OpenCloudOS-Kernel/lib/bitmap.c

1487 lines
44 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* lib/bitmap.c
* Helper functions for bitmap.h.
*/
#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/bug.h>
#include <linux/ctype.h>
#include <linux/device.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/thread_info.h>
#include <linux/uaccess.h>
#include <asm/page.h>
#include "kstrtox.h"
/**
* DOC: bitmap introduction
*
* bitmaps provide an array of bits, implemented using 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.
*
* 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.
*/
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);
bool __bitmap_or_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2,
const unsigned long *bitmap3,
unsigned int bits)
{
unsigned int k, lim = bits / BITS_PER_LONG;
unsigned long tmp;
for (k = 0; k < lim; ++k) {
if ((bitmap1[k] | bitmap2[k]) != bitmap3[k])
return false;
}
if (!(bits % BITS_PER_LONG))
return true;
tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k];
return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0;
}
void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits)
{
unsigned int k, lim = BITS_TO_LONGS(bits);
for (k = 0; k < lim; ++k)
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
lib: bitmap: change bitmap_shift_right to take unsigned parameters I've previously changed the nbits parameter of most bitmap_* functions to unsigned; now it is bitmap_shift_{left,right}'s turn. This alone saves some .text, but while at it I found that there were a few other things one could do. The end result of these seven patches is $ scripts/bloat-o-meter /tmp/bitmap.o.{old,new} add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-328 (-328) function old new delta __bitmap_shift_right 384 226 -158 __bitmap_shift_left 306 136 -170 and less importantly also a smaller stack footprint $ stack-o-meter.pl master bitmap file function old new delta lib/bitmap.o __bitmap_shift_right 24 8 -16 lib/bitmap.o __bitmap_shift_left 24 0 -24 For each pair of 0 <= shift <= nbits <= 256 I've tested the end result with a few randomly filled src buffers (including garbage beyond nbits), in each case verifying that the shift {left,right}-most bits of dst are zero and the remaining nbits-shift bits correspond to src, so I'm fairly confident I didn't screw up. That hasn't stopped me from being wrong before, though. This patch (of 7): gcc can generate slightly better code for stuff like "nbits % BITS_PER_LONG" when it knows nbits is not negative. Since negative size bitmaps or shift amounts don't make sense, change these parameters of bitmap_shift_right to unsigned. The expressions involving "lim - 1" are still ok, since if lim is 0 the loop is never executed. Also use "shift" and "nbits" consistently for the parameter names. 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>
2015-02-14 06:36:02 +08:00
* @nbits : 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.
*/
lib: bitmap: change bitmap_shift_right to take unsigned parameters I've previously changed the nbits parameter of most bitmap_* functions to unsigned; now it is bitmap_shift_{left,right}'s turn. This alone saves some .text, but while at it I found that there were a few other things one could do. The end result of these seven patches is $ scripts/bloat-o-meter /tmp/bitmap.o.{old,new} add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-328 (-328) function old new delta __bitmap_shift_right 384 226 -158 __bitmap_shift_left 306 136 -170 and less importantly also a smaller stack footprint $ stack-o-meter.pl master bitmap file function old new delta lib/bitmap.o __bitmap_shift_right 24 8 -16 lib/bitmap.o __bitmap_shift_left 24 0 -24 For each pair of 0 <= shift <= nbits <= 256 I've tested the end result with a few randomly filled src buffers (including garbage beyond nbits), in each case verifying that the shift {left,right}-most bits of dst are zero and the remaining nbits-shift bits correspond to src, so I'm fairly confident I didn't screw up. That hasn't stopped me from being wrong before, though. This patch (of 7): gcc can generate slightly better code for stuff like "nbits % BITS_PER_LONG" when it knows nbits is not negative. Since negative size bitmaps or shift amounts don't make sense, change these parameters of bitmap_shift_right to unsigned. The expressions involving "lim - 1" are still ok, since if lim is 0 the loop is never executed. Also use "shift" and "nbits" consistently for the parameter names. 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>
2015-02-14 06:36:02 +08:00
void __bitmap_shift_right(unsigned long *dst, const unsigned long *src,
unsigned shift, unsigned nbits)
{
unsigned k, lim = BITS_TO_LONGS(nbits);
lib: bitmap: change bitmap_shift_right to take unsigned parameters I've previously changed the nbits parameter of most bitmap_* functions to unsigned; now it is bitmap_shift_{left,right}'s turn. This alone saves some .text, but while at it I found that there were a few other things one could do. The end result of these seven patches is $ scripts/bloat-o-meter /tmp/bitmap.o.{old,new} add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-328 (-328) function old new delta __bitmap_shift_right 384 226 -158 __bitmap_shift_left 306 136 -170 and less importantly also a smaller stack footprint $ stack-o-meter.pl master bitmap file function old new delta lib/bitmap.o __bitmap_shift_right 24 8 -16 lib/bitmap.o __bitmap_shift_left 24 0 -24 For each pair of 0 <= shift <= nbits <= 256 I've tested the end result with a few randomly filled src buffers (including garbage beyond nbits), in each case verifying that the shift {left,right}-most bits of dst are zero and the remaining nbits-shift bits correspond to src, so I'm fairly confident I didn't screw up. That hasn't stopped me from being wrong before, though. This patch (of 7): gcc can generate slightly better code for stuff like "nbits % BITS_PER_LONG" when it knows nbits is not negative. Since negative size bitmaps or shift amounts don't make sense, change these parameters of bitmap_shift_right to unsigned. The expressions involving "lim - 1" are still ok, since if lim is 0 the loop is never executed. Also use "shift" and "nbits" consistently for the parameter names. 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>
2015-02-14 06:36:02 +08:00
unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
unsigned long mask = BITMAP_LAST_WORD_MASK(nbits);
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)
upper &= mask;
upper <<= (BITS_PER_LONG - rem);
}
lower = src[off + k];
if (off + k == lim - 1)
lower &= mask;
lower >>= rem;
dst[k] = lower | upper;
}
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
* @nbits : 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,
unsigned int shift, unsigned int nbits)
{
int k;
unsigned int lim = BITS_TO_LONGS(nbits);
unsigned 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] >> (BITS_PER_LONG - rem);
else
lower = 0;
upper = src[k] << rem;
dst[k + off] = lower | upper;
}
if (off)
memset(dst, 0, off*sizeof(unsigned long));
}
EXPORT_SYMBOL(__bitmap_shift_left);
/**
* bitmap_cut() - remove bit region from bitmap and right shift remaining bits
* @dst: destination bitmap, might overlap with src
* @src: source bitmap
* @first: start bit of region to be removed
* @cut: number of bits to remove
* @nbits: bitmap size, in bits
*
* Set the n-th bit of @dst iff the n-th bit of @src is set and
* n is less than @first, or the m-th bit of @src is set for any
* m such that @first <= n < nbits, and m = n + @cut.
