ4 module version
  lib: update LZ4 compressor module
  lib/test_sort.c: make it explicitly non-modular
  lib: add CONFIG_TEST_SORT to enable self-test of sort()
  rbtree: use designated initializers
  linux/kernel.h: fix DIV_ROUND_CLOSEST to support negative divisors
  lib/find_bit.c: micro-optimise find_next_*_bit
  lib: add module support to atomic64 tests
  lib: add module support to glob tests
  lib: add module support to crc32 tests
  kernel/ksysfs.c: add __ro_after_init to bin_attribute structure
  ...

27 files changed, 902 insertions, 173 deletions

diff --git a/include/linux/bug.h b/include/linux/bug.h
index baff2e8fc8a8..5828489309bb 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -124,18 +124,20 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr,
 
 /*
  * Since detected data corruption should stop operation on the affected
- * structures, this returns false if the corruption condition is found.
+ * structures. Return value must be checked and sanely acted on by caller.
  */
+static inline __must_check bool check_data_corruption(bool v) { return v; }
 #define CHECK_DATA_CORRUPTION(condition, fmt, ...)			 \
-	do {								 \
-		if (unlikely(condition)) {				 \
+	check_data_corruption(({					 \
+		bool corruption = unlikely(condition);			 \
+		if (corruption) {					 \
 			if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \
 				pr_err(fmt, ##__VA_ARGS__);		 \
 				BUG();					 \
 			} else						 \
 				WARN(1, fmt, ##__VA_ARGS__);		 \
-			return false;					 \
 		}							 \
-	} while (0)
+		corruption;						 \
+	}))
 
 #endif	/* _LINUX_BUG_H */
diff --git a/include/linux/cma.h b/include/linux/cma.h
index 6f0a91b37f68..03f32d0bd1d8 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -29,6 +29,7 @@ extern int __init cma_declare_contiguous(phys_addr_t base,
 extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 					unsigned int order_per_bit,
 					struct cma **res_cma);
-extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align);
+extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align,
+			      gfp_t gfp_mask);
 extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count);
 #endif
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index fddd1a5eb322..811f7a915658 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -122,6 +122,7 @@
 #define __attribute_const__	__attribute__((__const__))
 #define __maybe_unused		__attribute__((unused))
 #define __always_unused		__attribute__((unused))
+#define __mode(x)               __attribute__((mode(x)))
 
 /* gcc version specific checks */
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 1e77ff5818f1..d8a3dc042e1c 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -38,8 +38,8 @@ static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
-int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-			const struct iomap_ops *ops);
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+		    const struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
@@ -71,19 +71,13 @@ static inline unsigned int dax_radix_order(void *entry)
 		return PMD_SHIFT - PAGE_SHIFT;
 	return 0;
 }
-int dax_iomap_pmd_fault(struct vm_fault *vmf, const struct iomap_ops *ops);
 #else
 static inline unsigned int dax_radix_order(void *entry)
 {
 	return 0;
 }
-static inline int dax_iomap_pmd_fault(struct vm_fault *vmf,
-		const struct iomap_ops *ops)
-{
-	return VM_FAULT_FALLBACK;
-}
 #endif
-int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
+int dax_pfn_mkwrite(struct vm_fault *vmf);
 
 static inline bool vma_is_dax(struct vm_area_struct *vma)
 {
diff --git a/include/linux/device.h b/include/linux/device.h
index bd684fc8ec1d..a48a7ff70164 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1139,6 +1139,7 @@ static inline bool device_supports_offline(struct device *dev)
 extern void lock_device_hotplug(void);
 extern void unlock_device_hotplug(void);
 extern int lock_device_hotplug_sysfs(void);
+void assert_held_device_hotplug(void);
 extern int device_offline(struct device *dev);
 extern int device_online(struct device *dev);
 extern void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h
index fec734df1524..b67bf6ac907d 100644
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -112,7 +112,7 @@ static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size,
 }
 
 struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
-				       unsigned int order);
+				       unsigned int order, gfp_t gfp_mask);
 bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 				 int count);
 
@@ -145,7 +145,7 @@ int dma_declare_contiguous(struct device *dev, phys_addr_t size,
 
 static inline
 struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
-				       unsigned int order)
+				       unsigned int order, gfp_t gfp_mask)
 {
 	return NULL;
 }
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 0fe0b6295ab5..db373b9d3223 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -541,7 +541,7 @@ static inline bool pm_suspended_storage(void)
 #if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
 /* The below functions must be run on a range from a single zone. */
 extern int alloc_contig_range(unsigned long start, unsigned long end,
-			      unsigned migratetype);
+			      unsigned migratetype, gfp_t gfp_mask);
 extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
 #endif
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f0029e786205..a3762d49ba39 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -6,6 +6,18 @@ extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 			 struct vm_area_struct *vma);
 extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd);
+extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+			 pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
+			 struct vm_area_struct *vma);
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud);
+#else
+static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
+{
+}
+#endif
+
 extern int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd);
 extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
@@ -17,6 +29,9 @@ extern bool madvise_free_huge_pmd(struct mmu_gather *tlb,
 extern int zap_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, unsigned long addr);
+extern int zap_huge_pud(struct mmu_gather *tlb,
+			struct vm_area_struct *vma,
+			pud_t *pud, unsigned long addr);
 extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned char *vec);
@@ -26,8 +41,10 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
 			int prot_numa);
-int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
-			pfn_t pfn, bool write);
+int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+			pmd_t *pmd, pfn_t pfn, bool write);
+int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+			pud_t *pud, pfn_t pfn, bool write);
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
 	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
@@ -58,13 +75,14 @@ extern struct kobj_attribute shmem_enabled_attr;
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, int flags);
-
 #define HPAGE_PMD_SHIFT PMD_SHIFT
 #define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
 #define HPAGE_PMD_MASK	(~(HPAGE_PMD_SIZE - 1))
 
+#define HPAGE_PUD_SHIFT PUD_SHIFT
+#define HPAGE_PUD_SIZE	((1UL) << HPAGE_PUD_SHIFT)
+#define HPAGE_PUD_MASK	(~(HPAGE_PUD_SIZE - 1))
+
 extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 
 #define transparent_hugepage_enabled(__vma)				\
@@ -118,6 +136,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 		bool freeze, struct page *page);
 
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+		unsigned long address);
+
+#define split_huge_pud(__vma, __pud, __address)				\
+	do {								\
+		pud_t *____pud = (__pud);				\
+		if (pud_trans_huge(*____pud)				\
+					|| pud_devmap(*____pud))	\
+			__split_huge_pud(__vma, __pud, __address);	\
+	}  while (0)
+
 extern int hugepage_madvise(struct vm_area_struct *vma,
 			    unsigned long *vm_flags, int advice);
 extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
@@ -126,6 +155,8 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    long adjust_next);
 extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma);
+extern spinlock_t *__pud_trans_huge_lock(pud_t *pud,
+		struct vm_area_struct *vma);
 /* mmap_sem must be held on entry */
 static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma)
@@ -136,6 +167,15 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 	else
 		return NULL;
 }
+static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
+		struct vm_area_struct *vma)
+{
+	VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
+	if (pud_trans_huge(*pud) || pud_devmap(*pud))
+		return __pud_trans_huge_lock(pud, vma);
+	else
+		return NULL;
+}
 static inline int hpage_nr_pages(struct page *page)
 {
 	if (unlikely(PageTransHuge(page)))
@@ -143,6 +183,11 @@ static inline int hpage_nr_pages(struct page *page)
 	return 1;
 }
 
+struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, int flags);
+struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud, int flags);
+
 extern int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
 
 extern struct page *huge_zero_page;
@@ -157,6 +202,11 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
 	return is_huge_zero_page(pmd_page(pmd));
 }
 
