OpenCloudOS-Kernel/lib/bitmap.c

1188 lines
35 KiB
C
Raw Normal View History

/*
* lib/bitmap.c
* Helper functions for bitmap.h.
*
* This source code is licensed under the GNU General Public License,
* Version 2. See the file COPYING for more details.
*/
#include <linux/export.h>
#include <linux/thread_info.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/bug.h>
#include <asm/uaccess.h>
/*
* bitmaps provide an array of bits, implemented using an an
* array of unsigned longs. The number of valid bits in a
* given bitmap does _not_ need to be an exact multiple of
* BITS_PER_LONG.
*
* The possible unused bits in the last, partially used word
* of a bitmap are 'don't care'. The implementation makes
* no particular effort to keep them zero. It ensures that
* their value will not affect the results of any operation.
* The bitmap operations that return Boolean (bitmap_empty,
* for example) or scalar (bitmap_weight, for example) results
* carefully filter out these unused bits from impacting their
* results.
*
* These operations actually hold to a slightly stronger rule:
* if you don't input any bitmaps to these ops that have some
* unused bits set, then they won't output any set unused bits
* in output bitmaps.
*
* The byte ordering of bitmaps is more natural on little
* endian architectures. See the big-endian headers
* include/asm-ppc64/bitops.h and include/asm-s390/bitops.h
* for the best explanations of this ordering.
*/
lib: bitmap: make nbits parameter of bitmap_empty unsigned Many functions in lib/bitmap.c start with an expression such as lim = bits/BITS_PER_LONG. Since bits has type (signed) int, and since gcc cannot know that it is in fact non-negative, it generates worse code than it could. These patches, mostly consisting of changing various parameters to unsigned, gives a slight overall code reduction: add/remove: 1/1 grow/shrink: 8/16 up/down: 251/-414 (-163) function old new delta tick_device_uses_broadcast 335 425 +90 __irq_alloc_descs 498 554 +56 __bitmap_andnot 73 115 +42 __bitmap_and 70 101 +31 bitmap_weight - 11 +11 copy_hugetlb_page_range 752 762 +10 follow_hugetlb_page 846 854 +8 hugetlb_init 1415 1417 +2 hugetlb_nrpages_setup 130 131 +1 hugetlb_add_hstate 377 376 -1 bitmap_allocate_region 82 80 -2 select_task_rq_fair 2202 2191 -11 hweight_long 66 55 -11 __reg_op 230 219 -11 dm_stats_message 2849 2833 -16 bitmap_parselist 92 74 -18 __bitmap_weight 115 97 -18 __bitmap_subset 153 129 -24 __bitmap_full 128 104 -24 __bitmap_empty 120 96 -24 bitmap_set 179 149 -30 bitmap_clear 185 155 -30 __bitmap_equal 136 105 -31 __bitmap_intersects 148 108 -40 __bitmap_complement 109 67 -42 tick_device_setup_broadcast_func.isra 81 - -81 [The increases in __bitmap_and{,not} are due to bug fixes 17/18,18/18. No idea why bitmap_weight suddenly appears.] While 163 bytes treewide is insignificant, I believe the bitmap functions are often called with locks held, so saving even a few cycles might be worth it. While making these changes, I found a few other things that might be worth including. 16,17,18 are actual bug fixes. The rest shouldn't change the behaviour of any of the functions, provided no-one passed negative nbits values. If something should come up, it should be fairly bisectable. A few issues I thought about, but didn't know what to do with: * Many of the functions misbehave if nbits is compile-time 0; the out-of-line functions generally handle 0 correctly. bitmap_fill() is particularly bad, whether the 0 is known at compile time or not. It would probably be nice to add detection of at least compile-time 0 and handle that appropriately. * I didn't change __bitmap_shift_{left,right} to use unsigned because I want to fully understand why the algorithm works before making that change. However, AFAICT, they behave correctly for all (positive) shift amounts. This is not the case for the small_const_nbits versions. If for example nbits = n = BITS_PER_LONG, the shift operators turn into no-ops (at least on x86), so one get *dst = *src, whereas one would expect to get *dst=0. That difference in behaviour is somewhat annoying. This patch (of 18): The compiler can generate slightly smaller and simpler code when it knows that "nbits" is non-negative. Since no-one passes a negative bit-count, this shouldn't affect the semantics. Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:09:49 +08:00
int __bitmap_empty(const unsigned long *bitmap, unsigned int bits)
{
lib: bitmap: make nbits parameter of bitmap_empty unsigned Many functions in lib/bitmap.c start with an expression such as lim = bits/BITS_PER_LONG. Since bits has type (signed) int, and since gcc cannot know that it is in fact non-negative, it generates worse code than it could. These patches, mostly consisting of changing various parameters to unsigned, gives a slight overall code reduction: add/remove: 1/1 grow/shrink: 8/16 up/down: 251/-414 (-163) function old new delta tick_device_uses_broadcast 335 425 +90 __irq_alloc_descs 498 554 +56 __bitmap_andnot 73 115 +42 __bitmap_and 70 101 +31 bitmap_weight - 11 +11 copy_hugetlb_page_range 752 762 +10 follow_hugetlb_page 846 854 +8 hugetlb_init 1415 1417 +2 hugetlb_nrpages_setup 130 131 +1 hugetlb_add_hstate 377 376 -1 bitmap_allocate_region 82 80 -2 select_task_rq_fair 2202 2191 -11 hweight_long 66 55 -11 __reg_op 230 219 -11 dm_stats_message 2849 2833 -16 bitmap_parselist 92 74 -18 __bitmap_weight 115 97 -18 __bitmap_subset 153 129 -24 __bitmap_full 128 104 -24 __bitmap_empty 120 96 -24 bitmap_set 179 149 -30 bitmap_clear 185 155 -30 __bitmap_equal 136 105 -31 __bitmap_intersects 148 108 -40 __bitmap_complement 109 67 -42 tick_device_setup_broadcast_func.isra 81 - -81 [The increases in __bitmap_and{,not} are due to bug fixes 17/18,18/18. No idea why bitmap_weight suddenly appears.] While 163 bytes treewide is insignificant, I believe the bitmap functions are often called with locks held, so saving even a few cycles might be worth it. While making these changes, I found a few other things that might be worth including. 16,17,18 are actual bug fixes. The rest shouldn't change the behaviour of any of the functions, provided no-one passed negative nbits values. If something should come up, it should be fairly bisectable. A few issues I thought about, but didn't know what to do with: * Many of the functions misbehave if nbits is compile-time 0; the out-of-line functions generally handle 0 correctly. bitmap_fill() is particularly bad, whether the 0 is known at compile time or not. It would probably be nice to add detection of at least compile-time 0 and handle that appropriately. * I didn't change __bitmap_shift_{left,right} to use unsigned because I want to fully understand why the algorithm works before making that change. However, AFAICT, they behave correctly for all (positive) shift amounts. This is not the case for the small_const_nbits versions. If for example nbits = n = BITS_PER_LONG, the shift operators turn into no-ops (at least on x86), so one get *dst = *src, whereas one would expect to get *dst=0. That difference in behaviour is somewhat annoying. This patch (of 18): The compiler can generate slightly smaller and simpler code when it knows that "nbits" is non-negative. Since no-one passes a negative bit-count, this shouldn't affect the semantics. Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:09:49 +08:00
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
if (bitmap[k])
return 0;
if (bits % BITS_PER_LONG)
if (bitmap[k] & BITMAP_LAST_WORD_MASK(bits))
return 0;
return 1;
}
EXPORT_SYMBOL(__bitmap_empty);
int __bitmap_full(const unsigned long *bitmap, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
if (~bitmap[k])
return 0;
if (bits % BITS_PER_LONG)
if (~bitmap[k] & BITMAP_LAST_WORD_MASK(bits))
return 0;
return 1;
}
EXPORT_SYMBOL(__bitmap_full);
int __bitmap_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
if (bitmap1[k] != bitmap2[k])
return 0;
if (bits % BITS_PER_LONG)
if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
return 0;
return 1;
}
EXPORT_SYMBOL(__bitmap_equal);
void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
dst[k] = ~src[k];
if (bits % BITS_PER_LONG)
dst[k] = ~src[k];
}
EXPORT_SYMBOL(__bitmap_complement);
/**
* __bitmap_shift_right - logical right shift of the bits in a bitmap
* @dst : destination bitmap
* @src : source bitmap
* @shift : shift by this many bits
* @bits : bitmap size, in bits
*
* Shifting right (dividing) means moving bits in the MS -> LS bit
* direction. Zeros are fed into the vacated MS positions and the
* LS bits shifted off the bottom are lost.