*
* In pictures, example for a big-endian 32-bit architecture:
*
* The @src bitmap is::
*
* 31 63
* | |
* 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101
* | | | |
* 16 14 0 32
*
* if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is::
*
* 31 63
* | |
* 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010
* | | |
* 14 (bit 17 0 32
* from @src)
*
* Note that @dst and @src might overlap partially or entirely.
*
* This is implemented in the obvious way, with a shift and carry
* step for each moved bit. Optimisation is left as an exercise
* for the compiler.
*/
void bitmap_cut(unsigned long *dst, const unsigned long *src,
unsigned int first, unsigned int cut, unsigned int nbits)
{
unsigned int len = BITS_TO_LONGS(nbits);
unsigned long keep = 0, carry;
int i;
if (first % BITS_PER_LONG) {
keep = src[first / BITS_PER_LONG] &
(~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG));
}
memmove(dst, src, len * sizeof(*dst));
while (cut--) {
for (i = first / BITS_PER_LONG; i < len; i++) {
if (i < len - 1)
carry = dst[i + 1] & 1UL;
else
carry = 0;
dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1));
}
}
dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG);
dst[first / BITS_PER_LONG] |= keep;
}
EXPORT_SYMBOL(bitmap_cut);
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);
void __bitmap_replace(unsigned long *dst,
const unsigned long *old, const unsigned long *new,
const unsigned long *mask, unsigned int nbits)
{
unsigned int k;
unsigned int nr = BITS_TO_LONGS(nbits);
for (k = 0; k < nr; k++)
dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]);
}
EXPORT_SYMBOL(__bitmap_replace);
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_off - 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
* @align_offset: Alignment offset 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 plus @align_offset
* is multiple of that power of 2.
*/
unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
unsigned long size,
unsigned long start,
unsigned int nr,
unsigned long align_mask,
unsigned long align_offset)
{
unsigned long index, end, i;
again:
index = find_next_zero_bit(map, size, start);
/* Align allocation */
index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset;
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_off);
/*
* Bitmap printing & parsing functions: first version by Nadia Yvette Chambers,
* second version by Paul Jackson, third by Joe Korty.
*/
/**
* 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.
*/
int bitmap_parse_user(const char __user *ubuf,
unsigned int ulen, unsigned long *maskp,
int nmaskbits)
{
char *buf;
int ret;
buf = memdup_user_nul(ubuf, ulen);
if (IS_ERR(buf))
return PTR_ERR(buf);
lib: rework bitmap_parse() bitmap_parse() is ineffective and full of opaque variables and opencoded parts. It leads to hard understanding and usage of it. This rework includes: - remove bitmap_shift_left() call from the cycle. Now it makes the complexity of the algorithm as O(nbits^2). In the suggested approach the input string is parsed in reverse direction, so no shifts needed; - relax requirement on a single comma and no white spaces between chunks. It is considered useful in scripting, and it aligns with bitmap_parselist(); - split bitmap_parse() to small readable helpers; - make an explicit calculation of the end of input line at the beginning, so users of the bitmap_parse() won't bother doing this. Link: http://lkml.kernel.org/r/20200102043031.30357-6-yury.norov@gmail.com Signed-off-by: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 09:37:34 +08:00
ret = bitmap_parse(buf, UINT_MAX, maskp, nmaskbits);
kfree(buf);
return ret;
}
EXPORT_SYMBOL(bitmap_parse_user);
/**
* bitmap_print_to_pagebuf - convert bitmap to list or hex format ASCII string
* @list: indicates whether the bitmap must be list
* @buf: page aligned buffer into which string is placed
* @maskp: pointer to bitmap to convert
* @nmaskbits: size of bitmap, in bits
*
* Output format is a comma-separated list of decimal numbers and
* ranges if list is specified or hex digits grouped into comma-separated
* sets of 8 digits/set. Returns the number of characters written to buf.
*
* It is assumed that @buf is a pointer into a PAGE_SIZE, page-aligned
* area and that sufficient storage remains at @buf to accommodate the
* bitmap_print_to_pagebuf() output. Returns the number of characters
* actually printed to @buf, excluding terminating '\0'.
