mirror of https://github.com/acidanthera/audk.git
MdePkg/BaseMemoryLib: widen aligned accesses to 32 or 64 bits
Since the default BaseMemoryLib should be callable from any context, including ones where unaligned accesses are not allowed, it implements InternalCopyMem() and InternalSetMem() using byte accesses only. However, especially in a context where the MMU is off, such narrow accesses may be disproportionately costly, and so if the size and alignment of the access allow it, use 32-bit or even 64-bit loads and stores (the latter may be beneficial even on a 32-bit architectures like ARM, which has load pair/store pair instructions) Contributed-under: TianoCore Contribution Agreement 1.0 Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Reviewed-by: Liming Gao <liming.gao@intel.com>
This commit is contained in:
parent
94a3845be6
commit
01f688be90
|
@ -26,7 +26,7 @@
|
|||
|
||||
|
||||
#
|
||||
# VALID_ARCHITECTURES = IA32 X64 IPF EBC
|
||||
# VALID_ARCHITECTURES = IA32 X64 IPF EBC ARM AARCH64
|
||||
#
|
||||
|
||||
[Sources]
|
||||
|
|
|
@ -4,6 +4,9 @@
|
|||
particular platform easily if an optimized version is desired.
|
||||
|
||||
Copyright (c) 2006 - 2010, Intel Corporation. All rights reserved.<BR>
|
||||
Copyright (c) 2012 - 2013, ARM Ltd. All rights reserved.<BR>
|
||||
Copyright (c) 2016, Linaro Ltd. All rights reserved.<BR>
|
||||
|
||||
This program and the accompanying materials
|
||||
are licensed and made available under the terms and conditions of the BSD License
|
||||
which accompanies this distribution. The full text of the license may be found at
|
||||
|
@ -44,18 +47,107 @@ InternalMemCopyMem (
|
|||
//
|
||||
volatile UINT8 *Destination8;
|
||||
CONST UINT8 *Source8;
|
||||
volatile UINT32 *Destination32;
|
||||
CONST UINT32 *Source32;
|
||||
volatile UINT64 *Destination64;
|
||||
CONST UINT64 *Source64;
|
||||
UINTN Alignment;
|
||||
|
||||
if (SourceBuffer > DestinationBuffer) {
|
||||
Destination8 = (UINT8*)DestinationBuffer;
|
||||
Source8 = (CONST UINT8*)SourceBuffer;
|
||||
while (Length-- != 0) {
|
||||
*(Destination8++) = *(Source8++);
|
||||
if ((((UINTN)DestinationBuffer & 0x7) == 0) && (((UINTN)SourceBuffer & 0x7) == 0) && (Length >= 8)) {
|
||||
if (SourceBuffer > DestinationBuffer) {
|
||||
Destination64 = (UINT64*)DestinationBuffer;
|
||||
Source64 = (CONST UINT64*)SourceBuffer;
|
||||
while (Length >= 8) {
|
||||
*(Destination64++) = *(Source64++);
|
||||
Length -= 8;
|
||||
}
|
||||
|
||||
// Finish if there are still some bytes to copy
|
||||
Destination8 = (UINT8*)Destination64;
|
||||
Source8 = (CONST UINT8*)Source64;
|
||||
while (Length-- != 0) {
|
||||
*(Destination8++) = *(Source8++);
|
||||
}
|
||||
} else if (SourceBuffer < DestinationBuffer) {
|
||||
Destination64 = (UINT64*)((UINTN)DestinationBuffer + Length);
|
||||
Source64 = (CONST UINT64*)((UINTN)SourceBuffer + Length);
|
||||
|
||||
// Destination64 and Source64 were aligned on a 64-bit boundary
|
||||
// but if length is not a multiple of 8 bytes then they won't be
|
||||
// anymore.
|
||||
|
||||
Alignment = Length & 0x7;
|
||||
if (Alignment != 0) {
|
||||
Destination8 = (UINT8*)Destination64;
|
||||
Source8 = (CONST UINT8*)Source64;
|
||||
|
||||
while (Alignment-- != 0) {
|
||||
*(--Destination8) = *(--Source8);
|
||||
--Length;
|
||||
}
|
||||
Destination64 = (UINT64*)Destination8;
|
||||
Source64 = (CONST UINT64*)Source8;
|
||||
}
|
||||
|
||||
while (Length > 0) {
|
||||
*(--Destination64) = *(--Source64);
|
||||
Length -= 8;
|
||||
}
|
||||
}
|
||||
} else if (SourceBuffer < DestinationBuffer) {
|
||||
Destination8 = (UINT8*)DestinationBuffer + Length;
|
||||
Source8 = (CONST UINT8*)SourceBuffer + Length;
|
||||
while (Length-- != 0) {
|
||||
*(--Destination8) = *(--Source8);
|
||||
} else if ((((UINTN)DestinationBuffer & 0x3) == 0) && (((UINTN)SourceBuffer & 0x3) == 0) && (Length >= 4)) {
|
||||
if (SourceBuffer > DestinationBuffer) {
|
||||
Destination32 = (UINT32*)DestinationBuffer;
|
||||
Source32 = (CONST UINT32*)SourceBuffer;
|
||||
while (Length >= 4) {
|
||||
*(Destination32++) = *(Source32++);
|
||||
Length -= 4;
|
||||
}
|
||||
|
||||
// Finish if there are still some bytes to copy
|
||||
Destination8 = (UINT8*)Destination32;
|
||||
Source8 = (CONST UINT8*)Source32;
|
||||
while (Length-- != 0) {
|
||||
*(Destination8++) = *(Source8++);
|
||||
}
|
||||
} else if (SourceBuffer < DestinationBuffer) {
|
||||
Destination32 = (UINT32*)((UINTN)DestinationBuffer + Length);
|
||||
Source32 = (CONST UINT32*)((UINTN)SourceBuffer + Length);
|
||||
|
||||
// Destination32 and Source32 were aligned on a 32-bit boundary
|
||||
// but if length is not a multiple of 4 bytes then they won't be
|
||||
// anymore.