*/
void __bitmap_shift_right(unsigned long *dst,
const unsigned long *src, int shift, int bits)
{
int k, lim = BITS_TO_LONGS(bits), left = bits % BITS_PER_LONG;
int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
unsigned long mask = (1UL << left) - 1;
for (k = 0; off + k < lim; ++k) {
unsigned long upper, lower;
/*
* If shift is not word aligned, take lower rem bits of
* word above and make them the top rem bits of result.
*/
if (!rem || off + k + 1 >= lim)
upper = 0;
else {
upper = src[off + k + 1];
if (off + k + 1 == lim - 1 && left)
upper &= mask;
}
lower = src[off + k];
if (left && off + k == lim - 1)
lower &= mask;
dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem;
if (left && k == lim - 1)
dst[k] &= mask;
}
if (off)
memset(&dst[lim - off], 0, off*sizeof(unsigned long));
}
EXPORT_SYMBOL(__bitmap_shift_right);
/**
* __bitmap_shift_left - logical left shift of the bits in a bitmap
* @dst : destination bitmap
* @src : source bitmap
* @shift : shift by this many bits
* @bits : bitmap size, in bits
*
* Shifting left (multiplying) means moving bits in the LS -> MS
* direction. Zeros are fed into the vacated LS bit positions
* and those MS bits shifted off the top are lost.
*/
void __bitmap_shift_left(unsigned long *dst,
const unsigned long *src, int shift, int bits)
{
int k, lim = BITS_TO_LONGS(bits), left = bits % BITS_PER_LONG;
int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
for (k = lim - off - 1; k >= 0; --k) {
unsigned long upper, lower;
/*
* If shift is not word aligned, take upper rem bits of
* word below and make them the bottom rem bits of result.
*/
if (rem && k > 0)
lower = src[k - 1];
else
lower = 0;
upper = src[k];
if (left && k == lim - 1)
upper &= (1UL << left) - 1;
dst[k + off] = lower >> (BITS_PER_LONG - rem) | upper << rem;
if (left && k + off == lim - 1)
dst[k + off] &= (1UL << left) - 1;
}
if (off)
memset(dst, 0, off*sizeof(unsigned long));
}
EXPORT_SYMBOL(__bitmap_shift_left);
int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
unsigned int lim = bits/BITS_PER_LONG;
unsigned long result = 0;
for (k = 0; k < lim; k++)
result |= (dst[k] = bitmap1[k] & bitmap2[k]);
if (bits % BITS_PER_LONG)
result |= (dst[k] = bitmap1[k] & bitmap2[k] &
BITMAP_LAST_WORD_MASK(bits));
return result != 0;
}
EXPORT_SYMBOL(__bitmap_and);
void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
unsigned int nr = BITS_TO_LONGS(bits);
for (k = 0; k < nr; k++)
dst[k] = bitmap1[k] | bitmap2[k];
}
EXPORT_SYMBOL(__bitmap_or);
void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
unsigned int nr = BITS_TO_LONGS(bits);
for (k = 0; k < nr; k++)
dst[k] = bitmap1[k] ^ bitmap2[k];
}
EXPORT_SYMBOL(__bitmap_xor);
int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k;
unsigned int lim = bits/BITS_PER_LONG;
unsigned long result = 0;
for (k = 0; k < lim; k++)
result |= (dst[k] = bitmap1[k] & ~bitmap2[k]);
if (bits % BITS_PER_LONG)
result |= (dst[k] = bitmap1[k] & ~bitmap2[k] &
BITMAP_LAST_WORD_MASK(bits));
return result != 0;
}
EXPORT_SYMBOL(__bitmap_andnot);
int __bitmap_intersects(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
if (bitmap1[k] & bitmap2[k])
return 1;
if (bits % BITS_PER_LONG)
if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
return 1;
return 0;
}
EXPORT_SYMBOL(__bitmap_intersects);
int __bitmap_subset(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
for (k = 0; k < lim; ++k)
if (bitmap1[k] & ~bitmap2[k])
return 0;
if (bits % BITS_PER_LONG)
if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
return 0;
return 1;
}
EXPORT_SYMBOL(__bitmap_subset);
int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
{
unsigned int k, lim = bits/BITS_PER_LONG;
int w = 0;
for (k = 0; k < lim; k++)
w += hweight_long(bitmap[k]);
if (bits % BITS_PER_LONG)
w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
return w;
}
EXPORT_SYMBOL(__bitmap_weight);
void bitmap_set(unsigned long *map, unsigned int start, int len)
{
unsigned long *p = map + BIT_WORD(start);
const unsigned int size = start + len;
int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
while (len - bits_to_set >= 0) {
*p |= mask_to_set;
len -= bits_to_set;
bits_to_set = BITS_PER_LONG;
mask_to_set = ~0UL;
p++;
}
if (len) {
mask_to_set &= BITMAP_LAST_WORD_MASK(size);
*p |= mask_to_set;
}
}
EXPORT_SYMBOL(bitmap_set);
void bitmap_clear(unsigned long *map, unsigned int start, int len)
{
unsigned long *p = map + BIT_WORD(start);
const unsigned int size = start + len;
int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
while (len - bits_to_clear >= 0) {
*p &= ~mask_to_clear;
len -= bits_to_clear;
bits_to_clear = BITS_PER_LONG;
mask_to_clear = ~0UL;
p++;
}
if (len) {
mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
*p &= ~mask_to_clear;
}
}
EXPORT_SYMBOL(bitmap_clear);
/*
* bitmap_find_next_zero_area - find a contiguous aligned zero area
* @map: The address to base the search on
* @size: The bitmap size in bits
* @start: The bitnumber to start searching at
* @nr: The number of zeroed bits we're looking for
* @align_mask: Alignment mask for zero area
*
* The @align_mask should be one less than a power of 2; the effect is that
* the bit offset of all zero areas this function finds is multiples of that
* power of 2. A @align_mask of 0 means no alignment is required.
*/
unsigned long bitmap_find_next_zero_area(unsigned long *map,
unsigned long size,
unsigned long start,
unsigned int nr,
unsigned long align_mask)
{
unsigned long index, end, i;
again:
index = find_next_zero_bit(map, size, start);
/* Align allocation */
index = __ALIGN_MASK(index, align_mask);
end = index + nr;
if (end > size)
return end;
i = find_next_bit(map, end, index);
if (i < end) {
start = i + 1;
goto again;
}
return index;
}
EXPORT_SYMBOL(bitmap_find_next_zero_area);
/*
* Bitmap printing & parsing functions: first version by Nadia Yvette Chambers,
* second version by Paul Jackson, third by Joe Korty.
