d7aef8be96
When setting the size of a PCI BAR, the kernel only supports powers of two (as per the PCI spec). Previously, the size was incorrectly read by the kernel, and the address ranges assigned to the PCI devices could overlap, resulting in gem5 crashes. We now round up to the next power of two. Kudos to Sergei Trofimov who helped to debug this issue! Change-Id: I54ca399b62ea07c09d4cd989b17dfa670e841bbe Reviewed-by: Anouk Van Laer <anouk.vanlaer@arm.com> Reviewed-by: Sergei Trofimov <sergei.trofimov@arm.com> Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/2580 Reviewed-by: Paul Rosenfeld <prosenfeld@micron.com>
251 lines
6.9 KiB
C++
251 lines
6.9 KiB
C++
/*
|
|
* Copyright (c) 2017 ARM Limited
|
|
* All rights reserved
|
|
*
|
|
* The license below extends only to copyright in the software and shall
|
|
* not be construed as granting a license to any other intellectual
|
|
* property including but not limited to intellectual property relating
|
|
* to a hardware implementation of the functionality of the software
|
|
* licensed hereunder. You may use the software subject to the license
|
|
* terms below provided that you ensure that this notice is replicated
|
|
* unmodified and in its entirety in all distributions of the software,
|
|
* modified or unmodified, in source code or in binary form.
|
|
*
|
|
* Copyright (c) 2003-2005 The Regents of The University of Michigan
|
|
* All rights reserved.
|
|
*
|
|
* 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;
|
|
* neither the name of the copyright holders nor the names of its
|
|
* contributors may be used to endorse or promote products derived from
|
|
* this software without specific prior written permission.
|
|
*
|
|
* 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.
|
|
*
|
|
* Authors: Steve Reinhardt
|
|
* Nathan Binkert
|
|
*/
|
|
|
|
#ifndef __BASE_BITFIELD_HH__
|
|
#define __BASE_BITFIELD_HH__
|
|
|
|
#include <inttypes.h>
|
|
|
|
/**
|
|
* Generate a 64-bit mask of 'nbits' 1s, right justified.
|
|
*/
|
|
inline uint64_t
|
|
mask(int nbits)
|
|
{
|
|
return (nbits == 64) ? (uint64_t)-1LL : (1ULL << nbits) - 1;
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
* Extract the bitfield from position 'first' to 'last' (inclusive)
|
|
* from 'val' and right justify it. MSB is numbered 63, LSB is 0.
|
|
*/
|
|
template <class T>
|
|
inline
|
|
T
|
|
bits(T val, int first, int last)
|
|
{
|
|
int nbits = first - last + 1;
|
|
return (val >> last) & mask(nbits);
|
|
}
|
|
|
|
/**
|
|
* Extract the bit from this position from 'val' and right justify it.
|
|
*/
|
|
template <class T>
|
|
inline
|
|
T
|
|
bits(T val, int bit)
|
|
{
|
|
return bits(val, bit, bit);
|
|
}
|
|
|
|
/**
|
|
* Mask off the given bits in place like bits() but without shifting.
|
|
* msb = 63, lsb = 0
|
|
*/
|
|
template <class T>
|
|
inline
|
|
T
|
|
mbits(T val, int first, int last)
|
|
{
|
|
return val & (mask(first+1) & ~mask(last));
|
|
}
|
|
|
|
inline uint64_t
|
|
mask(int first, int last)
|
|
{
|
|
return mbits((uint64_t)-1LL, first, last);
|
|
}
|
|
|
|
/**
|
|
* Sign-extend an N-bit value to 64 bits.
|
|
*/
|
|
template <int N>
|
|
inline
|
|
uint64_t
|
|
sext(uint64_t val)
|
|
{
|
|
int sign_bit = bits(val, N-1, N-1);
|
|
return sign_bit ? (val | ~mask(N)) : val;
|
|
}
|
|
|
|
/**
|
|
* Return val with bits first to last set to bit_val
|
|
*/
|
|
template <class T, class B>
|
|
inline
|
|
T
|
|
insertBits(T val, int first, int last, B bit_val)
|
|
{
|
|
T t_bit_val = bit_val;
|
|
T bmask = mask(first - last + 1) << last;
|
|
return ((t_bit_val << last) & bmask) | (val & ~bmask);
|
|
}
|
|
|
|
/**
|
|
* Overloaded for access to only one bit in value
|
|
*/
|
|
template <class T, class B>
|
|
inline
|
|
T
|
|
insertBits(T val, int bit, B bit_val)
|
|
{
|
|
return insertBits(val, bit, bit, bit_val);
|
|
}
|
|
|
|
/**
|
|
* A convenience function to replace bits first to last of val with bit_val
|
|
* in place.
