Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "Subsystems affected by this patch series: mm/hotfixes, lz4, exec,
  mailmap, mm/thp, autofs, sysctl, mm/kmemleak, mm/misc and lib"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (35 commits)
  virtio: pci: constify ioreadX() iomem argument (as in generic implementation)
  ntb: intel: constify ioreadX() iomem argument (as in generic implementation)
  rtl818x: constify ioreadX() iomem argument (as in generic implementation)
  iomap: constify ioreadX() iomem argument (as in generic implementation)
  sh: use generic strncpy()
  sh: clkfwk: remove r8/r16/r32
  include/asm-generic/vmlinux.lds.h: align ro_after_init
  mm: annotate a data race in page_zonenum()
  mm/swap.c: annotate data races for lru_rotate_pvecs
  mm/rmap: annotate a data race at tlb_flush_batched
  mm/mempool: fix a data race in mempool_free()
  mm/list_lru: fix a data race in list_lru_count_one
  mm/memcontrol: fix a data race in scan count
  mm/page_counter: fix various data races at memsw
  mm/swapfile: fix and annotate various data races
  mm/filemap.c: fix a data race in filemap_fault()
  mm/swap_state: mark various intentional data races
  mm/page_io: mark various intentional data races
  mm/frontswap: mark various intentional data races
  mm/kmemleak: silence KCSAN splats in checksum
  ...

5 files changed, 37 insertions, 27 deletions

diff --git a/lib/iomap.c b/lib/iomap.c
index e909ab71e995..fbaa3e8f19d6 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -70,27 +70,27 @@ static void bad_io_access(unsigned long port, const char *access)
 #define mmio_read64be(addr) swab64(readq(addr))
 #endif
 
-unsigned int ioread8(void __iomem *addr)
+unsigned int ioread8(const void __iomem *addr)
 {
 	IO_COND(addr, return inb(port), return readb(addr));
 	return 0xff;
 }
-unsigned int ioread16(void __iomem *addr)
+unsigned int ioread16(const void __iomem *addr)
 {
 	IO_COND(addr, return inw(port), return readw(addr));
 	return 0xffff;
 }
-unsigned int ioread16be(void __iomem *addr)
+unsigned int ioread16be(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read16be(port), return mmio_read16be(addr));
 	return 0xffff;
 }
-unsigned int ioread32(void __iomem *addr)
+unsigned int ioread32(const void __iomem *addr)
 {
 	IO_COND(addr, return inl(port), return readl(addr));
 	return 0xffffffff;
 }
-unsigned int ioread32be(void __iomem *addr)
+unsigned int ioread32be(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read32be(port), return mmio_read32be(addr));
 	return 0xffffffff;
@@ -142,26 +142,26 @@ static u64 pio_read64be_hi_lo(unsigned long port)
 	return lo | (hi << 32);
 }
 
-u64 ioread64_lo_hi(void __iomem *addr)
+u64 ioread64_lo_hi(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64_lo_hi(port), return readq(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64_hi_lo(void __iomem *addr)
+u64 ioread64_hi_lo(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64_hi_lo(port), return readq(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64be_lo_hi(void __iomem *addr)
+u64 ioread64be_lo_hi(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64be_lo_hi(port),
 		return mmio_read64be(addr));
 	return 0xffffffffffffffffULL;
 }
 
-u64 ioread64be_hi_lo(void __iomem *addr)
+u64 ioread64be_hi_lo(const void __iomem *addr)
 {
 	IO_COND(addr, return pio_read64be_hi_lo(port),
 		return mmio_read64be(addr));
@@ -275,7 +275,7 @@ EXPORT_SYMBOL(iowrite64be_hi_lo);
  * order" (we also don't have IO barriers).
  */
 #ifndef mmio_insb
-static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
+static inline void mmio_insb(const void __iomem *addr, u8 *dst, int count)
 {
 	while (--count >= 0) {
 		u8 data = __raw_readb(addr);
@@ -283,7 +283,7 @@ static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
 		dst++;
 	}
 }
-static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
+static inline void mmio_insw(const void __iomem *addr, u16 *dst, int count)
 {
 	while (--count >= 0) {
 		u16 data = __raw_readw(addr);
@@ -291,7 +291,7 @@ static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
 		dst++;
 	}
 }
-static inline void mmio_insl(void __iomem *addr, u32 *dst, int count)
+static inline void mmio_insl(const void __iomem *addr, u32 *dst, int count)
 {
 	while (--count >= 0) {
 		u32 data = __raw_readl(addr);
@@ -325,15 +325,15 @@ static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count)
 }
 #endif
 
-void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insb(port,dst,count), mmio_insb(addr, dst, count));
 }
-void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insw(port,dst,count), mmio_insw(addr, dst, count));
 }
-void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count)
 {
 	IO_COND(addr, insl(port,dst,count), mmio_insl(addr, dst, count));
 }
diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c
index cc7b6d4cc7c7..90bb67994688 100644
--- a/lib/lz4/lz4_compress.c
+++ b/lib/lz4/lz4_compress.c
@@ -446,7 +446,7 @@ _last_literals:
 			*op++ = (BYTE)(lastRun << ML_BITS);
 		}
 