*/
#define CHUNKSZ 32
#define nbits_to_hold_value(val) fls(val)
#define BASEDEC 10 /* fancier cpuset lists input in decimal */
/**
* bitmap_scnprintf - convert bitmap to an ASCII hex string.
* @buf: byte buffer into which string is placed
* @buflen: reserved size of @buf, in bytes
* @maskp: pointer to bitmap to convert
* @nmaskbits: size of bitmap, in bits
*
* Exactly @nmaskbits bits are displayed. Hex digits are grouped into
* comma-separated sets of eight digits per set. Returns the number of
* characters which were written to *buf, excluding the trailing \0.
*/
int bitmap_scnprintf(char *buf, unsigned int buflen,
const unsigned long *maskp, int nmaskbits)
{
int i, word, bit, len = 0;
unsigned long val;
const char *sep = "";
int chunksz;
u32 chunkmask;
chunksz = nmaskbits & (CHUNKSZ - 1);
if (chunksz == 0)
chunksz = CHUNKSZ;
i = ALIGN(nmaskbits, CHUNKSZ) - CHUNKSZ;
for (; i >= 0; i -= CHUNKSZ) {
chunkmask = ((1ULL << chunksz) - 1);
word = i / BITS_PER_LONG;
bit = i % BITS_PER_LONG;
val = (maskp[word] >> bit) & chunkmask;
len += scnprintf(buf+len, buflen-len, "%s%0*lx", sep,
(chunksz+3)/4, val);
chunksz = CHUNKSZ;
sep = ",";
}
return len;
}
EXPORT_SYMBOL(bitmap_scnprintf);
/**
* __bitmap_parse - convert an ASCII hex string into a bitmap.
* @buf: pointer to buffer containing string.
* @buflen: buffer size in bytes. If string is smaller than this
* then it must be terminated with a \0.
* @is_user: location of buffer, 0 indicates kernel space
* @maskp: pointer to bitmap array that will contain result.
* @nmaskbits: size of bitmap, in bits.
*
* Commas group hex digits into chunks. Each chunk defines exactly 32
* bits of the resultant bitmask. No chunk may specify a value larger
* than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value
* then leading 0-bits are prepended. %-EINVAL is returned for illegal
* characters and for grouping errors such as "1,,5", ",44", "," and "".
* Leading and trailing whitespace accepted, but not embedded whitespace.
*/
int __bitmap_parse(const char *buf, unsigned int buflen,
int is_user, unsigned long *maskp,
int nmaskbits)
{
int c, old_c, totaldigits, ndigits, nchunks, nbits;
u32 chunk;
const char __user __force *ubuf = (const char __user __force *)buf;
bitmap_zero(maskp, nmaskbits);
nchunks = nbits = totaldigits = c = 0;
do {
chunk = ndigits = 0;
/* Get the next chunk of the bitmap */
while (buflen) {
old_c = c;
if (is_user) {
if (__get_user(c, ubuf++))
return -EFAULT;
}
else
c = *buf++;
buflen--;
if (isspace(c))
continue;
/*
* If the last character was a space and the current
* character isn't '\0', we've got embedded whitespace.
* This is a no-no, so throw an error.
*/
if (totaldigits && c && isspace(old_c))
return -EINVAL;
/* A '\0' or a ',' signal the end of the chunk */
if (c == '\0' || c == ',')
break;
if (!isxdigit(c))
return -EINVAL;
/*
* Make sure there are at least 4 free bits in 'chunk'.
* If not, this hexdigit will overflow 'chunk', so
* throw an error.
*/
if (chunk & ~((1UL << (CHUNKSZ - 4)) - 1))
return -EOVERFLOW;
chunk = (chunk << 4) | hex_to_bin(c);
ndigits++; totaldigits++;
}
if (ndigits == 0)
return -EINVAL;
if (nchunks == 0 && chunk == 0)
continue;
__bitmap_shift_left(maskp, maskp, CHUNKSZ, nmaskbits);
*maskp |= chunk;
nchunks++;
nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ;
if (nbits > nmaskbits)
return -EOVERFLOW;
} while (buflen && c == ',');
return 0;
}
EXPORT_SYMBOL(__bitmap_parse);
/**
* bitmap_parse_user - convert an ASCII hex string in a user buffer into a bitmap
*
* @ubuf: pointer to user buffer containing string.
* @ulen: buffer size in bytes. If string is smaller than this
* then it must be terminated with a \0.
* @maskp: pointer to bitmap array that will contain result.
* @nmaskbits: size of bitmap, in bits.
*
* Wrapper for __bitmap_parse(), providing it with user buffer.
*
* We cannot have this as an inline function in bitmap.h because it needs
* linux/uaccess.h to get the access_ok() declaration and this causes
* cyclic dependencies.
*/
int bitmap_parse_user(const char __user *ubuf,
unsigned int ulen, unsigned long *maskp,
int nmaskbits)
{
if (!access_ok(VERIFY_READ, ubuf, ulen))
return -EFAULT;
return __bitmap_parse((const char __force *)ubuf,
ulen, 1, maskp, nmaskbits);
}
EXPORT_SYMBOL(bitmap_parse_user);
/*
* bscnl_emit(buf, buflen, rbot, rtop, bp)
*
* Helper routine for bitmap_scnlistprintf(). Write decimal number
* or range to buf, suppressing output past buf+buflen, with optional
* comma-prefix. Return len of what was written to *buf, excluding the
* trailing \0.
*/
static inline int bscnl_emit(char *buf, int buflen, int rbot, int rtop, int len)
{
if (len > 0)
len += scnprintf(buf + len, buflen - len, ",");
if (rbot == rtop)
len += scnprintf(buf + len, buflen - len, "%d", rbot);
else
len += scnprintf(buf + len, buflen - len, "%d-%d", rbot, rtop);
return len;
}
/**
* bitmap_scnlistprintf - convert bitmap to list format ASCII string
* @buf: byte buffer into which string is placed
* @buflen: reserved size of @buf, in bytes
* @maskp: pointer to bitmap to convert
* @nmaskbits: size of bitmap, in bits
*
* Output format is a comma-separated list of decimal numbers and
* ranges. Consecutively set bits are shown as two hyphen-separated
* decimal numbers, the smallest and largest bit numbers set in
* the range. Output format is compatible with the format
* accepted as input by bitmap_parselist().
*
* The return value is the number of characters which were written to *buf
* excluding the trailing '\0', as per ISO C99's scnprintf.
*/
int bitmap_scnlistprintf(char *buf, unsigned int buflen,
const unsigned long *maskp, int nmaskbits)
{
int len = 0;
/* current bit is 'cur', most recently seen range is [rbot, rtop] */
int cur, rbot, rtop;
if (buflen == 0)
return 0;
buf[0] = 0;
rbot = cur = find_first_bit(maskp, nmaskbits);
while (cur < nmaskbits) {
rtop = cur;
cur = find_next_bit(maskp, nmaskbits, cur+1);
if (cur >= nmaskbits || cur > rtop + 1) {
len = bscnl_emit(buf, buflen, rbot, rtop, len);
rbot = cur;
}
}
return len;
}
EXPORT_SYMBOL(bitmap_scnlistprintf);
/**
* __bitmap_parselist - convert list format ASCII string to bitmap
* @buf: read nul-terminated user string from this buffer
* @buflen: buffer size in bytes. If string is smaller than this
* then it must be terminated with a \0.