|
||||
|
||||
Alignment = Length & 0x3;
|
||||
if (Alignment != 0) {
|
||||
Destination8 = (UINT8*)Destination32;
|
||||
Source8 = (CONST UINT8*)Source32;
|
||||
|
||||
while (Alignment-- != 0) {
|
||||
*(--Destination8) = *(--Source8);
|
||||
--Length;
|
||||
}
|
||||
Destination32 = (UINT32*)Destination8;
|
||||
Source32 = (CONST UINT32*)Source8;
|
||||
}
|
||||
|
||||
while (Length > 0) {
|
||||
*(--Destination32) = *(--Source32);
|
||||
Length -= 4;
|
||||
}
|
||||
}
|
||||
} else {
|
||||
if (SourceBuffer > DestinationBuffer) {
|
||||
Destination8 = (UINT8*)DestinationBuffer;
|
||||
Source8 = (CONST UINT8*)SourceBuffer;
|
||||
while (Length-- != 0) {
|
||||
*(Destination8++) = *(Source8++);
|
||||
}
|
||||
} else if (SourceBuffer < DestinationBuffer) {
|
||||
Destination8 = (UINT8*)DestinationBuffer + Length;
|
||||
Source8 = (CONST UINT8*)SourceBuffer + Length;
|
||||
while (Length-- != 0) {
|
||||
*(--Destination8) = *(--Source8);
|
||||
}
|
||||
}
|
||||
}
|
||||
return DestinationBuffer;
|
||||
|
|
|
@ -5,6 +5,9 @@
|
|||
is desired.
|
||||
|
||||
Copyright (c) 2006 - 2010, Intel Corporation. All rights reserved.<BR>
|
||||
Copyright (c) 2012 - 2013, ARM Ltd. All rights reserved.<BR>
|
||||
Copyright (c) 2016, Linaro Ltd. All rights reserved.<BR>
|
||||
|
||||
This program and the accompanying materials
|
||||
are licensed and made available under the terms and conditions of the BSD License
|
||||
which accompanies this distribution. The full text of the license may be found at
|
||||
|
@ -43,11 +46,42 @@ InternalMemSetMem (
|
|||
// volatile to prevent the optimizer from replacing this function with
|
||||
// the intrinsic memset()
|
||||
//
|
||||
volatile UINT8 *Pointer;
|
||||
volatile UINT8 *Pointer8;
|
||||
volatile UINT32 *Pointer32;
|
||||
volatile UINT64 *Pointer64;
|
||||
UINT32 Value32;
|
||||
UINT64 Value64;
|
||||
|
||||
Pointer = (UINT8*)Buffer;
|
||||
if ((((UINTN)Buffer & 0x7) == 0) && (Length >= 8)) {
|
||||
// Generate the 64bit value
|
||||
Value32 = (Value << 24) | (Value << 16) | (Value << 8) | Value;
|
||||
Value64 = LShiftU64 (Value32, 32) | Value32;
|
||||
|
||||
Pointer64 = (UINT64*)Buffer;
|
||||
while (Length >= 8) {
|
||||
*(Pointer64++) = Value64;
|
||||
Length -= 8;
|
||||
}
|
||||
|
||||
// Finish with bytes if needed
|
||||
Pointer8 = (UINT8*)Pointer64;
|
||||
} else if ((((UINTN)Buffer & 0x3) == 0) && (Length >= 4)) {
|
||||
// Generate the 32bit value
|
||||
Value32 = (Value << 24) | (Value << 16) | (Value << 8) | Value;
|
||||
|
||||
Pointer32 = (UINT32*)Buffer;
|
||||
while (Length >= 4) {
|
||||
*(Pointer32++) = Value32;
|
||||
Length -= 4;
|
||||
}
|
||||
|
||||
// Finish with bytes if needed
|
||||
Pointer8 = (UINT8*)Pointer32;
|
||||
} else {
|
||||
Pointer8 = (UINT8*)Buffer;
|
||||
}
|
||||
while (Length-- > 0) {
|
||||
*(Pointer++) = Value;
|
||||
*(Pointer8++) = Value;
|
||||
}
|
||||
return Buffer;
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue