summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
Diffstat (limited to 'lib')
-rw-r--r--lib/Kconfig9
-rw-r--r--lib/Makefile4
-rw-r--r--lib/bitmap.c30
-rw-r--r--lib/cpumask.c37
-rw-r--r--lib/devres.c28
-rw-r--r--lib/dma-debug.c2
-rw-r--r--lib/find_bit.c193
-rw-r--r--lib/find_last_bit.c36
-rw-r--r--lib/find_next_bit.c285
-rw-r--r--lib/iommu-common.c270
-rw-r--r--lib/raid6/algos.c41
-rw-r--r--lib/raid6/altivec.uc1
-rw-r--r--lib/raid6/avx2.c3
-rw-r--r--lib/raid6/int.uc41
-rw-r--r--lib/raid6/mmx.c2
-rw-r--r--lib/raid6/neon.c1
-rw-r--r--lib/raid6/sse1.c2
-rw-r--r--lib/raid6/sse2.c227
-rw-r--r--lib/raid6/test/test.c51
-rw-r--r--lib/raid6/tilegx.uc1
-rw-r--r--lib/string_helpers.c68
-rw-r--r--lib/test-hexdump.c2
-rw-r--r--lib/vsprintf.c244
23 files changed, 1037 insertions, 541 deletions
diff --git a/lib/Kconfig b/lib/Kconfig
index 42c925e9caea..34e332b8d326 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -18,9 +18,8 @@ config HAVE_ARCH_BITREVERSE
default n
depends on BITREVERSE
help
- This option provides an config for the architecture which have instruction
- can do bitreverse operation, we use the hardware instruction if the architecture
- have this capability.
+ This option enables the use of hardware bit-reversal instructions on
+ architectures which support such operations.
config RATIONAL
bool
@@ -403,10 +402,6 @@ config CPUMASK_OFFSTACK
them on the stack. This is a bit more expensive, but avoids
stack overflow.
-config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
- bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS
- depends on BROKEN
-
config CPU_RMAP
bool
depends on SMP
diff --git a/lib/Makefile b/lib/Makefile
index a1d67e408e12..ff37c8c2f7b2 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -25,7 +25,7 @@ obj-y += lockref.o
obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \
- bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
+ bsearch.o find_bit.o llist.o memweight.o kfifo.o \
percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o
obj-y += string_helpers.o
obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
@@ -108,7 +108,7 @@ obj-$(CONFIG_AUDIT_GENERIC) += audit.o
obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
obj-$(CONFIG_SWIOTLB) += swiotlb.o
-obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
+obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o
obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
diff --git a/lib/bitmap.c b/lib/bitmap.c
index d456f4c15a9f..64c0926f5dd8 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -42,36 +42,6 @@
* for the best explanations of this ordering.
*/
-int __bitmap_empty(const unsigned long *bitmap, unsigned int bits)
-{
- unsigned int k, lim = bits/BITS_PER_LONG;
- for (k = 0; k < lim; ++k)
- if (bitmap[k])
- return 0;
-
- if (bits % BITS_PER_LONG)
- if (bitmap[k] & BITMAP_LAST_WORD_MASK(bits))
- return 0;
-
- return 1;
-}
-EXPORT_SYMBOL(__bitmap_empty);
-
-int __bitmap_full(const unsigned long *bitmap, unsigned int bits)
-{
- unsigned int k, lim = bits/BITS_PER_LONG;
- for (k = 0; k < lim; ++k)
- if (~bitmap[k])
- return 0;
-
- if (bits % BITS_PER_LONG)
- if (~bitmap[k] & BITMAP_LAST_WORD_MASK(bits))
- return 0;
-
- return 1;
-}
-EXPORT_SYMBOL(__bitmap_full);
-
int __bitmap_equal(const unsigned long *bitmap1,
const unsigned long *bitmap2, unsigned int bits)
{
diff --git a/lib/cpumask.c b/lib/cpumask.c
index b6513a9f2892..830dd5dec40f 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -5,27 +5,6 @@
#include <linux/export.h>
#include <linux/bootmem.h>
-int __first_cpu(const cpumask_t *srcp)
-{
- return min_t(int, NR_CPUS, find_first_bit(srcp->bits, NR_CPUS));
-}
-EXPORT_SYMBOL(__first_cpu);
-
-int __next_cpu(int n, const cpumask_t *srcp)
-{
- return min_t(int, NR_CPUS, find_next_bit(srcp->bits, NR_CPUS, n+1));
-}
-EXPORT_SYMBOL(__next_cpu);
-
-#if NR_CPUS > 64
-int __next_cpu_nr(int n, const cpumask_t *srcp)
-{
- return min_t(int, nr_cpu_ids,
- find_next_bit(srcp->bits, nr_cpu_ids, n+1));
-}
-EXPORT_SYMBOL(__next_cpu_nr);
-#endif
-
/**
* cpumask_next_and - get the next cpu in *src1p & *src2p
* @n: the cpu prior to the place to search (ie. return will be > @n)
@@ -37,10 +16,11 @@ EXPORT_SYMBOL(__next_cpu_nr);
int cpumask_next_and(int n, const struct cpumask *src1p,
const struct cpumask *src2p)
{
- while ((n = cpumask_next(n, src1p)) < nr_cpu_ids)
- if (cpumask_test_cpu(n, src2p))
- break;
- return n;
+ struct cpumask tmp;
+
+ if (cpumask_and(&tmp, src1p, src2p))
+ return cpumask_next(n, &tmp);
+ return nr_cpu_ids;
}
EXPORT_SYMBOL(cpumask_next_and);
@@ -89,13 +69,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
dump_stack();
}
#endif
- /* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */
- if (*mask) {
- unsigned char *ptr = (unsigned char *)cpumask_bits(*mask);
- unsigned int tail;
- tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long);
- memset(ptr + cpumask_size() - tail, 0, tail);
- }
return *mask != NULL;
}
diff --git a/lib/devres.c b/lib/devres.c
index 0f1dd2e9d2c1..fbe2aac522e6 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -72,6 +72,34 @@ void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset,
EXPORT_SYMBOL(devm_ioremap_nocache);
/**
+ * devm_ioremap_wc - Managed ioremap_wc()
+ * @dev: Generic device to remap IO address for
+ * @offset: BUS offset to map
+ * @size: Size of map
+ *
+ * Managed ioremap_wc(). Map is automatically unmapped on driver detach.
+ */
+void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset,
+ resource_size_t size)
+{
+ void __iomem **ptr, *addr;
+
+ ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL);
+ if (!ptr)
+ return NULL;
+
+ addr = ioremap_wc(offset, size);
+ if (addr) {
+ *ptr = addr;
+ devres_add(dev, ptr);
+ } else
+ devres_free(ptr);
+
+ return addr;
+}
+EXPORT_SYMBOL(devm_ioremap_wc);
+
+/**
* devm_iounmap - Managed iounmap()
* @dev: Generic device to unmap for
* @addr: Address to unmap
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 9722bd2dbc9b..ae4b65e17e64 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -361,7 +361,7 @@ static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
unsigned int range = 0;
while (range <= max_range) {
- entry = __hash_bucket_find(*bucket, &index, containing_match);
+ entry = __hash_bucket_find(*bucket, ref, containing_match);
if (entry)
return entry;
diff --git a/lib/find_bit.c b/lib/find_bit.c
new file mode 100644
index 000000000000..18072ea9c20e
--- /dev/null
+++ b/lib/find_bit.c
@@ -0,0 +1,193 @@
+/* bit search implementation
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * Copyright (C) 2008 IBM Corporation
+ * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au>
+ * (Inspired by David Howell's find_next_bit implementation)
+ *
+ * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
+ * size and improve performance, 2015.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/bitmap.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+
+#if !defined(find_next_bit) || !defined(find_next_zero_bit)
+
+/*
+ * This is a common helper function for find_next_bit and
+ * find_next_zero_bit. The difference is the "invert" argument, which
+ * is XORed with each fetched word before searching it for one bits.
+ */
+static unsigned long _find_next_bit(const unsigned long *addr,
+ unsigned long nbits, unsigned long start, unsigned long invert)
+{
+ unsigned long tmp;
+
+ if (!nbits || start >= nbits)
+ return nbits;
+
+ tmp = addr[start / BITS_PER_LONG] ^ invert;
+
+ /* Handle 1st word. */
+ tmp &= BITMAP_FIRST_WORD_MASK(start);
+ start = round_down(start, BITS_PER_LONG);
+
+ while (!tmp) {
+ start += BITS_PER_LONG;
+ if (start >= nbits)
+ return nbits;
+
+ tmp = addr[start / BITS_PER_LONG] ^ invert;
+ }
+
+ return min(start + __ffs(tmp), nbits);
+}
+#endif
+
+#ifndef find_next_bit
+/*
+ * Find the next set bit in a memory region.
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ return _find_next_bit(addr, size, offset, 0UL);
+}
+EXPORT_SYMBOL(find_next_bit);
+#endif
+
+#ifndef find_next_zero_bit
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ return _find_next_bit(addr, size, offset, ~0UL);
+}
+EXPORT_SYMBOL(find_next_zero_bit);
+#endif
+
+#ifndef find_first_bit
+/*
+ * Find the first set bit in a memory region.
+ */
+unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
+{
+ unsigned long idx;
+
+ for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+ if (addr[idx])
+ return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
+ }
+
+ return size;
+}
+EXPORT_SYMBOL(find_first_bit);
+#endif
+
+#ifndef find_first_zero_bit
+/*
+ * Find the first cleared bit in a memory region.
+ */
+unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
+{
+ unsigned long idx;
+
+ for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
+ if (addr[idx] != ~0UL)
+ return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
+ }
+
+ return size;
+}
+EXPORT_SYMBOL(find_first_zero_bit);
+#endif
+
+#ifndef find_last_bit
+unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
+{
+ if (size) {
+ unsigned long val = BITMAP_LAST_WORD_MASK(size);
+ unsigned long idx = (size-1) / BITS_PER_LONG;
+
+ do {
+ val &= addr[idx];
+ if (val)
+ return idx * BITS_PER_LONG + __fls(val);
+
+ val = ~0ul;
+ } while (idx--);
+ }
+ return size;
+}
+EXPORT_SYMBOL(find_last_bit);
+#endif
+
+#ifdef __BIG_ENDIAN
+
+/* include/linux/byteorder does not support "unsigned long" type */
+static inline unsigned long ext2_swab(const unsigned long y)
+{
+#if BITS_PER_LONG == 64
+ return (unsigned long) __swab64((u64) y);
+#elif BITS_PER_LONG == 32
+ return (unsigned long) __swab32((u32) y);
+#else
+#error BITS_PER_LONG not defined
+#endif
+}
+
+#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
+static unsigned long _find_next_bit_le(const unsigned long *addr,
+ unsigned long nbits, unsigned long start, unsigned long invert)
+{
+ unsigned long tmp;
+
+ if (!nbits || start >= nbits)
+ return nbits;
+
+ tmp = addr[start / BITS_PER_LONG] ^ invert;
+
+ /* Handle 1st word. */
+ tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
+ start = round_down(start, BITS_PER_LONG);
+
+ while (!tmp) {
+ start += BITS_PER_LONG;
+ if (start >= nbits)
+ return nbits;
+
+ tmp = addr[start / BITS_PER_LONG] ^ invert;
+ }
+
+ return min(start + __ffs(ext2_swab(tmp)), nbits);
+}
+#endif
+
+#ifndef find_next_zero_bit_le
+unsigned long find_next_zero_bit_le(const void *addr, unsigned
+ long size, unsigned long offset)
+{
+ return _find_next_bit_le(addr, size, offset, ~0UL);
+}
+EXPORT_SYMBOL(find_next_zero_bit_le);
+#endif
+
+#ifndef find_next_bit_le
+unsigned long find_next_bit_le(const void *addr, unsigned
+ long size, unsigned long offset)
+{
+ return _find_next_bit_le(addr, size, offset, 0UL);
+}
+EXPORT_SYMBOL(find_next_bit_le);
+#endif
+
+#endif /* __BIG_ENDIAN */
diff --git a/lib/find_last_bit.c b/lib/find_last_bit.c
index 91ca09fbf6f9..3e3be40c6a6e 100644
--- a/lib/find_last_bit.c
+++ b/lib/find_last_bit.c
@@ -4,6 +4,9 @@
* Written by Rusty Russell <rusty@rustcorp.com.au>
* (Inspired by David Howell's find_next_bit implementation)
*
+ * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
+ * size and improve performance, 2015.
+ *
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
@@ -11,37 +14,26 @@
*/
#include <linux/bitops.h>
+#include <linux/bitmap.h>
#include <linux/export.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
+#include <linux/kernel.h>
#ifndef find_last_bit
unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
{
- unsigned long words;
- unsigned long tmp;
-
- /* Start at final word. */
- words = size / BITS_PER_LONG;
+ if (size) {
+ unsigned long val = BITMAP_LAST_WORD_MASK(size);
+ unsigned long idx = (size-1) / BITS_PER_LONG;
- /* Partial final word? */
- if (size & (BITS_PER_LONG-1)) {
- tmp = (addr[words] & (~0UL >> (BITS_PER_LONG
- - (size & (BITS_PER_LONG-1)))));
- if (tmp)
- goto found;
- }
+ do {
+ val &= addr[idx];
+ if (val)
+ return idx * BITS_PER_LONG + __fls(val);
- while (words) {
- tmp = addr[--words];
- if (tmp) {
-found:
- return words * BITS_PER_LONG + __fls(tmp);
- }
+ val = ~0ul;
+ } while (idx--);
}
-
- /* Not found */
return size;
}
EXPORT_SYMBOL(find_last_bit);
diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c
deleted file mode 100644
index 0cbfc0b4398f..000000000000
--- a/lib/find_next_bit.c
+++ /dev/null
@@ -1,285 +0,0 @@
-/* find_next_bit.c: fallback find next bit implementation
- *
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/bitops.h>
-#include <linux/export.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
-
-#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)
-
-#ifndef find_next_bit
-/*
- * Find the next set bit in a memory region.
- */
-unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
- unsigned long offset)
-{
- const unsigned long *p = addr + BITOP_WORD(offset);
- unsigned long result = offset & ~(BITS_PER_LONG-1);
- unsigned long tmp;
-
- if (offset >= size)
- return size;
- size -= result;
- offset %= BITS_PER_LONG;
- if (offset) {
- tmp = *(p++);
- tmp &= (~0UL << offset);
- if (size < BITS_PER_LONG)
- goto found_first;
- if (tmp)
- goto found_middle;
- size -= BITS_PER_LONG;
- result += BITS_PER_LONG;
- }
- while (size & ~(BITS_PER_LONG-1)) {
- if ((tmp = *(p++)))
- goto found_middle;
- result += BITS_PER_LONG;
- size -= BITS_PER_LONG;
- }
- if (!size)
- return result;
- tmp = *p;
-
-found_first:
- tmp &= (~0UL >> (BITS_PER_LONG - size));
- if (tmp == 0UL) /* Are any bits set? */
- return result + size; /* Nope. */
-found_middle:
- return result + __ffs(tmp);
-}
-EXPORT_SYMBOL(find_next_bit);
-#endif
-
-#ifndef find_next_zero_bit
-/*
- * This implementation of find_{first,next}_zero_bit was stolen from
- * Linus' asm-alpha/bitops.h.
- */
-unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
- unsigned long offset)
-{
- const unsigned long *p = addr + BITOP_WORD(offset);
- unsigned long result = offset & ~(BITS_PER_LONG-1);
- unsigned long tmp;
-
- if (offset >= size)
- return size;
- size -= result;
- offset %= BITS_PER_LONG;
- if (offset) {
- tmp = *(p++);
- tmp |= ~0UL >> (BITS_PER_LONG - offset);
- if (size < BITS_PER_LONG)
- goto found_first;
- if (~tmp)
- goto found_middle;
- size -= BITS_PER_LONG;
- result += BITS_PER_LONG;
- }
- while (size & ~(BITS_PER_LONG-1)) {
- if (~(tmp = *(p++)))
- goto found_middle;
- result += BITS_PER_LONG;
- size -= BITS_PER_LONG;
- }
- if (!size)
- return result;
- tmp = *p;
-
-found_first:
- tmp |= ~0UL << size;
- if (tmp == ~0UL) /* Are any bits zero? */
- return result + size; /* Nope. */
-found_middle:
- return result + ffz(tmp);
-}
-EXPORT_SYMBOL(find_next_zero_bit);
-#endif
-
-#ifndef find_first_bit
-/*
- * Find the first set bit in a memory region.
- */
-unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
-{
- const unsigned long *p = addr;
- unsigned long result = 0;
- unsigned long tmp;
-
- while (size & ~(BITS_PER_LONG-1)) {
- if ((tmp = *(p++)))
- goto found;
- result += BITS_PER_LONG;
- size -= BITS_PER_LONG;
- }
- if (!size)
- return result;
-
- tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
- if (tmp == 0UL) /* Are any bits set? */
- return result + size; /* Nope. */
-found:
- return result + __ffs(tmp);
-}
-EXPORT_SYMBOL(find_first_bit);
-#endif
-
-#ifndef find_first_zero_bit
-/*
- * Find the first cleared bit in a memory region.
- */
-unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
-{
- const unsigned long *p = addr;
- unsigned long result = 0;
- unsigned long tmp;
-
- while (size & ~(BITS_PER_LONG-1)) {
- if (~(tmp = *(p++)))
- goto found;
- result += BITS_PER_LONG;
- size -= BITS_PER_LONG;
- }
- if (!size)
- return result;
-
- tmp = (*p) | (~0UL << size);
- if (tmp == ~0UL) /* Are any bits zero? */
- return result + size; /* Nope. */
-found:
- return result + ffz(tmp);
-}
-EXPORT_SYMBOL(find_first_zero_bit);
-#endif
-
-#ifdef __BIG_ENDIAN
-
-/* include/linux/byteorder does not support "unsigned long" type */
-static inline unsigned long ext2_swabp(const unsigned long * x)
-{
-#if BITS_PER_LONG == 64
- return (unsigned long) __swab64p((u64 *) x);
-#elif BITS_PER_LONG == 32
- return (unsigned long) __swab32p((u32 *) x);
-#else
-#error BITS_PER_LONG not defined
-#endif
-}
-
-/* include/linux/byteorder doesn't support "unsigned long" type */
-static inline unsigned long ext2_swab(const unsigned long y)
-{
-#if BITS_PER_LONG == 64
- return (unsigned long) __swab64((u64) y);
-#elif BITS_PER_LONG == 32
- return (unsigned long) __swab32((u32) y);
-#else
-#error BITS_PER_LONG not defined
-#endif
-}
-
-#ifndef find_next_zero_bit_le
-unsigned long find_next_zero_bit_le(const void *addr, unsigned
- long size, unsigned long offset)
-{
- const unsigned long *p = addr;
- unsigned long result = offset & ~(BITS_PER_LONG - 1);
- unsigned long tmp;
-
- if (offset >= size)
- return size;
- p += BITOP_WORD(offset);
- size -= result;
- offset &= (BITS_PER_LONG - 1UL);
- if (offset) {
- tmp = ext2_swabp(p++);
- tmp |= (~0UL >> (BITS_PER_LONG - offset));
- if (size < BITS_PER_LONG)
- goto found_first;
- if (~tmp)
- goto found_middle;
- size -= BITS_PER_LONG;
- result += BITS_PER_LONG;
- }
-
- while (size & ~(BITS_PER_LONG - 1)) {
- if (~(tmp = *(p++)))
- goto found_middle_swap;
- result += BITS_PER_LONG;
- size -= BITS_PER_LONG;
- }
- if (!size)
- return result;
- tmp = ext2_swabp(p);
-found_first:
- tmp |= ~0UL << size;
- if (tmp == ~0UL) /* Are any bits zero? */
- return result + size; /* Nope. Skip ffz */
-found_middle:
- return result + ffz(tmp);
-
-found_middle_swap:
- return result + ffz(ext2_swab(tmp));
-}
-EXPORT_SYMBOL(find_next_zero_bit_le);
-#endif
-
-#ifndef find_next_bit_le
-unsigned long find_next_bit_le(const void *addr, unsigned
- long size, unsigned long offset)
-{
- const unsigned long *p = addr;
- unsigned long result = offset & ~(BITS_PER_LONG - 1);
- unsigned long tmp;
-
- if (offset >= size)
- return size;
- p += BITOP_WORD(offset);
- size -= result;
- offset &= (BITS_PER_LONG - 1UL);
- if (offset) {
- tmp = ext2_swabp(p++);
- tmp &= (~0UL << offset);
- if (size < BITS_PER_LONG)
- goto found_first;
- if (tmp)
- goto found_middle;
- size -= BITS_PER_LONG;
- result += BITS_PER_LONG;
- }
-
- while (size & ~(BITS_PER_LONG - 1)) {
- tmp = *(p++);
- if (tmp)
- goto found_middle_swap;
- result += BITS_PER_LONG;
- size -= BITS_PER_LONG;
- }
- if (!size)
- return result;
- tmp = ext2_swabp(p);
-found_first:
- tmp &= (~0UL >> (BITS_PER_LONG - size));
- if (tmp == 0UL) /* Are any bits set? */
- return result + size; /* Nope. */
-found_middle:
- return result + __ffs(tmp);
-
-found_middle_swap:
- return result + __ffs(ext2_swab(tmp));
-}
-EXPORT_SYMBOL(find_next_bit_le);
-#endif
-
-#endif /* __BIG_ENDIAN */
diff --git a/lib/iommu-common.c b/lib/iommu-common.c
new file mode 100644
index 000000000000..df30632f0bef
--- /dev/null
+++ b/lib/iommu-common.c
@@ -0,0 +1,270 @@
+/*
+ * IOMMU mmap management and range allocation functions.
+ * Based almost entirely upon the powerpc iommu allocator.
+ */
+
+#include <linux/export.h>
+#include <linux/bitmap.h>
+#include <linux/bug.h>
+#include <linux/iommu-helper.h>
+#include <linux/iommu-common.h>
+#include <linux/dma-mapping.h>
+#include <linux/hash.h>
+
+#ifndef DMA_ERROR_CODE
+#define DMA_ERROR_CODE (~(dma_addr_t)0x0)
+#endif
+
+static unsigned long iommu_large_alloc = 15;
+
+static DEFINE_PER_CPU(unsigned int, iommu_hash_common);
+
+static inline bool need_flush(struct iommu_map_table *iommu)
+{
+ return (iommu->lazy_flush != NULL &&
+ (iommu->flags & IOMMU_NEED_FLUSH) != 0);
+}
+
+static inline void set_flush(struct iommu_map_table *iommu)
+{
+ iommu->flags |= IOMMU_NEED_FLUSH;
+}
+
+static inline void clear_flush(struct iommu_map_table *iommu)
+{
+ iommu->flags &= ~IOMMU_NEED_FLUSH;
+}
+
+static void setup_iommu_pool_hash(void)
+{
+ unsigned int i;
+ static bool do_once;
+
+ if (do_once)
+ return;
+ do_once = true;
+ for_each_possible_cpu(i)
+ per_cpu(iommu_hash_common, i) = hash_32(i, IOMMU_POOL_HASHBITS);
+}
+
+/*
+ * Initialize iommu_pool entries for the iommu_map_table. `num_entries'
+ * is the number of table entries. If `large_pool' is set to true,
+ * the top 1/4 of the table will be set aside for pool allocations
+ * of more than iommu_large_alloc pages.