* @is_user: location of buffer, 0 indicates kernel space
* @maskp: write resulting mask here
* @nmaskbits: number of bits in mask to be written
*
* Input format is a comma-separated list of decimal numbers and
* ranges. Consecutively set bits are shown as two hyphen-separated
* decimal numbers, the smallest and largest bit numbers set in
* the range.
*
* Returns 0 on success, -errno on invalid input strings.
* Error values:
* %-EINVAL: second number in range smaller than first
* %-EINVAL: invalid character in string
* %-ERANGE: bit number specified too large for mask
*/
static int __bitmap_parselist(const char *buf, unsigned int buflen,
int is_user, unsigned long *maskp,
int nmaskbits)
{
unsigned a, b;
int c, old_c, totaldigits;
const char __user __force *ubuf = (const char __user __force *)buf;
int exp_digit, in_range;
totaldigits = c = 0;
bitmap_zero(maskp, nmaskbits);
do {
exp_digit = 1;
in_range = 0;
a = b = 0;
/* Get the next cpu# or a range of cpu#'s */
while (buflen) {
old_c = c;
if (is_user) {
if (__get_user(c, ubuf++))
return -EFAULT;
} else
c = *buf++;
buflen--;
if (isspace(c))
continue;
/*
* If the last character was a space and the current
* character isn't '\0', we've got embedded whitespace.
* This is a no-no, so throw an error.
*/
if (totaldigits && c && isspace(old_c))
return -EINVAL;
/* A '\0' or a ',' signal the end of a cpu# or range */
if (c == '\0' || c == ',')
break;
if (c == '-') {
if (exp_digit || in_range)
return -EINVAL;
b = 0;
in_range = 1;
exp_digit = 1;
continue;
}
if (!isdigit(c))
return -EINVAL;
b = b * 10 + (c - '0');
if (!in_range)
a = b;
exp_digit = 0;
totaldigits++;
}
if (!(a <= b))
return -EINVAL;
if (b >= nmaskbits)
return -ERANGE;
while (a <= b) {
set_bit(a, maskp);
a++;
}
} while (buflen && c == ',');
return 0;
}
int bitmap_parselist(const char *bp, unsigned long *maskp, int nmaskbits)
{
char *nl = strchrnul(bp, '\n');
int len = nl - bp;
return __bitmap_parselist(bp, len, 0, maskp, nmaskbits);
}
EXPORT_SYMBOL(bitmap_parselist);
/**
* bitmap_parselist_user()
*
* @ubuf: pointer to user buffer containing string.
* @ulen: buffer size in bytes. If string is smaller than this
* then it must be terminated with a \0.
* @maskp: pointer to bitmap array that will contain result.
* @nmaskbits: size of bitmap, in bits.
*
* Wrapper for bitmap_parselist(), providing it with user buffer.
*
* We cannot have this as an inline function in bitmap.h because it needs
* linux/uaccess.h to get the access_ok() declaration and this causes
* cyclic dependencies.
*/
int bitmap_parselist_user(const char __user *ubuf,
unsigned int ulen, unsigned long *maskp,
int nmaskbits)
{
if (!access_ok(VERIFY_READ, ubuf, ulen))
return -EFAULT;
return __bitmap_parselist((const char __force *)ubuf,
ulen, 1, maskp, nmaskbits);
}
EXPORT_SYMBOL(bitmap_parselist_user);
/**
* bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap
* @buf: pointer to a bitmap
* @pos: a bit position in @buf (0 <= @pos < @bits)
* @bits: number of valid bit positions in @buf
*
* Map the bit at position @pos in @buf (of length @bits) to the
* ordinal of which set bit it is. If it is not set or if @pos
* is not a valid bit position, map to -1.
*
* If for example, just bits 4 through 7 are set in @buf, then @pos
* values 4 through 7 will get mapped to 0 through 3, respectively,
* and other @pos values will get mapped to -1. When @pos value 7
* gets mapped to (returns) @ord value 3 in this example, that means
* that bit 7 is the 3rd (starting with 0th) set bit in @buf.
*
* The bit positions 0 through @bits are valid positions in @buf.
*/
static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits)
{
int i, ord;
if (pos < 0 || pos >= bits || !test_bit(pos, buf))
return -1;
i = find_first_bit(buf, bits);
ord = 0;
while (i < pos) {
i = find_next_bit(buf, bits, i + 1);
ord++;
}
BUG_ON(i != pos);
return ord;
}
/**
* bitmap_ord_to_pos - find position of n-th set bit in bitmap
* @buf: pointer to bitmap
* @ord: ordinal bit position (n-th set bit, n >= 0)
* @bits: number of valid bit positions in @buf
*
* Map the ordinal offset of bit @ord in @buf to its position in @buf.
* Value of @ord should be in range 0 <= @ord < weight(buf), else
* results are undefined.
*
* If for example, just bits 4 through 7 are set in @buf, then @ord
* values 0 through 3 will get mapped to 4 through 7, respectively,
* and all other @ord values return undefined values. When @ord value 3
* gets mapped to (returns) @pos value 7 in this example, that means
* that the 3rd set bit (starting with 0th) is at position 7 in @buf.
*
* The bit positions 0 through @bits are valid positions in @buf.
*/
cpusets: randomize node rotor used in cpuset_mem_spread_node() [ This patch has already been accepted as commit 0ac0c0d0f837 but later reverted (commit 35926ff5fba8) because it itroduced arch specific __node_random which was defined only for x86 code so it broke other archs. This is a followup without any arch specific code. Other than that there are no functional changes.] Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] [mhocko@suse.cz: Make it arch independent] [akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Paul Menage <menage@google.com> Cc: Jack Steiner <steiner@sgi.com> Cc: Robin Holt <holt@sgi.com> Cc: David Rientjes <rientjes@google.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: David Rientjes <rientjes@google.com> Cc: Jack Steiner <steiner@sgi.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Menage <menage@google.com> Cc: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-07-27 07:08:30 +08:00
int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
{
int pos = 0;
if (ord >= 0 && ord < bits) {
int i;
for (i = find_first_bit(buf, bits);
i < bits && ord > 0;
i = find_next_bit(buf, bits, i + 1))
ord--;
if (i < bits && ord == 0)
pos = i;
}
return pos;
}
/**
* bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap
* @dst: remapped result
* @src: subset to be remapped
* @old: defines domain of map
* @new: defines range of map
* @bits: number of bits in each of these bitmaps
*
* Let @old and @new define a mapping of bit positions, such that
* whatever position is held by the n-th set bit in @old is mapped
* to the n-th set bit in @new. In the more general case, allowing
* for the possibility that the weight 'w' of @new is less than the
* weight of @old, map the position of the n-th set bit in @old to
* the position of the m-th set bit in @new, where m == n % w.
*
* If either of the @old and @new bitmaps are empty, or if @src and
* @dst point to the same location, then this routine copies @src
* to @dst.
*
* The positions of unset bits in @old are mapped to themselves
* (the identify map).
*
* Apply the above specified mapping to @src, placing the result in
* @dst, clearing any bits previously set in @dst.
*
* For example, lets say that @old has bits 4 through 7 set, and
* @new has bits 12 through 15 set. This defines the mapping of bit
* position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other
* bit positions unchanged. So if say @src comes into this routine
* with bits 1, 5 and 7 set, then @dst should leave with bits 1,
* 13 and 15 set.