+static inline bool is_huge_zero_pud(pud_t pud)
+{
+	return false;
+}
+
 struct page *mm_get_huge_zero_page(struct mm_struct *mm);
 void mm_put_huge_zero_page(struct mm_struct *mm);
 
@@ -167,6 +217,10 @@ void mm_put_huge_zero_page(struct mm_struct *mm);
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; })
 
+#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; })
+#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
+#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
+
 #define hpage_nr_pages(x) 1
 
 #define transparent_hugepage_enabled(__vma) 0
@@ -195,6 +249,9 @@ static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 static inline void split_huge_pmd_address(struct vm_area_struct *vma,
 		unsigned long address, bool freeze, struct page *page) {}
 
+#define split_huge_pud(__vma, __pmd, __address)	\
+	do { } while (0)
+
 static inline int hugepage_madvise(struct vm_area_struct *vma,
 				   unsigned long *vm_flags, int advice)
 {
@@ -212,6 +269,11 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 {
 	return NULL;
 }
+static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
+		struct vm_area_struct *vma)
+{
+	return NULL;
+}
 
 static inline int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd)
 {
@@ -223,6 +285,11 @@ static inline bool is_huge_zero_page(struct page *page)
 	return false;
 }
 
+static inline bool is_huge_zero_pud(pud_t pud)
+{
+	return false;
+}
+
 static inline void mm_put_huge_zero_page(struct mm_struct *mm)
 {
 	return;
@@ -233,6 +300,12 @@ static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
 {
 	return NULL;
 }
+
+static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
+		unsigned long addr, pud_t *pud, int flags)
+{
+	return NULL;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 891459caa278..7291810067eb 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -79,8 +79,7 @@ int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
 		bool *did_zero, const struct iomap_ops *ops);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		const struct iomap_ops *ops);
-int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
-		const struct iomap_ops *ops);
+int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops);
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		loff_t start, loff_t len, const struct iomap_ops *ops);
 
diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index 1c30014ed176..d29e1e21bf3f 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -17,7 +17,7 @@
 
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/hrtimer.h>
+#include <linux/ktime.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/io.h>
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 820c0ad54a01..c908b25bf5a5 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -52,7 +52,7 @@ void kasan_free_pages(struct page *page, unsigned int order);
 void kasan_cache_create(struct kmem_cache *cache, size_t *size,
 			unsigned long *flags);
 void kasan_cache_shrink(struct kmem_cache *cache);
-void kasan_cache_destroy(struct kmem_cache *cache);
+void kasan_cache_shutdown(struct kmem_cache *cache);
 
 void kasan_poison_slab(struct page *page);
 void kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
@@ -98,7 +98,7 @@ static inline void kasan_cache_create(struct kmem_cache *cache,
 				      size_t *size,
 				      unsigned long *flags) {}
 static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
-static inline void kasan_cache_destroy(struct kmem_cache *cache) {}
+static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
 
 static inline void kasan_poison_slab(struct page *page) {}
 static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index cb09238f6d32..4c26dc3a8295 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -100,16 +100,18 @@
 )
 
 /*
- * Divide positive or negative dividend by positive divisor and round
- * to closest integer. Result is undefined for negative divisors and
- * for negative dividends if the divisor variable type is unsigned.
+ * Divide positive or negative dividend by positive or negative divisor
+ * and round to closest integer. Result is undefined for negative
+ * divisors if he dividend variable type is unsigned and for negative
+ * dividends if the divisor variable type is unsigned.
  */
 #define DIV_ROUND_CLOSEST(x, divisor)(			\
 {							\
 	typeof(x) __x = x;				\
 	typeof(divisor) __d = divisor;			\
 	(((typeof(x))-1) > 0 ||				\
-	 ((typeof(divisor))-1) > 0 || (__x) > 0) ?	\
+	 ((typeof(divisor))-1) > 0 ||			\
+	 (((__x) > 0) == ((__d) > 0))) ?		\
 		(((__x) + ((__d) / 2)) / (__d)) :	\
 		(((__x) - ((__d) / 2)) / (__d));	\
 }							\
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
index 6b784c59f321..394e3d9213b8 100644
--- a/include/linux/lz4.h
+++ b/include/linux/lz4.h
@@ -1,87 +1,648 @@
-#ifndef __LZ4_H__
-#define __LZ4_H__
-/*
- * LZ4 Kernel Interface
+/* LZ4 Kernel Interface
  *
  * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ * Copyright (C) 2016, Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
+ *
+ * This file is based on the original header file
+ * for LZ4 - Fast LZ compression algorithm.
+ *
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2016, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *	* Redistributions of source code must retain the above copyright
+ *	  notice, this list of conditions and the following disclaimer.
+ *	* Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ * You can contact the author at :
+ *	- LZ4 homepage : http://www.lz4.org
+ *	- LZ4 source repository : https://github.com/lz4/lz4
  */
-#define LZ4_MEM_COMPRESS	(16384)
-#define LZ4HC_MEM_COMPRESS	(262144 + (2 * sizeof(unsigned char *)))
 
+#ifndef __LZ4_H__
+#define __LZ4_H__
+
+#include <linux/types.h>
+#include <linux/string.h>	 /* memset, memcpy */
+
+/*-************************************************************************
+ *	CONSTANTS
+ **************************************************************************/
 /*
- * lz4_compressbound()
- * Provides the maximum size that LZ4 may output in a "worst case" scenario
- * (input data not compressible)
+ * LZ4_MEMORY_USAGE :
+ * Memory usage formula : N->2^N Bytes
+ * (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
+ * Increasing memory usage improves compression ratio
+ * Reduced memory usage can improve speed, due to cache effect
+ * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
  */
-static inline size_t lz4_compressbound(size_t isize)
-{
-	return isize + (isize / 255) + 16;
-}
+#define LZ4_MEMORY_USAGE 14
+
+#define LZ4_MAX_INPUT_SIZE	0x7E000000 /* 2 113 929 216 bytes */
+#define LZ4_COMPRESSBOUND(isize)	(\
+	(unsigned int)(isize) > (unsigned int)LZ4_MAX_INPUT_SIZE \
+	? 0 \
+	: (isize) + ((isize)/255) + 16)
+
+#define LZ4_ACCELERATION_DEFAULT 1
+#define LZ4_HASHLOG	 (LZ4_MEMORY_USAGE-2)
+#define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
+#define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG)
+
+#define LZ4HC_MIN_CLEVEL			3
+#define LZ4HC_DEFAULT_CLEVEL			9
+#define LZ4HC_MAX_CLEVEL			16
+
+#define LZ4HC_DICTIONARY_LOGSIZE 16
+#define LZ4HC_MAXD (1<<LZ4HC_DICTIONARY_LOGSIZE)
+#define LZ4HC_MAXD_MASK (LZ4HC_MAXD - 1)
+#define LZ4HC_HASH_LOG (LZ4HC_DICTIONARY_LOGSIZE - 1)
+#define LZ4HC_HASHTABLESIZE (1 << LZ4HC_HASH_LOG)
+#define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1)
+
+/*-************************************************************************
+ *	STREAMING CONSTANTS AND STRUCTURES
+ **************************************************************************/
+#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE - 3)) + 4)
+#define LZ4_STREAMSIZE	(LZ4_STREAMSIZE_U64 * sizeof(unsigned long long))
+
+#define LZ4_STREAMHCSIZE        262192
+#define LZ4_STREAMHCSIZE_SIZET (262192 / sizeof(size_t))
+
+#define LZ4_STREAMDECODESIZE_U64	4
+#define LZ4_STREAMDECODESIZE		 (LZ4_STREAMDECODESIZE_U64 * \
+	sizeof(unsigned long long))
 
 /*
- * lz4_compress()
- *	src     : source address of the original data
- *	src_len : size of the original data
- *	dst	: output buffer address of the compressed data
- *		This requires 'dst' of size LZ4_COMPRESSBOUND.
- *	dst_len : is the output size, which is returned after compress done
- *	workmem : address of the working memory.
- *		This requires 'workmem' of size LZ4_MEM_COMPRESS.
- *	return  : Success if return 0
- *		  Error if return (< 0)
- *	note :  Destination buffer and workmem must be already allocated with
- *		the defined size.
- */
-int lz4_compress(const unsigned char *src, size_t src_len,
-		unsigned char *dst, size_t *dst_len, void *wrkmem);
-
- /*
-  * lz4hc_compress()
-  *	 src	 : source address of the original data
-  *	 src_len : size of the original data
-  *	 dst	 : output buffer address of the compressed data
-  *		This requires 'dst' of size LZ4_COMPRESSBOUND.
-  *	 dst_len : is the output size, which is returned after compress done
-  *	 workmem : address of the working memory.
-  *		This requires 'workmem' of size LZ4HC_MEM_COMPRESS.
-  *	 return  : Success if return 0
-  *		   Error if return (< 0)
-  *	 note :  Destination buffer and workmem must be already allocated with
-  *		 the defined size.
-  */
-int lz4hc_compress(const unsigned char *src, size_t src_len,
-		unsigned char *dst, size_t *dst_len, void *wrkmem);
+ * LZ4_stream_t - information structure to track an LZ4 stream.
+ */
+typedef struct {
+	uint32_t hashTable[LZ4_HASH_SIZE_U32];
+	uint32_t currentOffset;
+	uint32_t initCheck;
+	const uint8_t *dictionary;
+	uint8_t *bufferStart;
+	uint32_t dictSize;
+} LZ4_stream_t_internal;
+typedef union {
+	unsigned long long table[LZ4_STREAMSIZE_U64];
+	LZ4_stream_t_internal internal_donotuse;
+} LZ4_stream_t;
 
 /*
- * lz4_decompress()
- *	src     : source address of the compressed data
- *	src_len : is the input size, whcih is returned after decompress done
- *	dest	: output buffer address of the decompressed data
- *	actual_dest_len: is the size of uncompressed data, supposing it's known
- *	return  : Success if return 0
- *		  Error if return (< 0)
- *	note :  Destination buffer must be already allocated.
- *		slightly faster than lz4_decompress_unknownoutputsize()
- */
-int lz4_decompress(const unsigned char *src, size_t *src_len,
-		unsigned char *dest, size_t actual_dest_len);
+ * LZ4_streamHC_t - information structure to track an LZ4HC stream.
+ */
+typedef struct {
+	unsigned int	 hashTable[LZ4HC_HASHTABLESIZE];
+	unsigned short	 chainTable[LZ4HC_MAXD];
+	/* next block to continue on current prefix */
+	const unsigned char *end;
+	/* All index relative to this position */
+	const unsigned char *base;
+	/* alternate base for extDict */
+	const unsigned char *dictBase;
+	/* below that point, need extDict */
+	unsigned int	 dictLimit;
+	/* below that point, no more dict */
+	unsigned int	 lowLimit;
+	/* index from which to continue dict update */
+	unsigned int	 nextToUpdate;
+	unsigned int	 compressionLevel;
+} LZ4HC_CCtx_internal;
+typedef union {
+	size_t table[LZ4_STREAMHCSIZE_SIZET];
+	LZ4HC_CCtx_internal internal_donotuse;
+} LZ4_streamHC_t;
 
