Ard Biesheuvel 01f688be90 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>
2016-09-13 16:28:15 +01:00

88 lines
2.6 KiB
C

/** @file
Implementation of the EfiSetMem routine. This function is broken
out into its own source file so that it can be excluded from a
build for a 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
http://opensource.org/licenses/bsd-license.php.
THE PROGRAM IS DISTRIBUTED UNDER THE BSD LICENSE ON AN "AS IS" BASIS,
WITHOUT WARRANTIES OR REPRESENTATIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED.
**/
#include "MemLibInternals.h"
/**
Set Buffer to Value for Size bytes.
@param Buffer The memory to set.
@param Length The number of bytes to set.
@param Value The value of the set operation.
@return Buffer
**/
VOID *
EFIAPI
InternalMemSetMem (
OUT VOID *Buffer,
IN UINTN Length,
IN UINT8 Value
)
{
//
// Declare the local variables that actually move the data elements as
// volatile to prevent the optimizer from replacing this function with
// the intrinsic memset()
//
volatile UINT8 *Pointer8;
volatile UINT32 *Pointer32;
volatile UINT64 *Pointer64;
UINT32 Value32;
UINT64 Value64;
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) {
*(Pointer8++) = Value;
}
return Buffer;
}