*/
void bitmap_remap(unsigned long *dst, const unsigned long *src,
const unsigned long *old, const unsigned long *new,
int bits)
{
int oldbit, w;
if (dst == src) /* following doesn't handle inplace remaps */
return;
bitmap_zero(dst, bits);
w = bitmap_weight(new, bits);
for_each_set_bit(oldbit, src, bits) {
int n = bitmap_pos_to_ord(old, oldbit, bits);
if (n < 0 || w == 0)
set_bit(oldbit, dst); /* identity map */
else
set_bit(bitmap_ord_to_pos(new, n % w, bits), dst);
}
}
EXPORT_SYMBOL(bitmap_remap);
/**
* bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit
* @oldbit: bit position to be mapped
* @old: defines domain of map
* @new: defines range of map
* @bits: number of bits in each of these bitmaps
*
* Let @old and @new define a mapping of bit positions, such that
* whatever position is held by the n-th set bit in @old is mapped
* to the n-th set bit in @new. In the more general case, allowing
* for the possibility that the weight 'w' of @new is less than the
* weight of @old, map the position of the n-th set bit in @old to
* the position of the m-th set bit in @new, where m == n % w.
*
* The positions of unset bits in @old are mapped to themselves
* (the identify map).
*
* Apply the above specified mapping to bit position @oldbit, returning
* the new bit position.
*
* For example, lets say that @old has bits 4 through 7 set, and
* @new has bits 12 through 15 set. This defines the mapping of bit
* position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other
* bit positions unchanged. So if say @oldbit is 5, then this routine
* returns 13.
*/
int bitmap_bitremap(int oldbit, const unsigned long *old,
const unsigned long *new, int bits)
{
int w = bitmap_weight(new, bits);
int n = bitmap_pos_to_ord(old, oldbit, bits);
if (n < 0 || w == 0)
return oldbit;
else
return bitmap_ord_to_pos(new, n % w, bits);
}
EXPORT_SYMBOL(bitmap_bitremap);
mempolicy: add bitmap_onto() and bitmap_fold() operations The following adds two more bitmap operators, bitmap_onto() and bitmap_fold(), with the usual cpumask and nodemask wrappers. The bitmap_onto() operator computes one bitmap relative to another. If the n-th bit in the origin mask is set, then the m-th bit of the destination mask will be set, where m is the position of the n-th set bit in the relative mask. The bitmap_fold() operator folds a bitmap into a second that has bit m set iff the input bitmap has some bit n set, where m == n mod sz, for the specified sz value. There are two substantive changes between this patch and its predecessor bitmap_relative: 1) Renamed bitmap_relative() to be bitmap_onto(). 2) Added bitmap_fold(). The essential motivation for bitmap_onto() is to provide a mechanism for converting a cpuset-relative CPU or Node mask to an absolute mask. Cpuset relative masks are written as if the current task were in a cpuset whose CPUs or Nodes were just the consecutive ones numbered 0..N-1, for some N. The bitmap_onto() operator is provided in anticipation of adding support for the first such cpuset relative mask, by the mbind() and set_mempolicy() system calls, using a planned flag of MPOL_F_RELATIVE_NODES. These bitmap operators (and their nodemask wrappers, in particular) will be used in code that converts the user specified cpuset relative memory policy to a specific system node numbered policy, given the current mems_allowed of the tasks cpuset. Such cpuset relative mempolicies will address two deficiencies of the existing interface between cpusets and mempolicies: 1) A task cannot at present reliably establish a cpuset relative mempolicy because there is an essential race condition, in that the tasks cpuset may be changed in between the time the task can query its cpuset placement, and the time the task can issue the applicable mbind or set_memplicy system call. 2) A task cannot at present establish what cpuset relative mempolicy it would like to have, if it is in a smaller cpuset than it might have mempolicy preferences for, because the existing interface only allows specifying mempolicies for nodes currently allowed by the cpuset. Cpuset relative mempolicies are useful for tasks that don't distinguish particularly between one CPU or Node and another, but only between how many of each are allowed, and the proper placement of threads and memory pages on the various CPUs and Nodes available. The motivation for the added bitmap_fold() can be seen in the following example. Let's say an application has specified some mempolicies that presume 16 memory nodes, including say a mempolicy that specified MPOL_F_RELATIVE_NODES (cpuset relative) nodes 12-15. Then lets say that application is crammed into a cpuset that only has 8 memory nodes, 0-7. If one just uses bitmap_onto(), this mempolicy, mapped to that cpuset, would ignore the requested relative nodes above 7, leaving it empty of nodes. That's not good; better to fold the higher nodes down, so that some nodes are included in the resulting mapped mempolicy. In this case, the mempolicy nodes 12-15 are taken modulo 8 (the weight of the mems_allowed of the confining cpuset), resulting in a mempolicy specifying nodes 4-7. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: <kosaki.motohiro@jp.fujitsu.com> Cc: <ray-lk@madrabbit.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:29 +08:00
/**
* bitmap_onto - translate one bitmap relative to another
* @dst: resulting translated bitmap
* @orig: original untranslated bitmap
* @relmap: bitmap relative to which translated
* @bits: number of bits in each of these bitmaps
*
* Set the n-th bit of @dst iff there exists some m such that the
* n-th bit of @relmap is set, the m-th bit of @orig is set, and
* the n-th bit of @relmap is also the m-th _set_ bit of @relmap.
* (If you understood the previous sentence the first time your
* read it, you're overqualified for your current job.)
*
* In other words, @orig is mapped onto (surjectively) @dst,
* using the the map { <n, m> | the n-th bit of @relmap is the
* m-th set bit of @relmap }.
*
* Any set bits in @orig above bit number W, where W is the
* weight of (number of set bits in) @relmap are mapped nowhere.
* In particular, if for all bits m set in @orig, m >= W, then
* @dst will end up empty. In situations where the possibility
* of such an empty result is not desired, one way to avoid it is
* to use the bitmap_fold() operator, below, to first fold the
* @orig bitmap over itself so that all its set bits x are in the
* range 0 <= x < W. The bitmap_fold() operator does this by
* setting the bit (m % W) in @dst, for each bit (m) set in @orig.
*
* Example [1] for bitmap_onto():
* Let's say @relmap has bits 30-39 set, and @orig has bits
* 1, 3, 5, 7, 9 and 11 set. Then on return from this routine,
* @dst will have bits 31, 33, 35, 37 and 39 set.
*
* When bit 0 is set in @orig, it means turn on the bit in
* @dst corresponding to whatever is the first bit (if any)
* that is turned on in @relmap. Since bit 0 was off in the
* above example, we leave off that bit (bit 30) in @dst.
*
* When bit 1 is set in @orig (as in the above example), it
* means turn on the bit in @dst corresponding to whatever
* is the second bit that is turned on in @relmap. The second
* bit in @relmap that was turned on in the above example was
* bit 31, so we turned on bit 31 in @dst.
*
* Similarly, we turned on bits 33, 35, 37 and 39 in @dst,
* because they were the 4th, 6th, 8th and 10th set bits
* set in @relmap, and the 4th, 6th, 8th and 10th bits of
* @orig (i.e. bits 3, 5, 7 and 9) were also set.