+ */
+void iommu_tbl_pool_init(struct iommu_map_table *iommu,
+ unsigned long num_entries,
+ u32 table_shift,
+ void (*lazy_flush)(struct iommu_map_table *),
+ bool large_pool, u32 npools,
+ bool skip_span_boundary_check)
+{
+ unsigned int start, i;
+ struct iommu_pool *p = &(iommu->large_pool);
+
+ setup_iommu_pool_hash();
+ if (npools == 0)
+ iommu->nr_pools = IOMMU_NR_POOLS;
+ else
+ iommu->nr_pools = npools;
+ BUG_ON(npools > IOMMU_NR_POOLS);
+
+ iommu->table_shift = table_shift;
+ iommu->lazy_flush = lazy_flush;
+ start = 0;
+ if (skip_span_boundary_check)
+ iommu->flags |= IOMMU_NO_SPAN_BOUND;
+ if (large_pool)
+ iommu->flags |= IOMMU_HAS_LARGE_POOL;
+
+ if (!large_pool)
+ iommu->poolsize = num_entries/iommu->nr_pools;
+ else
+ iommu->poolsize = (num_entries * 3 / 4)/iommu->nr_pools;
+ for (i = 0; i < iommu->nr_pools; i++) {
+ spin_lock_init(&(iommu->pools[i].lock));
+ iommu->pools[i].start = start;
+ iommu->pools[i].hint = start;
+ start += iommu->poolsize; /* start for next pool */
+ iommu->pools[i].end = start - 1;
+ }
+ if (!large_pool)
+ return;
+ /* initialize large_pool */
+ spin_lock_init(&(p->lock));
+ p->start = start;
+ p->hint = p->start;
+ p->end = num_entries;
+}
+EXPORT_SYMBOL(iommu_tbl_pool_init);
+
+unsigned long iommu_tbl_range_alloc(struct device *dev,
+ struct iommu_map_table *iommu,
+ unsigned long npages,
+ unsigned long *handle,
+ unsigned long mask,
+ unsigned int align_order)
+{
+ unsigned int pool_hash = __this_cpu_read(iommu_hash_common);
+ unsigned long n, end, start, limit, boundary_size;
+ struct iommu_pool *pool;
+ int pass = 0;
+ unsigned int pool_nr;
+ unsigned int npools = iommu->nr_pools;
+ unsigned long flags;
+ bool large_pool = ((iommu->flags & IOMMU_HAS_LARGE_POOL) != 0);
+ bool largealloc = (large_pool && npages > iommu_large_alloc);
+ unsigned long shift;
+ unsigned long align_mask = 0;
+
+ if (align_order > 0)
+ align_mask = 0xffffffffffffffffl >> (64 - align_order);
+
+ /* Sanity check */
+ if (unlikely(npages == 0)) {
+ WARN_ON_ONCE(1);
+ return DMA_ERROR_CODE;
+ }
+
+ if (largealloc) {
+ pool = &(iommu->large_pool);
+ pool_nr = 0; /* to keep compiler happy */
+ } else {
+ /* pick out pool_nr */
+ pool_nr = pool_hash & (npools - 1);
+ pool = &(iommu->pools[pool_nr]);
+ }
+ spin_lock_irqsave(&pool->lock, flags);
+
+ again:
+ if (pass == 0 && handle && *handle &&
+ (*handle >= pool->start) && (*handle < pool->end))
+ start = *handle;
+ else
+ start = pool->hint;
+
+ limit = pool->end;
+
+ /* The case below can happen if we have a small segment appended
+ * to a large, or when the previous alloc was at the very end of
+ * the available space. If so, go back to the beginning. If a
+ * flush is needed, it will get done based on the return value
+ * from iommu_area_alloc() below.
+ */
+ if (start >= limit)
+ start = pool->start;
+ shift = iommu->table_map_base >> iommu->table_shift;
+ if (limit + shift > mask) {
+ limit = mask - shift + 1;
+ /* If we're constrained on address range, first try
+ * at the masked hint to avoid O(n) search complexity,
+ * but on second pass, start at 0 in pool 0.
+ */
+ if ((start & mask) >= limit || pass > 0) {
+ spin_unlock(&(pool->lock));
+ pool = &(iommu->pools[0]);
+ spin_lock(&(pool->lock));
+ start = pool->start;
+ } else {
+ start &= mask;
+ }
+ }
+
+ if (dev)
+ boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
+ 1 << iommu->table_shift);
+ else
+ boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift);
+
+ boundary_size = boundary_size >> iommu->table_shift;
+ /*
+ * if the skip_span_boundary_check had been set during init, we set
+ * things up so that iommu_is_span_boundary() merely checks if the
+ * (index + npages) < num_tsb_entries
+ */
+ if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) {
+ shift = 0;
+ boundary_size = iommu->poolsize * iommu->nr_pools;
+ }
+ n = iommu_area_alloc(iommu->map, limit, start, npages, shift,
+ boundary_size, align_mask);
+ if (n == -1) {
+ if (likely(pass == 0)) {
+ /* First failure, rescan from the beginning. */
+ pool->hint = pool->start;
+ set_flush(iommu);
+ pass++;
+ goto again;
+ } else if (!largealloc && pass <= iommu->nr_pools) {
+ spin_unlock(&(pool->lock));
+ pool_nr = (pool_nr + 1) & (iommu->nr_pools - 1);
+ pool = &(iommu->pools[pool_nr]);
+ spin_lock(&(pool->lock));
+ pool->hint = pool->start;
+ set_flush(iommu);
+ pass++;
+ goto again;
+ } else {
+ /* give up */
+ n = DMA_ERROR_CODE;
+ goto bail;
+ }
+ }
+ if (n < pool->hint || need_flush(iommu)) {
+ clear_flush(iommu);
+ iommu->lazy_flush(iommu);
+ }
+
+ end = n + npages;
+ pool->hint = end;
+
+ /* Update handle for SG allocations */
+ if (handle)
+ *handle = end;
+bail:
+ spin_unlock_irqrestore(&(pool->lock), flags);
+
+ return n;
+}
+EXPORT_SYMBOL(iommu_tbl_range_alloc);
+
+static struct iommu_pool *get_pool(struct iommu_map_table *tbl,
+ unsigned long entry)
+{
+ struct iommu_pool *p;
+ unsigned long largepool_start = tbl->large_pool.start;
+ bool large_pool = ((tbl->flags & IOMMU_HAS_LARGE_POOL) != 0);
+
+ /* The large pool is the last pool at the top of the table */
+ if (large_pool && entry >= largepool_start) {
+ p = &tbl->large_pool;
+ } else {
+ unsigned int pool_nr = entry / tbl->poolsize;
+
+ BUG_ON(pool_nr >= tbl->nr_pools);
+ p = &tbl->pools[pool_nr];
+ }
+ return p;
+}
+
+/* Caller supplies the index of the entry into the iommu map table
+ * itself when the mapping from dma_addr to the entry is not the
+ * default addr->entry mapping below.
