bucket: correct broken unaligned load/store in armv5

armv5 devices and older (i.e. <= arm9 generation) require addresses that are
stored to and loaded from to to be 4-byte aligned.

If this is not the case the lower 2 bits of the address are cleared and the load
is performed in an unexpected order, including up to 3 bytes of data located
prior to the address.

Inlined buckets are stored after their key in a page and since there is no
guarantee that the key will be of a length that is a multiple of 4, it is
possible for unaligned load/stores to occur when they are cast back to bucket
and page pointer types.

The fix adds a new field to track whether the current architecture exhibits this
issue, sets it on module load for ARM architectures, and then on bucket open, if
this field is set and the address is unaligned, a byte-by-byte copy of the
inlined bucket is performed.

Ref: http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka15414.html

Author: lorenzo-stoakes

bolt_386.go

@@ -5,3 +5,6 @@ const maxMapSize = 0x7FFFFFFF // 2GB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0xFFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

bolt_amd64.go

@@ -5,3 +5,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

bolt_arm.go

@@ -1,7 +1,28 @@
 package bolt
 
+import "unsafe"
+
 // maxMapSize represents the largest mmap size supported by Bolt.
 const maxMapSize = 0x7FFFFFFF // 2GB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0xFFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned bool
+
+func init() {
+	// Simple check to see whether this arch handles unaligned load/stores
+	// correctly.
+
+	// ARM9 and older devices require load/stores to be from/to aligned
+	// addresses. If not, the lower 2 bits are cleared and that address is
+	// read in a jumbled up order.
+
+	// See http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka15414.html
+
+	raw := [6]byte{0xfe, 0xef, 0x11, 0x22, 0x22, 0x11}
+	val := *(*uint32)(unsafe.Pointer(uintptr(unsafe.Pointer(&raw)) + 2))
+
+	brokenUnaligned = val != 0x11222211
+}

bolt_arm64.go

@@ -7,3 +7,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

bolt_ppc64le.go

@@ -7,3 +7,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

bolt_s390x.go

@@ -7,3 +7,6 @@ const maxMapSize = 0xFFFFFFFFFFFF // 256TB
 
 // maxAllocSize is the size used when creating array pointers.
 const maxAllocSize = 0x7FFFFFFF
+
+// Are unaligned load/stores broken on this arch?
+var brokenUnaligned = false

bucket.go

@@ -130,9 +130,17 @@ func (b *Bucket) Bucket(name []byte) *Bucket {
 func (b *Bucket) openBucket(value []byte) *Bucket {
 	var child = newBucket(b.tx)
 
+	// If unaligned load/stores are broken on this arch and value is
+	// unaligned simply clone to an aligned byte array.
+	unaligned := brokenUnaligned && uintptr(unsafe.Pointer(&value[0]))&3 != 0
+
+	if unaligned {
+		value = cloneBytes(value)
+	}
+
 	// If this is a writable transaction then we need to copy the bucket entry.
 	// Read-only transactions can point directly at the mmap entry.
-	if b.tx.writable {
+	if b.tx.writable && !unaligned {
 		child.bucket = &bucket{}
 		*child.bucket = *(*bucket)(unsafe.Pointer(&value[0]))
 	} else {