*
* When bit 11 is set in @orig, it means turn on the bit in
* @dst corresponding to whatever is the twelfth bit that is
mempolicy: add bitmap_onto() and bitmap_fold() operations The following adds two more bitmap operators, bitmap_onto() and bitmap_fold(), with the usual cpumask and nodemask wrappers. The bitmap_onto() operator computes one bitmap relative to another. If the n-th bit in the origin mask is set, then the m-th bit of the destination mask will be set, where m is the position of the n-th set bit in the relative mask. The bitmap_fold() operator folds a bitmap into a second that has bit m set iff the input bitmap has some bit n set, where m == n mod sz, for the specified sz value. There are two substantive changes between this patch and its predecessor bitmap_relative: 1) Renamed bitmap_relative() to be bitmap_onto(). 2) Added bitmap_fold(). The essential motivation for bitmap_onto() is to provide a mechanism for converting a cpuset-relative CPU or Node mask to an absolute mask. Cpuset relative masks are written as if the current task were in a cpuset whose CPUs or Nodes were just the consecutive ones numbered 0..N-1, for some N. The bitmap_onto() operator is provided in anticipation of adding support for the first such cpuset relative mask, by the mbind() and set_mempolicy() system calls, using a planned flag of MPOL_F_RELATIVE_NODES. These bitmap operators (and their nodemask wrappers, in particular) will be used in code that converts the user specified cpuset relative memory policy to a specific system node numbered policy, given the current mems_allowed of the tasks cpuset. Such cpuset relative mempolicies will address two deficiencies of the existing interface between cpusets and mempolicies: 1) A task cannot at present reliably establish a cpuset relative mempolicy because there is an essential race condition, in that the tasks cpuset may be changed in between the time the task can query its cpuset placement, and the time the task can issue the applicable mbind or set_memplicy system call. 2) A task cannot at present establish what cpuset relative mempolicy it would like to have, if it is in a smaller cpuset than it might have mempolicy preferences for, because the existing interface only allows specifying mempolicies for nodes currently allowed by the cpuset. Cpuset relative mempolicies are useful for tasks that don't distinguish particularly between one CPU or Node and another, but only between how many of each are allowed, and the proper placement of threads and memory pages on the various CPUs and Nodes available. The motivation for the added bitmap_fold() can be seen in the following example. Let's say an application has specified some mempolicies that presume 16 memory nodes, including say a mempolicy that specified MPOL_F_RELATIVE_NODES (cpuset relative) nodes 12-15. Then lets say that application is crammed into a cpuset that only has 8 memory nodes, 0-7. If one just uses bitmap_onto(), this mempolicy, mapped to that cpuset, would ignore the requested relative nodes above 7, leaving it empty of nodes. That's not good; better to fold the higher nodes down, so that some nodes are included in the resulting mapped mempolicy. In this case, the mempolicy nodes 12-15 are taken modulo 8 (the weight of the mems_allowed of the confining cpuset), resulting in a mempolicy specifying nodes 4-7. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: <kosaki.motohiro@jp.fujitsu.com> Cc: <ray-lk@madrabbit.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:29 +08:00
* turned on in @relmap. In the above example, there were
* only ten bits turned on in @relmap (30..39), so that bit
* 11 was set in @orig had no affect on @dst.
*
* Example [2] for bitmap_fold() + bitmap_onto():
* Let's say @relmap has these ten bits set:
* 40 41 42 43 45 48 53 61 74 95
* (for the curious, that's 40 plus the first ten terms of the
* Fibonacci sequence.)
*
* Further lets say we use the following code, invoking
* bitmap_fold() then bitmap_onto, as suggested above to
* avoid the possitility of an empty @dst result:
*
* unsigned long *tmp; // a temporary bitmap's bits
*
* bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits);
* bitmap_onto(dst, tmp, relmap, bits);
*
* Then this table shows what various values of @dst would be, for
* various @orig's. I list the zero-based positions of each set bit.
* The tmp column shows the intermediate result, as computed by
* using bitmap_fold() to fold the @orig bitmap modulo ten
* (the weight of @relmap).
*
* @orig tmp @dst
* 0 0 40
* 1 1 41
* 9 9 95
* 10 0 40 (*)
* 1 3 5 7 1 3 5 7 41 43 48 61
* 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45
* 0 9 18 27 0 9 8 7 40 61 74 95
* 0 10 20 30 0 40
* 0 11 22 33 0 1 2 3 40 41 42 43
* 0 12 24 36 0 2 4 6 40 42 45 53
* 78 102 211 1 2 8 41 42 74 (*)
*
* (*) For these marked lines, if we hadn't first done bitmap_fold()
* into tmp, then the @dst result would have been empty.
*
* If either of @orig or @relmap is empty (no set bits), then @dst
* will be returned empty.
*
* If (as explained above) the only set bits in @orig are in positions
* m where m >= W, (where W is the weight of @relmap) then @dst will
* once again be returned empty.
*
* All bits in @dst not set by the above rule are cleared.
*/
void bitmap_onto(unsigned long *dst, const unsigned long *orig,
const unsigned long *relmap, int bits)
{
int n, m; /* same meaning as in above comment */
if (dst == orig) /* following doesn't handle inplace mappings */
return;
bitmap_zero(dst, bits);
/*
* The following code is a more efficient, but less
* obvious, equivalent to the loop:
* for (m = 0; m < bitmap_weight(relmap, bits); m++) {
* n = bitmap_ord_to_pos(orig, m, bits);
* if (test_bit(m, orig))
* set_bit(n, dst);
* }
*/
m = 0;
for_each_set_bit(n, relmap, bits) {
mempolicy: add bitmap_onto() and bitmap_fold() operations The following adds two more bitmap operators, bitmap_onto() and bitmap_fold(), with the usual cpumask and nodemask wrappers. The bitmap_onto() operator computes one bitmap relative to another. If the n-th bit in the origin mask is set, then the m-th bit of the destination mask will be set, where m is the position of the n-th set bit in the relative mask. The bitmap_fold() operator folds a bitmap into a second that has bit m set iff the input bitmap has some bit n set, where m == n mod sz, for the specified sz value. There are two substantive changes between this patch and its predecessor bitmap_relative: 1) Renamed bitmap_relative() to be bitmap_onto(). 2) Added bitmap_fold(). The essential motivation for bitmap_onto() is to provide a mechanism for converting a cpuset-relative CPU or Node mask to an absolute mask. Cpuset relative masks are written as if the current task were in a cpuset whose CPUs or Nodes were just the consecutive ones numbered 0..N-1, for some N. The bitmap_onto() operator is provided in anticipation of adding support for the first such cpuset relative mask, by the mbind() and set_mempolicy() system calls, using a planned flag of MPOL_F_RELATIVE_NODES. These bitmap operators (and their nodemask wrappers, in particular) will be used in code that converts the user specified cpuset relative memory policy to a specific system node numbered policy, given the current mems_allowed of the tasks cpuset. Such cpuset relative mempolicies will address two deficiencies of the existing interface between cpusets and mempolicies: 1) A task cannot at present reliably establish a cpuset relative mempolicy because there is an essential race condition, in that the tasks cpuset may be changed in between the time the task can query its cpuset placement, and the time the task can issue the applicable mbind or set_memplicy system call. 2) A task cannot at present establish what cpuset relative mempolicy it would like to have, if it is in a smaller cpuset than it might have mempolicy preferences for, because the existing interface only allows specifying mempolicies for nodes currently allowed by the cpuset. Cpuset relative mempolicies are useful for tasks that don't distinguish particularly between one CPU or Node and another, but only between how many of each are allowed, and the proper placement of threads and memory pages on the various CPUs and Nodes available. The motivation for the added bitmap_fold() can be seen in the following example. Let's say an application has specified some mempolicies that presume 16 memory nodes, including say a mempolicy that specified MPOL_F_RELATIVE_NODES (cpuset relative) nodes 12-15. Then lets say that application is crammed into a cpuset that only has 8 memory nodes, 0-7. If one just uses bitmap_onto(), this mempolicy, mapped to that cpuset, would ignore the requested relative nodes above 7, leaving it empty of nodes. That's not good; better to fold the higher nodes down, so that some nodes are included in the resulting mapped mempolicy. In this case, the mempolicy nodes 12-15 are taken modulo 8 (the weight of the mems_allowed of the confining cpuset), resulting in a mempolicy specifying nodes 4-7. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: <kosaki.motohiro@jp.fujitsu.com> Cc: <ray-lk@madrabbit.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:29 +08:00
/* m == bitmap_pos_to_ord(relmap, n, bits) */
if (test_bit(m, orig))
set_bit(n, dst);
m++;
}
}
EXPORT_SYMBOL(bitmap_onto);
/**
* bitmap_fold - fold larger bitmap into smaller, modulo specified size
* @dst: resulting smaller bitmap
* @orig: original larger bitmap
* @sz: specified size
* @bits: number of bits in each of these bitmaps
*
* For each bit oldbit in @orig, set bit oldbit mod @sz in @dst.