+ */
+void iommu_tbl_range_free(struct iommu_map_table *iommu, u64 dma_addr,
+ unsigned long npages, unsigned long entry)
+{
+ struct iommu_pool *pool;
+ unsigned long flags;
+ unsigned long shift = iommu->table_shift;
+
+ if (entry == DMA_ERROR_CODE) /* use default addr->entry mapping */
+ entry = (dma_addr - iommu->table_map_base) >> shift;
+ pool = get_pool(iommu, entry);
+
+ spin_lock_irqsave(&(pool->lock), flags);
+ bitmap_clear(iommu->map, entry, npages);
+ spin_unlock_irqrestore(&(pool->lock), flags);
+}
+EXPORT_SYMBOL(iommu_tbl_range_free);
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index dbef2314901e..975c6e0434bd 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -131,11 +131,12 @@ static inline const struct raid6_recov_calls *raid6_choose_recov(void)
static inline const struct raid6_calls *raid6_choose_gen(
void *(*const dptrs)[(65536/PAGE_SIZE)+2], const int disks)
{
- unsigned long perf, bestperf, j0, j1;
+ unsigned long perf, bestgenperf, bestxorperf, j0, j1;
+ int start = (disks>>1)-1, stop = disks-3; /* work on the second half of the disks */
const struct raid6_calls *const *algo;
const struct raid6_calls *best;
- for (bestperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
+ for (bestgenperf = 0, bestxorperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
if (!best || (*algo)->prefer >= best->prefer) {
if ((*algo)->valid && !(*algo)->valid())
continue;
@@ -153,19 +154,45 @@ static inline const struct raid6_calls *raid6_choose_gen(
}
preempt_enable();
- if (perf > bestperf) {
- bestperf = perf;
+ if (perf > bestgenperf) {
+ bestgenperf = perf;
best = *algo;
}
- pr_info("raid6: %-8s %5ld MB/s\n", (*algo)->name,
+ pr_info("raid6: %-8s gen() %5ld MB/s\n", (*algo)->name,
(perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
+
+ if (!(*algo)->xor_syndrome)
+ continue;
+
+ perf = 0;
+
+ preempt_disable();
+ j0 = jiffies;
+ while ((j1 = jiffies) == j0)
+ cpu_relax();
+ while (time_before(jiffies,
+ j1 + (1<<RAID6_TIME_JIFFIES_LG2))) {
+ (*algo)->xor_syndrome(disks, start, stop,
+ PAGE_SIZE, *dptrs);
+ perf++;
+ }
+ preempt_enable();
+
+ if (best == *algo)
+ bestxorperf = perf;
+
+ pr_info("raid6: %-8s xor() %5ld MB/s\n", (*algo)->name,
+ (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2+1));
}
}
if (best) {
- pr_info("raid6: using algorithm %s (%ld MB/s)\n",
+ pr_info("raid6: using algorithm %s gen() %ld MB/s\n",
best->name,
- (bestperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
+ (bestgenperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
+ if (best->xor_syndrome)
+ pr_info("raid6: .... xor() %ld MB/s, rmw enabled\n",
+ (bestxorperf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2+1));
raid6_call = *best;
} else
pr_err("raid6: Yikes! No algorithm found!\n");
diff --git a/lib/raid6/altivec.uc b/lib/raid6/altivec.uc
index 7cc12b532e95..bec27fce7501 100644
--- a/lib/raid6/altivec.uc
+++ b/lib/raid6/altivec.uc
@@ -119,6 +119,7 @@ int raid6_have_altivec(void)
const struct raid6_calls raid6_altivec$# = {
raid6_altivec$#_gen_syndrome,
+ NULL, /* XOR not yet implemented */
raid6_have_altivec,
"altivecx$#",
0
diff --git a/lib/raid6/avx2.c b/lib/raid6/avx2.c
index bc3b1dd436eb..76734004358d 100644
--- a/lib/raid6/avx2.c
+++ b/lib/raid6/avx2.c
@@ -89,6 +89,7 @@ static void raid6_avx21_gen_syndrome(int disks, size_t bytes, void **ptrs)
const struct raid6_calls raid6_avx2x1 = {
raid6_avx21_gen_syndrome,
+ NULL, /* XOR not yet implemented */
raid6_have_avx2,
"avx2x1",
1 /* Has cache hints */
@@ -150,6 +151,7 @@ static void raid6_avx22_gen_syndrome(int disks, size_t bytes, void **ptrs)
const struct raid6_calls raid6_avx2x2 = {
raid6_avx22_gen_syndrome,
+ NULL, /* XOR not yet implemented */
raid6_have_avx2,
"avx2x2",
1 /* Has cache hints */
@@ -242,6 +244,7 @@ static void raid6_avx24_gen_syndrome(int disks, size_t bytes, void **ptrs)
const struct raid6_calls raid6_avx2x4 = {
raid6_avx24_gen_syndrome,
+ NULL, /* XOR not yet implemented */
raid6_have_avx2,
"avx2x4",
1 /* Has cache hints */
diff --git a/lib/raid6/int.uc b/lib/raid6/int.uc
index 5b50f8dfc5d2..558aeac9342a 100644
--- a/lib/raid6/int.uc
+++ b/lib/raid6/int.uc
@@ -107,9 +107,48 @@ static void raid6_int$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
}
}
+static void raid6_int$#_xor_syndrome(int disks, int start, int stop,
+ size_t bytes, void **ptrs)
+{
+ u8 **dptr = (u8 **)ptrs;
+ u8 *p, *q;
+ int d, z, z0;
+
+ unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
+
+ z0 = stop; /* P/Q right side optimization */