|
|
*/
|
|
template <class T, class B>
|
|
inline
|
|
void
|
|
replaceBits(T& val, int first, int last, B bit_val)
|
|
{
|
|
val = insertBits(val, first, last, bit_val);
|
|
}
|
|
|
|
/** Overloaded function to allow to access only 1 bit*/
|
|
template <class T, class B>
|
|
inline
|
|
void
|
|
replaceBits(T& val, int bit, B bit_val)
|
|
{
|
|
val = insertBits(val, bit, bit, bit_val);
|
|
}
|
|
/**
|
|
* Returns the bit position of the MSB that is set in the input
|
|
*/
|
|
inline
|
|
int
|
|
findMsbSet(uint64_t val) {
|
|
int msb = 0;
|
|
if (!val)
|
|
return 0;
|
|
if (bits(val, 63,32)) { msb += 32; val >>= 32; }
|
|
if (bits(val, 31,16)) { msb += 16; val >>= 16; }
|
|
if (bits(val, 15,8)) { msb += 8; val >>= 8; }
|
|
if (bits(val, 7,4)) { msb += 4; val >>= 4; }
|
|
if (bits(val, 3,2)) { msb += 2; val >>= 2; }
|
|
if (bits(val, 1,1)) { msb += 1; }
|
|
return msb;
|
|
}
|
|
|
|
/**
|
|
* Returns the bit position of the LSB that is set in the input
|
|
*/
|
|
inline int
|
|
findLsbSet(uint64_t val) {
|
|
int lsb = 0;
|
|
if (!val)
|
|
return sizeof(val) * 8;
|
|
if (!bits(val, 31,0)) { lsb += 32; val >>= 32; }
|
|
if (!bits(val, 15,0)) { lsb += 16; val >>= 16; }
|
|
if (!bits(val, 7,0)) { lsb += 8; val >>= 8; }
|
|
if (!bits(val, 3,0)) { lsb += 4; val >>= 4; }
|
|
if (!bits(val, 1,0)) { lsb += 2; val >>= 2; }
|
|
if (!bits(val, 0,0)) { lsb += 1; }
|
|
return lsb;
|
|
}
|
|
|
|
/**
|
|
* Checks if a number is a power of two, or zero.
|
|
*/
|
|
template <class T>
|
|
inline bool
|
|
isPow2(T v) {
|
|
return (v & (v - 1)) == (T)0;
|
|
}
|
|
|
|
/**
|
|
* Returns the number of set ones in the provided value.
|
|
* PD algorithm from
|
|
* http://graphics.stanford.edu/~seander/bithacks.html#CountBitsSetParallel
|
|
*/
|
|
inline int
|
|
popCount(uint64_t val) {
|
|
#ifndef __has_builtin
|
|
#define __has_builtin(foo) 0
|
|
#endif
|
|
#if defined(__GNUC__) || (defined(__clang__) && __has_builtin(__builtin_popcountl))
|
|
return __builtin_popcountl(val);
|
|
#else
|
|
const uint64_t m1 = 0x5555555555555555; // ..010101b
|
|
const uint64_t m2 = 0x3333333333333333; // ..110011b
|
|
const uint64_t m4 = 0x0f0f0f0f0f0f0f0f; // ..001111b
|
|
const uint64_t sum = 0x0101010101010101;
|
|
|
|
val -= (val >> 1) & m1; // 2 bits count -> 2 bits
|
|
val = (val & m2) + ((val >> 2) & m2); // 4 bits count -> 4 bits
|
|
val = (val + (val >> 4)) & m4; // 8 bits count -> 8 bits
|
|
return (val * sum) >> 56; // horizontal sum
|
|
#endif // defined(__GNUC__) || (defined(__clang__) && __has_builtin(__builtin_popcountl))
|
|
}
|
|
|
|
/**
|
|
* Align to the next highest power of two.
|
|
*
|
|
* The number passed in is aligned to the next highest power of two,
|
|
* if it is not already a power of two. Please note that if 0 is
|
|
* passed in, 0 is returned.
|
|
*
|
|
* This code has been modified from the following:
|
|
* http://graphics.stanford.edu/~seander/bithacks.html#RoundUpPowerOf2
|
|
*/
|
|
inline uint64_t alignToPowerOfTwo(uint64_t val)
|
|
{
|
|
val--;
|
|
val |= val >> 1;
|
|
val |= val >> 2;
|
|
val |= val >> 4;
|
|
val |= val >> 8;
|
|
val |= val >> 16;
|
|
val |= val >> 32;
|
|
val++;
|
|
|
|
return val;
|
|
};
|
|
|
|
#endif // __BASE_BITFIELD_HH__
|