* Clear all other bits in @dst. See further the comment and
* Example [2] for bitmap_onto() for why and how to use this.
*/
void bitmap_fold(unsigned long *dst, const unsigned long *orig,
int sz, int bits)
{
int oldbit;
if (dst == orig) /* following doesn't handle inplace mappings */
return;
bitmap_zero(dst, bits);
for_each_set_bit(oldbit, orig, bits)
mempolicy: add bitmap_onto() and bitmap_fold() operations The following adds two more bitmap operators, bitmap_onto() and bitmap_fold(), with the usual cpumask and nodemask wrappers. The bitmap_onto() operator computes one bitmap relative to another. If the n-th bit in the origin mask is set, then the m-th bit of the destination mask will be set, where m is the position of the n-th set bit in the relative mask. The bitmap_fold() operator folds a bitmap into a second that has bit m set iff the input bitmap has some bit n set, where m == n mod sz, for the specified sz value. There are two substantive changes between this patch and its predecessor bitmap_relative: 1) Renamed bitmap_relative() to be bitmap_onto(). 2) Added bitmap_fold(). The essential motivation for bitmap_onto() is to provide a mechanism for converting a cpuset-relative CPU or Node mask to an absolute mask. Cpuset relative masks are written as if the current task were in a cpuset whose CPUs or Nodes were just the consecutive ones numbered 0..N-1, for some N. The bitmap_onto() operator is provided in anticipation of adding support for the first such cpuset relative mask, by the mbind() and set_mempolicy() system calls, using a planned flag of MPOL_F_RELATIVE_NODES. These bitmap operators (and their nodemask wrappers, in particular) will be used in code that converts the user specified cpuset relative memory policy to a specific system node numbered policy, given the current mems_allowed of the tasks cpuset. Such cpuset relative mempolicies will address two deficiencies of the existing interface between cpusets and mempolicies: 1) A task cannot at present reliably establish a cpuset relative mempolicy because there is an essential race condition, in that the tasks cpuset may be changed in between the time the task can query its cpuset placement, and the time the task can issue the applicable mbind or set_memplicy system call. 2) A task cannot at present establish what cpuset relative mempolicy it would like to have, if it is in a smaller cpuset than it might have mempolicy preferences for, because the existing interface only allows specifying mempolicies for nodes currently allowed by the cpuset. Cpuset relative mempolicies are useful for tasks that don't distinguish particularly between one CPU or Node and another, but only between how many of each are allowed, and the proper placement of threads and memory pages on the various CPUs and Nodes available. The motivation for the added bitmap_fold() can be seen in the following example. Let's say an application has specified some mempolicies that presume 16 memory nodes, including say a mempolicy that specified MPOL_F_RELATIVE_NODES (cpuset relative) nodes 12-15. Then lets say that application is crammed into a cpuset that only has 8 memory nodes, 0-7. If one just uses bitmap_onto(), this mempolicy, mapped to that cpuset, would ignore the requested relative nodes above 7, leaving it empty of nodes. That's not good; better to fold the higher nodes down, so that some nodes are included in the resulting mapped mempolicy. In this case, the mempolicy nodes 12-15 are taken modulo 8 (the weight of the mems_allowed of the confining cpuset), resulting in a mempolicy specifying nodes 4-7. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: David Rientjes <rientjes@google.com> Cc: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: <kosaki.motohiro@jp.fujitsu.com> Cc: <ray-lk@madrabbit.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:29 +08:00
set_bit(oldbit % sz, dst);
}
EXPORT_SYMBOL(bitmap_fold);
/*
* Common code for bitmap_*_region() routines.
* bitmap: array of unsigned longs corresponding to the bitmap
* pos: the beginning of the region
* order: region size (log base 2 of number of bits)
* reg_op: operation(s) to perform on that region of bitmap
*
* Can set, verify and/or release a region of bits in a bitmap,
* depending on which combination of REG_OP_* flag bits is set.
*
* A region of a bitmap is a sequence of bits in the bitmap, of
* some size '1 << order' (a power of two), aligned to that same
* '1 << order' power of two.
*
* Returns 1 if REG_OP_ISFREE succeeds (region is all zero bits).
* Returns 0 in all other cases and reg_ops.
*/
enum {
REG_OP_ISFREE, /* true if region is all zero bits */
REG_OP_ALLOC, /* set all bits in region */
REG_OP_RELEASE, /* clear all bits in region */
};
static int __reg_op(unsigned long *bitmap, unsigned int pos, int order, int reg_op)
{
int nbits_reg; /* number of bits in region */
int index; /* index first long of region in bitmap */
int offset; /* bit offset region in bitmap[index] */
int nlongs_reg; /* num longs spanned by region in bitmap */
int nbitsinlong; /* num bits of region in each spanned long */
unsigned long mask; /* bitmask for one long of region */
int i; /* scans bitmap by longs */
int ret = 0; /* return value */
/*
* Either nlongs_reg == 1 (for small orders that fit in one long)
* or (offset == 0 && mask == ~0UL) (for larger multiword orders.)
*/
nbits_reg = 1 << order;
index = pos / BITS_PER_LONG;
offset = pos - (index * BITS_PER_LONG);
nlongs_reg = BITS_TO_LONGS(nbits_reg);
nbitsinlong = min(nbits_reg, BITS_PER_LONG);
/*
* Can't do "mask = (1UL << nbitsinlong) - 1", as that
* overflows if nbitsinlong == BITS_PER_LONG.
*/
mask = (1UL << (nbitsinlong - 1));
mask += mask - 1;
mask <<= offset;
switch (reg_op) {
case REG_OP_ISFREE:
for (i = 0; i < nlongs_reg; i++) {
if (bitmap[index + i] & mask)
goto done;
}
ret = 1; /* all bits in region free (zero) */
break;
case REG_OP_ALLOC:
for (i = 0; i < nlongs_reg; i++)
bitmap[index + i] |= mask;
break;
case REG_OP_RELEASE:
for (i = 0; i < nlongs_reg; i++)
bitmap[index + i] &= ~mask;
break;
}
done:
return ret;
}
/**
* bitmap_find_free_region - find a contiguous aligned mem region
* @bitmap: array of unsigned longs corresponding to the bitmap
* @bits: number of bits in the bitmap
* @order: region size (log base 2 of number of bits) to find
*
* Find a region of free (zero) bits in a @bitmap of @bits bits and
* allocate them (set them to one). Only consider regions of length
* a power (@order) of two, aligned to that power of two, which
* makes the search algorithm much faster.