 /*
- * lz4_decompress_unknownoutputsize()
- *	src     : source address of the compressed data
- *	src_len : is the input size, therefore the compressed size
- *	dest	: output buffer address of the decompressed data
- *	dest_len: is the max size of the destination buffer, which is
- *			returned with actual size of decompressed data after
- *			decompress done
- *	return  : Success if return 0
- *		  Error if return (< 0)
- *	note :  Destination buffer must be already allocated.
- */
-int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len,
-		unsigned char *dest, size_t *dest_len);
+ * LZ4_streamDecode_t - information structure to track an
+ *	LZ4 stream during decompression.
+ *
+ * init this structure using LZ4_setStreamDecode (or memset()) before first use
+ */
+typedef struct {
+	const uint8_t *externalDict;
+	size_t extDictSize;
+	const uint8_t *prefixEnd;
+	size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+typedef union {
+	unsigned long long table[LZ4_STREAMDECODESIZE_U64];
+	LZ4_streamDecode_t_internal internal_donotuse;
+} LZ4_streamDecode_t;
+
+/*-************************************************************************
+ *	SIZE OF STATE
+ **************************************************************************/
+#define LZ4_MEM_COMPRESS	LZ4_STREAMSIZE
+#define LZ4HC_MEM_COMPRESS	LZ4_STREAMHCSIZE
+
+/*-************************************************************************
+ *	Compression Functions
+ **************************************************************************/
+
+/**
+ * LZ4_compressBound() - Max. output size in worst case szenarios
+ * @isize: Size of the input data
+ *
+ * Return: Max. size LZ4 may output in a "worst case" szenario
+ * (data not compressible)
+ */
+static inline int LZ4_compressBound(size_t isize)
+{
+	return LZ4_COMPRESSBOUND(isize);
+}
+
+/**
+ * LZ4_compress_default() - Compress data from source to dest
+ * @source: source address of the original data
+ * @dest: output buffer address of the compressed data
+ * @inputSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE
+ * @maxOutputSize: full or partial size of buffer 'dest'
+ *	which must be already allocated
+ * @wrkmem: address of the working memory.
+ *	This requires 'workmem' of LZ4_MEM_COMPRESS.
+ *
+ * Compresses 'sourceSize' bytes from buffer 'source'
+ * into already allocated 'dest' buffer of size 'maxOutputSize'.
+ * Compression is guaranteed to succeed if
+ * 'maxOutputSize' >= LZ4_compressBound(inputSize).
+ * It also runs faster, so it's a recommended setting.
+ * If the function cannot compress 'source' into a more limited 'dest' budget,
+ * compression stops *immediately*, and the function result is zero.
+ * As a consequence, 'dest' content is not valid.
+ *
+ * Return: Number of bytes written into buffer 'dest'
+ *	(necessarily <= maxOutputSize) or 0 if compression fails
+ */
+int LZ4_compress_default(const char *source, char *dest, int inputSize,
+	int maxOutputSize, void *wrkmem);
+
+/**
+ * LZ4_compress_fast() - As LZ4_compress_default providing an acceleration param
+ * @source: source address of the original data
+ * @dest: output buffer address of the compressed data
+ * @inputSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE
+ * @maxOutputSize: full or partial size of buffer 'dest'
+ *	which must be already allocated
+ * @acceleration: acceleration factor
+ * @wrkmem: address of the working memory.
+ *	This requires 'workmem' of LZ4_MEM_COMPRESS.
+ *
+ * Same as LZ4_compress_default(), but allows to select an "acceleration"
+ * factor. The larger the acceleration value, the faster the algorithm,
+ * but also the lesser the compression. It's a trade-off. It can be fine tuned,
+ * with each successive value providing roughly +~3% to speed.
+ * An acceleration value of "1" is the same as regular LZ4_compress_default()
+ * Values <= 0 will be replaced by LZ4_ACCELERATION_DEFAULT, which is 1.
+ *
+ * Return: Number of bytes written into buffer 'dest'
+ *	(necessarily <= maxOutputSize) or 0 if compression fails
+ */
+int LZ4_compress_fast(const char *source, char *dest, int inputSize,
+	int maxOutputSize, int acceleration, void *wrkmem);
+
+/**
+ * LZ4_compress_destSize() - Compress as much data as possible
+ *	from source to dest
+ * @source: source