-		memcpy(op, anchor, lastRun);
+		LZ4_memcpy(op, anchor, lastRun);
 
 		op += lastRun;
 	}
@@ -708,7 +708,7 @@ _last_literals:
 		} else {
 			*op++ = (BYTE)(lastRunSize<<ML_BITS);
 		}
-		memcpy(op, anchor, lastRunSize);
+		LZ4_memcpy(op, anchor, lastRunSize);
 		op += lastRunSize;
 	}
 
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index 5371dab6b481..00cb0d0b73e1 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -153,7 +153,7 @@ static FORCE_INLINE int LZ4_decompress_generic(
 		   && likely((endOnInput ? ip < shortiend : 1) &
 			     (op <= shortoend))) {
 			/* Copy the literals */
-			memcpy(op, ip, endOnInput ? 16 : 8);
+			LZ4_memcpy(op, ip, endOnInput ? 16 : 8);
 			op += length; ip += length;
 
 			/*
@@ -172,9 +172,9 @@ static FORCE_INLINE int LZ4_decompress_generic(
 			    (offset >= 8) &&
 			    (dict == withPrefix64k || match >= lowPrefix)) {
 				/* Copy the match. */
-				memcpy(op + 0, match + 0, 8);
-				memcpy(op + 8, match + 8, 8);
-				memcpy(op + 16, match + 16, 2);
+				LZ4_memcpy(op + 0, match + 0, 8);
+				LZ4_memcpy(op + 8, match + 8, 8);
+				LZ4_memcpy(op + 16, match + 16, 2);
 				op += length + MINMATCH;
 				/* Both stages worked, load the next token. */
 				continue;
@@ -263,7 +263,7 @@ static FORCE_INLINE int LZ4_decompress_generic(
 				}
 			}
 
-			memcpy(op, ip, length);
+			LZ4_memcpy(op, ip, length);
 			ip += length;
 			op += length;
 
@@ -350,7 +350,7 @@ _copy_match:
 				size_t const copySize = (size_t)(lowPrefix - match);
 				size_t const restSize = length - copySize;
 
-				memcpy(op, dictEnd - copySize, copySize);
+				LZ4_memcpy(op, dictEnd - copySize, copySize);
 				op += copySize;
 				if (restSize > (size_t)(op - lowPrefix)) {
 					/* overlap copy */
@@ -360,7 +360,7 @@ _copy_match:
 					while (op < endOfMatch)
 						*op++ = *copyFrom++;
 				} else {
-					memcpy(op, lowPrefix, restSize);
+					LZ4_memcpy(op, lowPrefix, restSize);
 					op += restSize;
 				}
 			}
@@ -386,7 +386,7 @@ _copy_match:
 				while (op < copyEnd)
 					*op++ = *match++;
 			} else {
-				memcpy(op, match, mlen);
+				LZ4_memcpy(op, match, mlen);
 			}
 			op = copyEnd;
 			if (op == oend)
@@ -400,7 +400,7 @@ _copy_match:
 			op[2] = match[2];
 			op[3] = match[3];
 			match += inc32table[offset];
-			memcpy(op + 4, match, 4);
+			LZ4_memcpy(op + 4, match, 4);
 			match -= dec64table[offset];
 		} else {
 			LZ4_copy8(op, match);
diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h
index 1a7fa9d9170f..c91dd96ef629 100644
--- a/lib/lz4/lz4defs.h
+++ b/lib/lz4/lz4defs.h
@@ -137,6 +137,16 @@ static FORCE_INLINE void LZ4_writeLE16(void *memPtr, U16 value)
 	return put_unaligned_le16(value, memPtr);
 }
 
+/*
+ * LZ4 relies on memcpy with a constant size being inlined. In freestanding
+ * environments, the compiler can't assume the implementation of memcpy() is
+ * standard compliant, so apply its specialized memcpy() inlining logic. When
+ * possible, use __builtin_memcpy() to tell the compiler to analyze memcpy()
+ * as-if it were standard compliant, so it can inline it in freestanding
+ * environments. This is needed when decompressing the Linux Kernel, for example.
+ */
+#define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
+
 static FORCE_INLINE void LZ4_copy8(void *dst, const void *src)
 {
 #if LZ4_ARCH64
diff --git a/lib/lz4/lz4hc_compress.c b/lib/lz4/lz4hc_compress.c
index 1b61d874e337..e7ac8694b797 100644
--- a/lib/lz4/lz4hc_compress.c
+++ b/lib/lz4/lz4hc_compress.c
@@ -570,7 +570,7 @@ _Search3:
 			*op++ = (BYTE) lastRun;
 		} else
 			*op++ = (BYTE)(lastRun<<ML_BITS);
-		memcpy(op, anchor, iend - anchor);
+		LZ4_memcpy(op, anchor, iend - anchor);
 		op += iend - anchor;
 	}