*
* Return the bit offset in bitmap of the allocated region,
* or -errno on failure.
*/
int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order)
{
unsigned int pos, end; /* scans bitmap by regions of size order */
for (pos = 0 ; (end = pos + (1U << order)) <= bits; pos = end) {
if (!__reg_op(bitmap, pos, order, REG_OP_ISFREE))
continue;
__reg_op(bitmap, pos, order, REG_OP_ALLOC);
return pos;
}
return -ENOMEM;
}
EXPORT_SYMBOL(bitmap_find_free_region);
/**
[PATCH] bitmap: region cleanup Paul Mundt <lethal@linux-sh.org> says: This patch set implements a number of patches to clean up and restructure the bitmap region code, in addition to extending the interface to support multiword spanning allocations. The current implementation (before this patch set) is limited by only being able to allocate pages <= BITS_PER_LONG, as noted by the strategically positioned BUG_ON() at lib/bitmap.c:752: /* We don't do regions of pages > BITS_PER_LONG. The * algorithm would be a simple look for multiple zeros in the * array, but there's no driver today that needs this. If you * trip this BUG(), you get to code it... */ BUG_ON(pages > BITS_PER_LONG); As I seem to have been the first person to trigger this, the result ends up being the following patch set with the help of Paul Jackson. The final patch in the series eliminates quite a bit of code duplication, so the bitmap code size ends up being smaller than the current implementation as an added bonus. After these are applied, it should already be possible to do multiword allocations with dma_alloc_coherent() out of ranges established by dma_declare_coherent_memory() on x86 without having to change any of the code, and the SH store queue API will follow up on this as the other user that needs support for this. This patch: Some code cleanup on the lib/bitmap.c bitmap_*_region() routines: * spacing * variable names * comments Has no change to code function. Signed-off-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:15:44 +08:00
* bitmap_release_region - release allocated bitmap region
* @bitmap: array of unsigned longs corresponding to the bitmap
* @pos: beginning of bit region to release
* @order: region size (log base 2 of number of bits) to release
*
* This is the complement to __bitmap_find_free_region() and releases
* the found region (by clearing it in the bitmap).
*
* No return value.
*/
void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order)
{
__reg_op(bitmap, pos, order, REG_OP_RELEASE);
}
EXPORT_SYMBOL(bitmap_release_region);
[PATCH] bitmap: region cleanup Paul Mundt <lethal@linux-sh.org> says: This patch set implements a number of patches to clean up and restructure the bitmap region code, in addition to extending the interface to support multiword spanning allocations. The current implementation (before this patch set) is limited by only being able to allocate pages <= BITS_PER_LONG, as noted by the strategically positioned BUG_ON() at lib/bitmap.c:752: /* We don't do regions of pages > BITS_PER_LONG. The * algorithm would be a simple look for multiple zeros in the * array, but there's no driver today that needs this. If you * trip this BUG(), you get to code it... */ BUG_ON(pages > BITS_PER_LONG); As I seem to have been the first person to trigger this, the result ends up being the following patch set with the help of Paul Jackson. The final patch in the series eliminates quite a bit of code duplication, so the bitmap code size ends up being smaller than the current implementation as an added bonus. After these are applied, it should already be possible to do multiword allocations with dma_alloc_coherent() out of ranges established by dma_declare_coherent_memory() on x86 without having to change any of the code, and the SH store queue API will follow up on this as the other user that needs support for this. This patch: Some code cleanup on the lib/bitmap.c bitmap_*_region() routines: * spacing * variable names * comments Has no change to code function. Signed-off-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:15:44 +08:00
/**
* bitmap_allocate_region - allocate bitmap region
* @bitmap: array of unsigned longs corresponding to the bitmap
* @pos: beginning of bit region to allocate
* @order: region size (log base 2 of number of bits) to allocate
[PATCH] bitmap: region cleanup Paul Mundt <lethal@linux-sh.org> says: This patch set implements a number of patches to clean up and restructure the bitmap region code, in addition to extending the interface to support multiword spanning allocations. The current implementation (before this patch set) is limited by only being able to allocate pages <= BITS_PER_LONG, as noted by the strategically positioned BUG_ON() at lib/bitmap.c:752: /* We don't do regions of pages > BITS_PER_LONG. The * algorithm would be a simple look for multiple zeros in the * array, but there's no driver today that needs this. If you * trip this BUG(), you get to code it... */ BUG_ON(pages > BITS_PER_LONG); As I seem to have been the first person to trigger this, the result ends up being the following patch set with the help of Paul Jackson. The final patch in the series eliminates quite a bit of code duplication, so the bitmap code size ends up being smaller than the current implementation as an added bonus. After these are applied, it should already be possible to do multiword allocations with dma_alloc_coherent() out of ranges established by dma_declare_coherent_memory() on x86 without having to change any of the code, and the SH store queue API will follow up on this as the other user that needs support for this. This patch: Some code cleanup on the lib/bitmap.c bitmap_*_region() routines: * spacing * variable names * comments Has no change to code function. Signed-off-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:15:44 +08:00
*
* Allocate (set bits in) a specified region of a bitmap.
*
* Return 0 on success, or %-EBUSY if specified region wasn't
[PATCH] bitmap: region cleanup Paul Mundt <lethal@linux-sh.org> says: This patch set implements a number of patches to clean up and restructure the bitmap region code, in addition to extending the interface to support multiword spanning allocations. The current implementation (before this patch set) is limited by only being able to allocate pages <= BITS_PER_LONG, as noted by the strategically positioned BUG_ON() at lib/bitmap.c:752: /* We don't do regions of pages > BITS_PER_LONG. The * algorithm would be a simple look for multiple zeros in the * array, but there's no driver today that needs this. If you * trip this BUG(), you get to code it... */ BUG_ON(pages > BITS_PER_LONG); As I seem to have been the first person to trigger this, the result ends up being the following patch set with the help of Paul Jackson. The final patch in the series eliminates quite a bit of code duplication, so the bitmap code size ends up being smaller than the current implementation as an added bonus. After these are applied, it should already be possible to do multiword allocations with dma_alloc_coherent() out of ranges established by dma_declare_coherent_memory() on x86 without having to change any of the code, and the SH store queue API will follow up on this as the other user that needs support for this. This patch: Some code cleanup on the lib/bitmap.c bitmap_*_region() routines: * spacing * variable names * comments Has no change to code function. Signed-off-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 19:15:44 +08:00
* free (not all bits were zero).
*/
int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order)
{
if (!__reg_op(bitmap, pos, order, REG_OP_ISFREE))
return -EBUSY;
return __reg_op(bitmap, pos, order, REG_OP_ALLOC);
}
EXPORT_SYMBOL(bitmap_allocate_region);
/**
* bitmap_copy_le - copy a bitmap, putting the bits into little-endian order.
* @dst: destination buffer
* @src: bitmap to copy
* @nbits: number of bits in the bitmap
*
* Require nbits % BITS_PER_LONG == 0.
*/
void bitmap_copy_le(void *dst, const unsigned long *src, int nbits)
{
unsigned long *d = dst;
int i;
for (i = 0; i < nbits/BITS_PER_LONG; i++) {
if (BITS_PER_LONG == 64)
d[i] = cpu_to_le64(src[i]);
else
d[i] = cpu_to_le32(src[i]);
}
}
EXPORT_SYMBOL(bitmap_copy_le);