*/
int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp,
int nmaskbits)
{
ptrdiff_t len = PAGE_SIZE - offset_in_page(buf);
return list ? scnprintf(buf, len, "%*pbl\n", nmaskbits, maskp) :
scnprintf(buf, len, "%*pb\n", nmaskbits, maskp);
}
EXPORT_SYMBOL(bitmap_print_to_pagebuf);
cpumask: introduce cpumap_print_list/bitmask_to_buf to support large bitmask and list The existing cpumap_print_to_pagebuf() is used by cpu topology and other drivers to export hexadecimal bitmask and decimal list to userspace by sysfs ABI. Right now, those drivers are using a normal attribute for this kind of ABIs. A normal attribute typically has show entry as below: static ssize_t example_dev_show(struct device *dev, struct device_attribute *attr, char *buf) { ... return cpumap_print_to_pagebuf(true, buf, &pmu_mmdc->cpu); } show entry of attribute has no offset and count parameters and this means the file is limited to one page only. cpumap_print_to_pagebuf() API works terribly well for this kind of normal attribute with buf parameter and without offset, count: static inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } The problem is once we have many cpus, we have a chance to make bitmask or list more than one page. Especially for list, it could be as complex as 0,3,5,7,9,...... We have no simple way to know it exact size. It turns out bin_attribute is a way to break this limit. bin_attribute has show entry as below: static ssize_t example_bin_attribute_show(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t count) { ... } With the new offset and count parameters, this makes sysfs ABI be able to support file size more than one page. For example, offset could be >= 4096. This patch introduces cpumap_print_bitmask/list_to_buf() and their bitmap infrastructure bitmap_print_bitmask/list_to_buf() so that those drivers can move to bin_attribute to support large bitmask and list. At the same time, we have to pass those corresponding parameters such as offset, count from bin_attribute to this new API. Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Stefano Brivio <sbrivio@redhat.com> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: "Ma, Jianpeng" <jianpeng.ma@intel.com> Cc: Yury Norov <yury.norov@gmail.com> Cc: Valentin Schneider <valentin.schneider@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Signed-off-by: Tian Tao <tiantao6@hisilicon.com> Signed-off-by: Barry Song <song.bao.hua@hisilicon.com> Link: https://lore.kernel.org/r/20210806110251.560-2-song.bao.hua@hisilicon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-08-06 19:02:47 +08:00
/**
* bitmap_print_to_buf - convert bitmap to list or hex format ASCII string
* @list: indicates whether the bitmap must be list
* true: print in decimal list format
* false: print in hexadecimal bitmask format
*/
static int bitmap_print_to_buf(bool list, char *buf, const unsigned long *maskp,
int nmaskbits, loff_t off, size_t count)
{
const char *fmt = list ? "%*pbl\n" : "%*pb\n";
ssize_t size;
void *data;
data = kasprintf(GFP_KERNEL, fmt, nmaskbits, maskp);
if (!data)
return -ENOMEM;
size = memory_read_from_buffer(buf, count, &off, data, strlen(data) + 1);
kfree(data);
return size;
}
/**
* bitmap_print_bitmask_to_buf - convert bitmap to hex bitmask format ASCII string
*
* The bitmap_print_to_pagebuf() is used indirectly via its cpumap wrapper
* cpumap_print_to_pagebuf() or directly by drivers to export hexadecimal
* bitmask and decimal list to userspace by sysfs ABI.
* Drivers might be using a normal attribute for this kind of ABIs. A
* normal attribute typically has show entry as below:
* static ssize_t example_attribute_show(struct device *dev,
* struct device_attribute *attr, char *buf)
* {
* ...
* return bitmap_print_to_pagebuf(true, buf, &mask, nr_trig_max);
* }
* show entry of attribute has no offset and count parameters and this
* means the file is limited to one page only.
* bitmap_print_to_pagebuf() API works terribly well for this kind of
* normal attribute with buf parameter and without offset, count:
* bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp,
* int nmaskbits)
* {
* }
* The problem is once we have a large bitmap, we have a chance to get a
* bitmask or list more than one page. Especially for list, it could be
* as complex as 0,3,5,7,9,... We have no simple way to know it exact size.
* It turns out bin_attribute is a way to break this limit. bin_attribute
* has show entry as below:
* static ssize_t
* example_bin_attribute_show(struct file *filp, struct kobject *kobj,
* struct bin_attribute *attr, char *buf,
* loff_t offset, size_t count)
* {
* ...
* }
* With the new offset and count parameters, this makes sysfs ABI be able
* to support file size more than one page. For example, offset could be
* >= 4096.
* bitmap_print_bitmask_to_buf(), bitmap_print_list_to_buf() wit their
* cpumap wrapper cpumap_print_bitmask_to_buf(), cpumap_print_list_to_buf()
* make those drivers be able to support large bitmask and list after they
* move to use bin_attribute. In result, we have to pass the corresponding
* parameters such as off, count from bin_attribute show entry to this API.
*
* @buf: buffer into which string is placed
* @maskp: pointer to bitmap to convert
* @nmaskbits: size of bitmap, in bits
* @off: in the string from which we are copying, We copy to @buf
* @count: the maximum number of bytes to print
*
* The role of cpumap_print_bitmask_to_buf() and cpumap_print_list_to_buf()
* is similar with cpumap_print_to_pagebuf(), the difference is that
* bitmap_print_to_pagebuf() mainly serves sysfs attribute with the assumption
* the destination buffer is exactly one page and won't be more than one page.
* cpumap_print_bitmask_to_buf() and cpumap_print_list_to_buf(), on the other
* hand, mainly serves bin_attribute which doesn't work with exact one page,
* and it can break the size limit of converted decimal list and hexadecimal
* bitmask.
*
* WARNING!
*
* This function is not a replacement for sprintf() or bitmap_print_to_pagebuf().
* It is intended to workaround sysfs limitations discussed above and should be
* used carefully in general case for the following reasons:
* - Time complexity is O(nbits^2/count), comparing to O(nbits) for snprintf().
* - Memory complexity is O(nbits), comparing to O(1) for snprintf().
* - @off and @count are NOT offset and number of bits to print.
* - If printing part of bitmap as list, the resulting string is not a correct
* list representation of bitmap. Particularly, some bits within or out of
* related interval may be erroneously set or unset. The format of the string
* may be broken, so bitmap_parselist-like parser may fail parsing it.
* - If printing the whole bitmap as list by parts, user must ensure the order
* of calls of the function such that the offset is incremented linearly.
* - If printing the whole bitmap as list by parts, user must keep bitmap
* unchanged between the very first and very last call. Otherwise concatenated
* result may be incorrect, and format may be broken.
*
cpumask: introduce cpumap_print_list/bitmask_to_buf to support large bitmask and list The existing cpumap_print_to_pagebuf() is used by cpu topology and other drivers to export hexadecimal bitmask and decimal list to userspace by sysfs ABI. Right now, those drivers are using a normal attribute for this kind of ABIs. A normal attribute typically has show entry as below: static ssize_t example_dev_show(struct device *dev, struct device_attribute *attr, char *buf) { ... return cpumap_print_to_pagebuf(true, buf, &pmu_mmdc->cpu); } show entry of attribute has no offset and count parameters and this means the file is limited to one page only. cpumap_print_to_pagebuf() API works terribly well for this kind of normal attribute with buf parameter and without offset, count: static inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } The problem is once we have many cpus, we have a chance to make bitmask or list more than one page. Especially for list, it could be as complex as 0,3,5,7,9,...... We have no simple way to know it exact size. It turns out bin_attribute is a way to break this limit. bin_attribute has show entry as below: static ssize_t example_bin_attribute_show(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t offset, size_t count) { ... } With the new offset and count parameters, this makes sysfs ABI be able to support file size more than one page. For example, offset could be >= 4096. This patch introduces cpumap_print_bitmask/list_to_buf() and their bitmap infrastructure bitmap_print_bitmask/list_to_buf() so that those drivers can move to bin_attribute to support large bitmask and list. At the same time, we have to pass those corresponding parameters such as offset, count from bin_attribute to this new API. Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Stefano Brivio <sbrivio@redhat.com> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: "Ma, Jianpeng" <jianpeng.ma@intel.com> Cc: Yury Norov <yury.norov@gmail.com> Cc: Valentin Schneider <valentin.schneider@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Daniel Bristot de Oliveira <bristot@redhat.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Signed-off-by: Tian Tao <tiantao6@hisilicon.com> Signed-off-by: Barry Song <song.bao.hua@hisilicon.com> Link: https://lore.kernel.org/r/20210806110251.560-2-song.bao.hua@hisilicon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-08-06 19:02:47 +08:00
* Returns the number of characters actually printed to @buf
*/
int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp,
int nmaskbits, loff_t off, size_t count)
{
return bitmap_print_to_buf(false, buf, maskp, nmaskbits, off, count);
}
EXPORT_SYMBOL(bitmap_print_bitmask_to_buf);
/**
* bitmap_print_list_to_buf - convert bitmap to decimal list format ASCII string
*
* Everything is same with the above bitmap_print_bitmask_to_buf() except
* the print format.
*/
int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp,
int nmaskbits, loff_t off, size_t count)
{
return bitmap_print_to_buf(true, buf, maskp, nmaskbits, off, count);
}
EXPORT_SYMBOL(bitmap_print_list_to_buf);
/*
* Region 9-38:4/10 describes the following bitmap structure:
* 0 9 12 18 38 N
* .........****......****......****..................
* ^ ^ ^ ^ ^
* start off group_len end nbits
*/
struct region {
unsigned int start;
unsigned int off;
unsigned int group_len;
unsigned int end;
unsigned int nbits;
};
static void bitmap_set_region(const struct region *r, unsigned long *bitmap)
{
unsigned int start;
for (start = r->start; start <= r->end; start += r->group_len)
bitmap_set(bitmap, start, min(r->end - start + 1, r->off));
}
static int bitmap_check_region(const struct region *r)
{
if (r->start > r->end || r->group_len == 0 || r->off > r->group_len)
return -EINVAL;
if (r->end >= r->nbits)
return -ERANGE;
return 0;
}
static const char *bitmap_getnum(const char *str, unsigned int *num,
unsigned int lastbit)
{
unsigned long long n;
unsigned int len;
if (str[0] == 'N') {
*num = lastbit;
return str + 1;
}
len = _parse_integer(str, 10, &n);
if (!len)
return ERR_PTR(-EINVAL);
if (len & KSTRTOX_OVERFLOW || n != (unsigned int)n)
return ERR_PTR(-EOVERFLOW);
*num = n;
return str + len;
}
static inline bool end_of_str(char c)
{
return c == '\0' || c == '\n';
}
static inline bool __end_of_region(char c)
{
return isspace(c) || c == ',';
}
static inline bool end_of_region(char c)
{
return __end_of_region(c) || end_of_str(c);
}
/*
* The format allows commas and whitespaces at the beginning
* of the region.
*/
static const char *bitmap_find_region(const char *str)
{
while (__end_of_region(*str))
str++;
return end_of_str(*str) ? NULL : str;
}
lib: rework bitmap_parse() bitmap_parse() is ineffective and full of opaque variables and opencoded parts. It leads to hard understanding and usage of it. This rework includes: - remove bitmap_shift_left() call from the cycle. Now it makes the complexity of the algorithm as O(nbits^2). In the suggested approach the input string is parsed in reverse direction, so no shifts needed; - relax requirement on a single comma and no white spaces between chunks. It is considered useful in scripting, and it aligns with bitmap_parselist(); - split bitmap_parse() to small readable helpers; - make an explicit calculation of the end of input line at the beginning, so users of the bitmap_parse() won't bother doing this. Link: http://lkml.kernel.org/r/20200102043031.30357-6-yury.norov@gmail.com Signed-off-by: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 09:37:34 +08:00
static const char *bitmap_find_region_reverse(const char *start, const char *end)
{
while (start <= end && __end_of_region(*end))
end--;
return end;
}
static const char *bitmap_parse_region(const char *str, struct region *r)
{
unsigned int lastbit = r->nbits - 1;
if (!strncasecmp(str, "all", 3)) {
r->start = 0;
r->end = lastbit;
str += 3;
goto check_pattern;
}
str = bitmap_getnum(str, &r->start, lastbit);
if (IS_ERR(str))
return str;
if (end_of_region(*str))
goto no_end;
if (*str != '-')
return ERR_PTR(-EINVAL);
str = bitmap_getnum(str + 1, &r->end, lastbit);
if (IS_ERR(str))
return str;
check_pattern:
if (end_of_region(*str))
goto no_pattern;
if (*str != ':')
return ERR_PTR(-EINVAL);
str = bitmap_getnum(str + 1, &r->off, lastbit);
if (IS_ERR(str))
return str;
if (*str != '/')
return ERR_PTR(-EINVAL);
return bitmap_getnum(str + 1, &r->group_len, lastbit);
no_end:
r->end = r->start;
no_pattern:
r->off = r->end + 1;
r->group_len = r->end + 1;
return end_of_str(*str) ? NULL : str;
}
/**
* bitmap_parselist - convert list format ASCII string to bitmap
* @buf: read user string from this buffer; must be terminated
* with a \0 or \n.
* @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.
2016-10-12 04:51:35 +08:00
* Optionally each range can be postfixed to denote that only parts of it
* should be set. The range will divided to groups of specific size.
* From each group will be used only defined amount of bits.
* Syntax: range:used_size/group_size
* Example: 0-1023:2/256 ==> 0,1,256,257,512,513,768,769
* The value 'N' can be used as a dynamically substituted token for the
* maximum allowed value; i.e (nmaskbits - 1). Keep in mind that it is
* dynamic, so if system changes cause the bitmap width to change, such
* as more cores in a CPU list, then any ranges using N will also change.
*
* Returns: 0 on success, -errno on invalid input strings. Error values:
*
* - ``-EINVAL``: wrong region format
* - ``-EINVAL``: invalid character in string
* - ``-ERANGE``: bit number specified too large for mask
* - ``-EOVERFLOW``: integer overflow in the input parameters
*/
int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits)
{
struct region r;
long ret;
r.nbits = nmaskbits;
bitmap_zero(maskp, r.nbits);
while (buf) {
buf = bitmap_find_region(buf);
if (buf == NULL)
return 0;
2016-10-12 04:51:35 +08:00
buf = bitmap_parse_region(buf, &r);
if (IS_ERR(buf))
return PTR_ERR(buf);
2016-10-12 04:51:35 +08:00
ret = bitmap_check_region(&r);
if (ret)
return ret;
bitmap_set_region(&r, maskp);
}
return 0;
}
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.
*/
int bitmap_parselist_user(const char __user *ubuf,
unsigned int ulen, unsigned long *maskp,
int nmaskbits)
{
lib: make bitmap_parselist_user() a wrapper on bitmap_parselist() Patch series "lib: rework bitmap_parselist and tests", v5. bitmap_parselist has been evolved from a pretty simple idea for long and now lacks for refactoring. It is not structured, has nested loops and a set of opaque-named variables. Things are more complicated because bitmap_parselist() is a part of user interface, and its behavior should not change. In this patchset - bitmap_parselist_user() made a wrapper on bitmap_parselist(); - bitmap_parselist() reworked (patch 2); - time measurement in test_bitmap_parselist switched to ktime_get (patch 3); - new tests introduced (patch 4), and - bitmap_parselist_user() testing enabled with the same testset as bitmap_parselist() (patch 5). This patch (of 5): Currently we parse user data byte after byte which leads to overcomplification of parsing algorithm. The only user of bitmap_parselist_user() is not performance-critical, and so we can duplicate user data to kernel buffer and simply call bitmap_parselist(). This rework lets us unify and simplify bitmap_parselist() and bitmap_parselist_user(), which is done in the following patch. Link: http://lkml.kernel.org/r/20190405173211.11373-2-ynorov@marvell.com Signed-off-by: Yury Norov <ynorov@marvell.com> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: Mike Travis <travis@sgi.com> Cc: Guenter Roeck <linux@roeck-us.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-15 06:43:11 +08:00
char *buf;
int ret;
buf = memdup_user_nul(ubuf, ulen);
if (IS_ERR(buf))
return PTR_ERR(buf);
ret = bitmap_parselist(buf, maskp, nmaskbits);
kfree(buf);
return ret;
}
EXPORT_SYMBOL(bitmap_parselist_user);
lib: rework bitmap_parse() bitmap_parse() is ineffective and full of opaque variables and opencoded parts. It leads to hard understanding and usage of it. This rework includes: - remove bitmap_shift_left() call from the cycle. Now it makes the complexity of the algorithm as O(nbits^2). In the suggested approach the input string is parsed in reverse direction, so no shifts needed; - relax requirement on a single comma and no white spaces between chunks. It is considered useful in scripting, and it aligns with bitmap_parselist(); - split bitmap_parse() to small readable helpers; - make an explicit calculation of the end of input line at the beginning, so users of the bitmap_parse() won't bother doing this. Link: http://lkml.kernel.org/r/20200102043031.30357-6-yury.norov@gmail.com Signed-off-by: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 09:37:34 +08:00
static const char *bitmap_get_x32_reverse(const char *start,
const char *end, u32 *num)
{
u32 ret = 0;
int c, i;
for (i = 0; i < 32; i += 4) {
c = hex_to_bin(*end--);
if (c < 0)
return ERR_PTR(-EINVAL);
ret |= c << i;
if (start > end || __end_of_region(*end))
goto out;
}
if (hex_to_bin(*end--) >= 0)
return ERR_PTR(-EOVERFLOW);
out:
*num = ret;
return end;
}
/**
* bitmap_parse - convert an ASCII hex string into a bitmap.
* @start: pointer to buffer containing string.
* @buflen: buffer size in bytes. If string is smaller than this
* then it must be terminated with a \0 or \n. In that case,
* UINT_MAX may be provided instead of string length.
* @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. Grouping such as "1,,5", ",44", "," or "" is allowed.
* Leading, embedded and trailing whitespace accepted.
*/
int bitmap_parse(const char *start, unsigned int buflen,
unsigned long *maskp, int nmaskbits)
{
const char *end = strnchrnul(start, buflen, '\n') - 1;
int chunks = BITS_TO_U32(nmaskbits);
u32 *bitmap = (u32 *)maskp;
int unset_bit;
lib: fix bitmap_parse() on 64-bit big endian archs Commit 2d6261583be0 ("lib: rework bitmap_parse()") does not take into account order of halfwords on 64-bit big endian architectures. As result (at least) Receive Packet Steering, IRQ affinity masks and runtime kernel test "test_bitmap" get broken on s390. [andriy.shevchenko@linux.intel.com: convert infinite while loop to a for loop] Link: http://lkml.kernel.org/r/20200609140535.87160-1-andriy.shevchenko@linux.intel.com Fixes: 2d6261583be0 ("lib: rework bitmap_parse()") Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/1591634471-17647-1-git-send-email-agordeev@linux.ibm.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-11 09:41:41 +08:00
int chunk;
lib: rework bitmap_parse() bitmap_parse() is ineffective and full of opaque variables and opencoded parts. It leads to hard understanding and usage of it. This rework includes: - remove bitmap_shift_left() call from the cycle. Now it makes the complexity of the algorithm as O(nbits^2). In the suggested approach the input string is parsed in reverse direction, so no shifts needed; - relax requirement on a single comma and no white spaces between chunks. It is considered useful in scripting, and it aligns with bitmap_parselist(); - split bitmap_parse() to small readable helpers; - make an explicit calculation of the end of input line at the beginning, so users of the bitmap_parse() won't bother doing this. Link: http://lkml.kernel.org/r/20200102043031.30357-6-yury.norov@gmail.com Signed-off-by: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 09:37:34 +08:00
lib: fix bitmap_parse() on 64-bit big endian archs Commit 2d6261583be0 ("lib: rework bitmap_parse()") does not take into account order of halfwords on 64-bit big endian architectures. As result (at least) Receive Packet Steering, IRQ affinity masks and runtime kernel test "test_bitmap" get broken on s390. [andriy.shevchenko@linux.intel.com: convert infinite while loop to a for loop] Link: http://lkml.kernel.org/r/20200609140535.87160-1-andriy.shevchenko@linux.intel.com Fixes: 2d6261583be0 ("lib: rework bitmap_parse()") Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/1591634471-17647-1-git-send-email-agordeev@linux.ibm.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-11 09:41:41 +08:00
for (chunk = 0; ; chunk++) {
lib: rework bitmap_parse() bitmap_parse() is ineffective and full of opaque variables and opencoded parts. It leads to hard understanding and usage of it. This rework includes: - remove bitmap_shift_left() call from the cycle. Now it makes the complexity of the algorithm as O(nbits^2). In the suggested approach the input string is parsed in reverse direction, so no shifts needed; - relax requirement on a single comma and no white spaces between chunks. It is considered useful in scripting, and it aligns with bitmap_parselist(); - split bitmap_parse() to small readable helpers; - make an explicit calculation of the end of input line at the beginning, so users of the bitmap_parse() won't bother doing this. Link: http://lkml.kernel.org/r/20200102043031.30357-6-yury.norov@gmail.com Signed-off-by: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 09:37:34 +08:00
end = bitmap_find_region_reverse(start, end);
if (start > end)
break;
if (!chunks--)
return -EOVERFLOW;
lib: fix bitmap_parse() on 64-bit big endian archs Commit 2d6261583be0 ("lib: rework bitmap_parse()") does not take into account order of halfwords on 64-bit big endian architectures. As result (at least) Receive Packet Steering, IRQ affinity masks and runtime kernel test "test_bitmap" get broken on s390. [andriy.shevchenko@linux.intel.com: convert infinite while loop to a for loop] Link: http://lkml.kernel.org/r/20200609140535.87160-1-andriy.shevchenko@linux.intel.com Fixes: 2d6261583be0 ("lib: rework bitmap_parse()") Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com> Cc: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/1591634471-17647-1-git-send-email-agordeev@linux.ibm.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-11 09:41:41 +08:00
#if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN)
end = bitmap_get_x32_reverse(start, end, &bitmap[chunk ^ 1]);
#else
end = bitmap_get_x32_reverse(start, end, &bitmap[chunk]);
#endif
lib: rework bitmap_parse() bitmap_parse() is ineffective and full of opaque variables and opencoded parts. It leads to hard understanding and usage of it. This rework includes: - remove bitmap_shift_left() call from the cycle. Now it makes the complexity of the algorithm as O(nbits^2). In the suggested approach the input string is parsed in reverse direction, so no shifts needed; - relax requirement on a single comma and no white spaces between chunks. It is considered useful in scripting, and it aligns with bitmap_parselist(); - split bitmap_parse() to small readable helpers; - make an explicit calculation of the end of input line at the beginning, so users of the bitmap_parse() won't bother doing this. Link: http://lkml.kernel.org/r/20200102043031.30357-6-yury.norov@gmail.com Signed-off-by: Yury Norov <yury.norov@gmail.com> Cc: Amritha Nambiar <amritha.nambiar@intel.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miklos Szeredi <mszeredi@redhat.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: "Tobin C . Harding" <tobin@kernel.org> Cc: Vineet Gupta <vineet.gupta1@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-02-04 09:37:34 +08:00
if (IS_ERR(end))
return PTR_ERR(end);
}
unset_bit = (BITS_TO_U32(nmaskbits) - chunks) * 32;
if (unset_bit < nmaskbits) {
bitmap_clear(maskp, unset_bit, nmaskbits - unset_bit);
return 0;
}
if (find_next_bit(maskp, unset_bit, nmaskbits) != unset_bit)
return -EOVERFLOW;
return 0;
}
EXPORT_SYMBOL(bitmap_parse);
/**
* 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 < @nbits)
* @nbits: number of valid bit positions in @buf
*
* Map the bit at position @pos in @buf (of length @nbits) 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, unsigned int pos, unsigned int nbits)
{
if (pos >= nbits || !test_bit(pos, buf))
return -1;
return __bitmap_weight(buf, pos);
}
/**
* 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)
* @nbits: 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). If @ord
* >= weight(buf), returns @nbits.
*
* 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 returns @nbits. 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 @nbits-1 are valid positions in @buf.
*/
unsigned int bitmap_ord_to_pos(const unsigned long *buf, unsigned int ord, unsigned int nbits)
{
unsigned int pos;
for (pos = find_first_bit(buf, nbits);
pos < nbits && ord;
pos = find_next_bit(buf, nbits, pos + 1))
ord--;
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
* @nbits: 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,
unsigned int nbits)
{
unsigned int oldbit, w;
if (dst == src) /* following doesn't handle inplace remaps */
return;
bitmap_zero(dst, nbits);
w = bitmap_weight(new, nbits);
for_each_set_bit(oldbit, src, nbits) {
int n = bitmap_pos_to_ord(old, oldbit, nbits);
if (n < 0 || w == 0)
set_bit(oldbit, dst); /* identity map */
else
set_bit(bitmap_ord_to_pos(new, n % w, nbits), 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);
#ifdef CONFIG_NUMA
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 map { <n, m> | the n-th bit of @relmap is the
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-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::
*
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
* 40 41 42 43 45 48 53 61 74 95
*
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
* (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 possibility of an empty @dst result::
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
*
* 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):
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
*
* =============== ============== =================
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
* @orig tmp @dst
* 0 0 40
* 1 1 41
* 9 9 95
* 10 0 40 [#f1]_
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
* 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 [#f1]_
* =============== ============== =================
*
* .. [#f1]
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
*
* For these marked lines, if we hadn't first done bitmap_fold()
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
* 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, unsigned int 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
{
unsigned int n, m; /* same meaning as in above comment */
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
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++;
}
}
/**
* bitmap_fold - fold larger bitmap into smaller, modulo specified size
* @dst: resulting smaller bitmap
* @orig: original larger bitmap
* @sz: specified size
* @nbits: number of bits in each of these bitmaps
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
*
* 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,
unsigned int sz, unsigned int nbits)
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
{
unsigned int oldbit;
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
if (dst == orig) /* following doesn't handle inplace mappings */
return;
bitmap_zero(dst, nbits);
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
for_each_set_bit(oldbit, orig, nbits)
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);
}
#endif /* CONFIG_NUMA */
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
/*
* 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.
*/
#ifdef __BIG_ENDIAN
void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits)
{
unsigned int i;
for (i = 0; i < nbits/BITS_PER_LONG; i++) {
if (BITS_PER_LONG == 64)
dst[i] = cpu_to_le64(src[i]);
else
dst[i] = cpu_to_le32(src[i]);
}
}
EXPORT_SYMBOL(bitmap_copy_le);
#endif
bitmap: new bitmap_copy_safe and bitmap_{from,to}_arr32 This patchset replaces bitmap_{to,from}_u32array with more simple and standard looking copy-like functions. bitmap_from_u32array() takes 4 arguments (bitmap_to_u32array is similar): - unsigned long *bitmap, which is destination; - unsigned int nbits, the length of destination bitmap, in bits; - const u32 *buf, the source; and - unsigned int nwords, the length of source buffer in ints. In description to the function it is detailed like: * copy min(nbits, 32*nwords) bits from @buf to @bitmap, remaining * bits between nword and nbits in @bitmap (if any) are cleared. Having two size arguments looks unneeded and potentially dangerous. It is unneeded because normally user of copy-like function should take care of the size of destination and make it big enough to fit source data. And it is dangerous because function may hide possible error if user doesn't provide big enough bitmap, and data becomes silently dropped. That's why all copy-like functions have 1 argument for size of copying data, and I don't see any reason to make bitmap_from_u32array() different. One exception that comes in mind is strncpy() which also provides size of destination in arguments, but it's strongly argued by the possibility of taking broken strings in source. This is not the case of bitmap_{from,to}_u32array(). There is no many real users of bitmap_{from,to}_u32array(), and they all very clearly provide size of destination matched with the size of source, so additional functionality is not used in fact. Like this: bitmap_from_u32array(to->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_usettings.link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NU32); Where: #define __ETHTOOL_LINK_MODE_MASK_NU32 \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) In this patch, bitmap_copy_safe and bitmap_{from,to}_arr32 are introduced. 'Safe' in bitmap_copy_safe() stands for clearing unused bits in bitmap beyond last bit till the end of last word. It is useful for hardening API when bitmap is assumed to be exposed to userspace. bitmap_{from,to}_arr32 functions are replacements for bitmap_{from,to}_u32array. They don't take unneeded nwords argument, and so simpler in implementation and understanding. This patch suggests optimization for 32-bit systems - aliasing bitmap_{from,to}_arr32 to bitmap_copy_safe. Other possible optimization is aliasing 64-bit LE bitmap_{from,to}_arr32 to more generic function(s). But I didn't end up with the function that would be helpful by itself, and can be used to alias 64-bit LE bitmap_{from,to}_arr32, like bitmap_copy_safe() does. So I preferred to leave things as is. The following patch switches kernel to new API and introduces test for it. Discussion is here: https://lkml.org/lkml/2017/11/15/592 [ynorov@caviumnetworks.com: rename bitmap_copy_safe to bitmap_copy_clear_tail] Link: http://lkml.kernel.org/r/20180201172508.5739-3-ynorov@caviumnetworks.com Link: http://lkml.kernel.org/r/20171228150019.27953-1-ynorov@caviumnetworks.com Signed-off-by: Yury Norov <ynorov@caviumnetworks.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: David Decotigny <decot@googlers.com>, Cc: David S. Miller <davem@davemloft.net>, Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-07 07:38:02 +08:00
unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags)
{
return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long),
flags);
}
EXPORT_SYMBOL(bitmap_alloc);
unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags)
{
return bitmap_alloc(nbits, flags | __GFP_ZERO);
}
EXPORT_SYMBOL(bitmap_zalloc);
void bitmap_free(const unsigned long *bitmap)
{
kfree(bitmap);
}
EXPORT_SYMBOL(bitmap_free);
static void devm_bitmap_free(void *data)
{
unsigned long *bitmap = data;
bitmap_free(bitmap);
}
unsigned long *devm_bitmap_alloc(struct device *dev,
unsigned int nbits, gfp_t flags)
{
unsigned long *bitmap;
int ret;
bitmap = bitmap_alloc(nbits, flags);
if (!bitmap)
return NULL;
ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap);
if (ret)
return NULL;
return bitmap;
}
EXPORT_SYMBOL_GPL(devm_bitmap_alloc);
unsigned long *devm_bitmap_zalloc(struct device *dev,
unsigned int nbits, gfp_t flags)
{
return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO);
}
EXPORT_SYMBOL_GPL(devm_bitmap_zalloc);
bitmap: new bitmap_copy_safe and bitmap_{from,to}_arr32 This patchset replaces bitmap_{to,from}_u32array with more simple and standard looking copy-like functions. bitmap_from_u32array() takes 4 arguments (bitmap_to_u32array is similar): - unsigned long *bitmap, which is destination; - unsigned int nbits, the length of destination bitmap, in bits; - const u32 *buf, the source; and - unsigned int nwords, the length of source buffer in ints. In description to the function it is detailed like: * copy min(nbits, 32*nwords) bits from @buf to @bitmap, remaining * bits between nword and nbits in @bitmap (if any) are cleared. Having two size arguments looks unneeded and potentially dangerous. It is unneeded because normally user of copy-like function should take care of the size of destination and make it big enough to fit source data. And it is dangerous because function may hide possible error if user doesn't provide big enough bitmap, and data becomes silently dropped. That's why all copy-like functions have 1 argument for size of copying data, and I don't see any reason to make bitmap_from_u32array() different. One exception that comes in mind is strncpy() which also provides size of destination in arguments, but it's strongly argued by the possibility of taking broken strings in source. This is not the case of bitmap_{from,to}_u32array(). There is no many real users of bitmap_{from,to}_u32array(), and they all very clearly provide size of destination matched with the size of source, so additional functionality is not used in fact. Like this: bitmap_from_u32array(to->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_usettings.link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NU32); Where: #define __ETHTOOL_LINK_MODE_MASK_NU32 \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) In this patch, bitmap_copy_safe and bitmap_{from,to}_arr32 are introduced. 'Safe' in bitmap_copy_safe() stands for clearing unused bits in bitmap beyond last bit till the end of last word. It is useful for hardening API when bitmap is assumed to be exposed to userspace. bitmap_{from,to}_arr32 functions are replacements for bitmap_{from,to}_u32array. They don't take unneeded nwords argument, and so simpler in implementation and understanding. This patch suggests optimization for 32-bit systems - aliasing bitmap_{from,to}_arr32 to bitmap_copy_safe. Other possible optimization is aliasing 64-bit LE bitmap_{from,to}_arr32 to more generic function(s). But I didn't end up with the function that would be helpful by itself, and can be used to alias 64-bit LE bitmap_{from,to}_arr32, like bitmap_copy_safe() does. So I preferred to leave things as is. The following patch switches kernel to new API and introduces test for it. Discussion is here: https://lkml.org/lkml/2017/11/15/592 [ynorov@caviumnetworks.com: rename bitmap_copy_safe to bitmap_copy_clear_tail] Link: http://lkml.kernel.org/r/20180201172508.5739-3-ynorov@caviumnetworks.com Link: http://lkml.kernel.org/r/20171228150019.27953-1-ynorov@caviumnetworks.com Signed-off-by: Yury Norov <ynorov@caviumnetworks.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: David Decotigny <decot@googlers.com>, Cc: David S. Miller <davem@davemloft.net>, Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-07 07:38:02 +08:00
#if BITS_PER_LONG == 64
/**
* bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap
* @bitmap: array of unsigned longs, the destination bitmap
* @buf: array of u32 (in host byte order), the source bitmap
* @nbits: number of bits in @bitmap
*/
void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits)
bitmap: new bitmap_copy_safe and bitmap_{from,to}_arr32 This patchset replaces bitmap_{to,from}_u32array with more simple and standard looking copy-like functions. bitmap_from_u32array() takes 4 arguments (bitmap_to_u32array is similar): - unsigned long *bitmap, which is destination; - unsigned int nbits, the length of destination bitmap, in bits; - const u32 *buf, the source; and - unsigned int nwords, the length of source buffer in ints. In description to the function it is detailed like: * copy min(nbits, 32*nwords) bits from @buf to @bitmap, remaining * bits between nword and nbits in @bitmap (if any) are cleared. Having two size arguments looks unneeded and potentially dangerous. It is unneeded because normally user of copy-like function should take care of the size of destination and make it big enough to fit source data. And it is dangerous because function may hide possible error if user doesn't provide big enough bitmap, and data becomes silently dropped. That's why all copy-like functions have 1 argument for size of copying data, and I don't see any reason to make bitmap_from_u32array() different. One exception that comes in mind is strncpy() which also provides size of destination in arguments, but it's strongly argued by the possibility of taking broken strings in source. This is not the case of bitmap_{from,to}_u32array(). There is no many real users of bitmap_{from,to}_u32array(), and they all very clearly provide size of destination matched with the size of source, so additional functionality is not used in fact. Like this: bitmap_from_u32array(to->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_usettings.link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NU32); Where: #define __ETHTOOL_LINK_MODE_MASK_NU32 \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) In this patch, bitmap_copy_safe and bitmap_{from,to}_arr32 are introduced. 'Safe' in bitmap_copy_safe() stands for clearing unused bits in bitmap beyond last bit till the end of last word. It is useful for hardening API when bitmap is assumed to be exposed to userspace. bitmap_{from,to}_arr32 functions are replacements for bitmap_{from,to}_u32array. They don't take unneeded nwords argument, and so simpler in implementation and understanding. This patch suggests optimization for 32-bit systems - aliasing bitmap_{from,to}_arr32 to bitmap_copy_safe. Other possible optimization is aliasing 64-bit LE bitmap_{from,to}_arr32 to more generic function(s). But I didn't end up with the function that would be helpful by itself, and can be used to alias 64-bit LE bitmap_{from,to}_arr32, like bitmap_copy_safe() does. So I preferred to leave things as is. The following patch switches kernel to new API and introduces test for it. Discussion is here: https://lkml.org/lkml/2017/11/15/592 [ynorov@caviumnetworks.com: rename bitmap_copy_safe to bitmap_copy_clear_tail] Link: http://lkml.kernel.org/r/20180201172508.5739-3-ynorov@caviumnetworks.com Link: http://lkml.kernel.org/r/20171228150019.27953-1-ynorov@caviumnetworks.com Signed-off-by: Yury Norov <ynorov@caviumnetworks.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: David Decotigny <decot@googlers.com>, Cc: David S. Miller <davem@davemloft.net>, Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-02-07 07:38:02 +08:00
{
unsigned int i, halfwords;
halfwords = DIV_ROUND_UP(nbits, 32);
for (i = 0; i < halfwords; i++) {
bitmap[i/2] = (unsigned long) buf[i];
if (++i < halfwords)
bitmap[i/2] |= ((unsigned long) buf[i]) << 32;
}
/* Clear tail bits in last word beyond nbits. */
if (nbits % BITS_PER_LONG)
bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits);
}
EXPORT_SYMBOL(bitmap_from_arr32);
/**
* bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits
* @buf: array of u32 (in host byte order), the dest bitmap
* @bitmap: array of unsigned longs, the source bitmap
* @nbits: number of bits in @bitmap
*/
void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits)
{
unsigned int i, halfwords;
halfwords = DIV_ROUND_UP(nbits, 32);
for (i = 0; i < halfwords; i++) {
buf[i] = (u32) (bitmap[i/2] & UINT_MAX);
if (++i < halfwords)
buf[i] = (u32) (bitmap[i/2] >> 32);
}
/* Clear tail bits in last element of array beyond nbits. */
if (nbits % BITS_PER_LONG)
buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31));
}
EXPORT_SYMBOL(bitmap_to_arr32);
#endif