+ p = dptr[disks-2]; /* XOR parity */
+ q = dptr[disks-1]; /* RS syndrome */
+
+ for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
+ /* P/Q data pages */
+ wq$$ = wp$$ = *(unative_t *)&dptr[z0][d+$$*NSIZE];
+ for ( z = z0-1 ; z >= start ; z-- ) {
+ wd$$ = *(unative_t *)&dptr[z][d+$$*NSIZE];
+ wp$$ ^= wd$$;
+ w2$$ = MASK(wq$$);
+ w1$$ = SHLBYTE(wq$$);
+ w2$$ &= NBYTES(0x1d);
+ w1$$ ^= w2$$;
+ wq$$ = w1$$ ^ wd$$;
+ }
+ /* P/Q left side optimization */
+ for ( z = start-1 ; z >= 0 ; z-- ) {
+ w2$$ = MASK(wq$$);
+ w1$$ = SHLBYTE(wq$$);
+ w2$$ &= NBYTES(0x1d);
+ wq$$ = w1$$ ^ w2$$;
+ }
+ *(unative_t *)&p[d+NSIZE*$$] ^= wp$$;
+ *(unative_t *)&q[d+NSIZE*$$] ^= wq$$;
+ }
+
+}
+
const struct raid6_calls raid6_intx$# = {
raid6_int$#_gen_syndrome,
- NULL, /* always valid */
+ raid6_int$#_xor_syndrome,
+ NULL, /* always valid */
"int" NSTRING "x$#",
0
};
diff --git a/lib/raid6/mmx.c b/lib/raid6/mmx.c
index 590c71c9e200..b3b0e1fcd3af 100644
--- a/lib/raid6/mmx.c
+++ b/lib/raid6/mmx.c
@@ -76,6 +76,7 @@ static void raid6_mmx1_gen_syndrome(int disks, size_t bytes, void **ptrs)
const struct raid6_calls raid6_mmxx1 = {
raid6_mmx1_gen_syndrome,
+ NULL, /* XOR not yet implemented */
raid6_have_mmx,
"mmxx1",
0
@@ -134,6 +135,7 @@ static void raid6_mmx2_gen_syndrome(int disks, size_t bytes, void **ptrs)
const struct raid6_calls raid6_mmxx2 = {
raid6_mmx2_gen_syndrome,
+ NULL, /* XOR not yet implemented */
raid6_have_mmx,
"mmxx2",
0
diff --git a/lib/raid6/neon.c b/lib/raid6/neon.c
index 36ad4705df1a..d9ad6ee284f4 100644
--- a/lib/raid6/neon.c
+++ b/lib/raid6/neon.c
@@ -42,6 +42,7 @@
} \
struct raid6_calls const raid6_neonx ## _n = { \
raid6_neon ## _n ## _gen_syndrome, \
+ NULL, /* XOR not yet implemented */ \
raid6_have_neon, \
"neonx" #_n, \
0 \
diff --git a/lib/raid6/sse1.c b/lib/raid6/sse1.c
index f76297139445..9025b8ca9aa3 100644
--- a/lib/raid6/sse1.c
+++ b/lib/raid6/sse1.c
@@ -92,6 +92,7 @@ static void raid6_sse11_gen_syndrome(int disks, size_t bytes, void **ptrs)
const struct raid6_calls raid6_sse1x1 = {
raid6_sse11_gen_syndrome,
+ NULL, /* XOR not yet implemented */
raid6_have_sse1_or_mmxext,
"sse1x1",
1 /* Has cache hints */
@@ -154,6 +155,7 @@ static void raid6_sse12_gen_syndrome(int disks, size_t bytes, void **ptrs)
const struct raid6_calls raid6_sse1x2 = {
raid6_sse12_gen_syndrome,
+ NULL, /* XOR not yet implemented */
raid6_have_sse1_or_mmxext,
"sse1x2",
1 /* Has cache hints */
diff --git a/lib/raid6/sse2.c b/lib/raid6/sse2.c
index 85b82c85f28e..1d2276b007ee 100644
--- a/lib/raid6/sse2.c
+++ b/lib/raid6/sse2.c
@@ -88,8 +88,58 @@ static void raid6_sse21_gen_syndrome(int disks, size_t bytes, void **ptrs)
kernel_fpu_end();
}
+
+static void raid6_sse21_xor_syndrome(int disks, int start, int stop,
+ size_t bytes, void **ptrs)
+ {
+ u8 **dptr = (u8 **)ptrs;
+ u8 *p, *q;
+ int d, z, z0;
+
+ z0 = stop; /* P/Q right side optimization */
+ p = dptr[disks-2]; /* XOR parity */
+ q = dptr[disks-1]; /* RS syndrome */
+
+ kernel_fpu_begin();
+
+ asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0]));
+
+ for ( d = 0 ; d < bytes ; d += 16 ) {
+ asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d]));
+ asm volatile("movdqa %0,%%xmm2" : : "m" (p[d]));
+ asm volatile("pxor %xmm4,%xmm2");
+ /* P/Q data pages */
+ for ( z = z0-1 ; z >= start ; z-- ) {
+ asm volatile("pxor %xmm5,%xmm5");
+ asm volatile("pcmpgtb %xmm4,%xmm5");
+ asm volatile("paddb %xmm4,%xmm4");
+ asm volatile("pand %xmm0,%xmm5");
+ asm volatile("pxor %xmm5,%xmm4");
+ asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d]));
+ asm volatile("pxor %xmm5,%xmm2");
+ asm volatile("pxor %xmm5,%xmm4");
+ }
+ /* P/Q left side optimization */
+ for ( z = start-1 ; z >= 0 ; z-- ) {
+ asm volatile("pxor %xmm5,%xmm5");
+ asm volatile("pcmpgtb %xmm4,%xmm5");
+ asm volatile("paddb %xmm4,%xmm4");
+ asm volatile("pand %xmm0,%xmm5");
+ asm volatile("pxor %xmm5,%xmm4");
+ }
+ asm volatile("pxor %0,%%xmm4" : : "m" (q[d]));
+ /* Don't use movntdq for r/w memory area < cache line */
+ asm volatile("movdqa %%xmm4,%0" : "=m" (q[d]));
+ asm volatile("movdqa %%xmm2,%0" : "=m" (p[d]));
+ }
+
+ asm volatile("sfence" : : : "memory");
+ kernel_fpu_end();
+}
+
const struct raid6_calls raid6_sse2x1 = {
raid6_sse21_gen_syndrome,
+ raid6_sse21_xor_syndrome,
raid6_have_sse2,
"sse2x1",
1 /* Has cache hints */
@@ -150,8 +200,76 @@ static void raid6_sse22_gen_syndrome(int disks, size_t bytes, void **ptrs)
kernel_fpu_end();
}
+ static void raid6_sse22_xor_syndrome(int disks, int start, int stop,
+ size_t bytes, void **ptrs)
+ {
+ u8 **dptr = (u8 **)ptrs;
+ u8 *p, *q;
+ int d, z, z0;
+
+ z0 = stop; /* P/Q right side optimization */
+ p = dptr[disks-2]; /* XOR parity */
+ q = dptr[disks-1]; /* RS syndrome */
+
+ kernel_fpu_begin();
+
+ asm volatile("movdqa %0,%%xmm0" : : "m" (raid6_sse_constants.x1d[0]));
+
+ for ( d = 0 ; d < bytes ; d += 32 ) {
+ asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d]));
+ asm volatile("movdqa %0,%%xmm6" :: "m" (dptr[z0][d+16]));
+ asm volatile("movdqa %0,%%xmm2" : : "m" (p[d]));
+ asm volatile("movdqa %0,%%xmm3" : : "m" (p[d+16]));
+ asm volatile("pxor %xmm4,%xmm2");
+ asm volatile("pxor %xmm6,%xmm3");
+ /* P/Q data pages */
+ for ( z = z0-1 ; z >= start ; z-- ) {
+ asm volatile("pxor %xmm5,%xmm5");
+ asm volatile("pxor %xmm7,%xmm7");
+ asm volatile("pcmpgtb %xmm4,%xmm5");
+ asm volatile("pcmpgtb %xmm6,%xmm7");
+ asm volatile("paddb %xmm4,%xmm4");
+ asm volatile("paddb %xmm6,%xmm6");
+ asm volatile("pand %xmm0,%xmm5");
+ asm volatile("pand %xmm0,%xmm7");
+ asm volatile("pxor %xmm5,%xmm4");
+ asm volatile("pxor %xmm7,%xmm6");
+ asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d]));
+ asm volatile("movdqa %0,%%xmm7" :: "m" (dptr[z][d+16]));
+ asm volatile("pxor %xmm5,%xmm2");
+ asm volatile("pxor %xmm7,%xmm3");
+ asm volatile("pxor %xmm5,%xmm4");
+ asm volatile("pxor %xmm7,%xmm6");
+ }
+ /* P/Q left side optimization */
+ for ( z = start-1 ; z >= 0 ; z-- ) {
+ asm volatile("pxor %xmm5,%xmm5");
+ asm volatile("pxor %xmm7,%xmm7");
+ asm volatile("pcmpgtb %xmm4,%xmm5");
+ asm volatile("pcmpgtb %xmm6,%xmm7");
+ asm volatile("paddb %xmm4,%xmm4");
+ asm volatile("paddb %xmm6,%xmm6");
+ asm volatile("pand %xmm0,%xmm5");
+ asm volatile("pand %xmm0,%xmm7");
+ asm volatile("pxor %xmm5,%xmm4");
+ asm volatile("pxor %xmm7,%xmm6");
+ }
+ asm volatile("pxor %0,%%xmm4" : : "m" (q[d]));
+ asm volatile("pxor %0,%%xmm6" : : "m" (q[d+16]));
+ /* Don't use movntdq for r/w memory area < cache line */
+ asm volatile("movdqa %%xmm4,%0" : "=m" (q[d]));
+ asm volatile("movdqa %%xmm6,%0" : "=m" (q[d+16]));
+ asm volatile("movdqa %%xmm2,%0" : "=m" (p[d]));
+ asm volatile("movdqa %%xmm3,%0" : "=m" (p[d+16]));
+ }
+
+ asm volatile("sfence" : : : "memory");
+ kernel_fpu_end();
+ }
+
const struct raid6_calls raid6_sse2x2 = {
raid6_sse22_gen_syndrome,
+ raid6_sse22_xor_syndrome,
raid6_have_sse2,
"sse2x2",
1 /* Has cache hints */
@@ -248,8 +366,117 @@ static void raid6_sse24_gen_syndrome(int disks, size_t bytes, void **ptrs)
kernel_fpu_end();
}
+ static void raid6_sse24_xor_syndrome(int disks, int start, int stop,
+ size_t bytes, void **ptrs)
+ {
+ u8 **dptr = (u8 **)ptrs;
+ u8 *p, *q;
+ int d, z, z0;
+
+ z0 = stop; /* P/Q right side optimization */
+ p = dptr[disks-2]; /* XOR parity */
+ q = dptr[disks-1]; /* RS syndrome */
+
+ kernel_fpu_begin();
+
+ asm volatile("movdqa %0,%%xmm0" :: "m" (raid6_sse_constants.x1d[0]));
+
+ for ( d = 0 ; d < bytes ; d += 64 ) {
+ asm volatile("movdqa %0,%%xmm4" :: "m" (dptr[z0][d]));
+ asm volatile("movdqa %0,%%xmm6" :: "m" (dptr[z0][d+16]));
+ asm volatile("movdqa %0,%%xmm12" :: "m" (dptr[z0][d+32]));
+ asm volatile("movdqa %0,%%xmm14" :: "m" (dptr[z0][d+48]));
+ asm volatile("movdqa %0,%%xmm2" : : "m" (p[d]));
+ asm volatile("movdqa %0,%%xmm3" : : "m" (p[d+16]));
+ asm volatile("movdqa %0,%%xmm10" : : "m" (p[d+32]));
+ asm volatile("movdqa %0,%%xmm11" : : "m" (p[d+48]));
+ asm volatile("pxor %xmm4,%xmm2");
+ asm volatile("pxor %xmm6,%xmm3");
+ asm volatile("pxor %xmm12,%xmm10");
+ asm volatile("pxor %xmm14,%xmm11");
+ /* P/Q data pages */
+ for ( z = z0-1 ; z >= start ; z-- ) {
+ asm volatile("prefetchnta %0" :: "m" (dptr[z][d]));
+ asm volatile("prefetchnta %0" :: "m" (dptr[z][d+32]));
+ asm volatile("pxor %xmm5,%xmm5");
+ asm volatile("pxor %xmm7,%xmm7");
+ asm volatile("pxor %xmm13,%xmm13");
+ asm volatile("pxor %xmm15,%xmm15");
+ asm volatile("pcmpgtb %xmm4,%xmm5");
+ asm volatile("pcmpgtb %xmm6,%xmm7");
+ asm volatile("pcmpgtb %xmm12,%xmm13");
+ asm volatile("pcmpgtb %xmm14,%xmm15");
+ asm volatile("paddb %xmm4,%xmm4");
+ asm volatile("paddb %xmm6,%xmm6");
+ asm volatile("paddb %xmm12,%xmm12");
+ asm volatile("paddb %xmm14,%xmm14");
+ asm volatile("pand %xmm0,%xmm5");
+ asm volatile("pand %xmm0,%xmm7");
+ asm volatile("pand %xmm0,%xmm13");
+ asm volatile("pand %xmm0,%xmm15");
+ asm volatile("pxor %xmm5,%xmm4");
+ asm volatile("pxor %xmm7,%xmm6");
+ asm volatile("pxor %xmm13,%xmm12");
+ asm volatile("pxor %xmm15,%xmm14");
+ asm volatile("movdqa %0,%%xmm5" :: "m" (dptr[z][d]));
+ asm volatile("movdqa %0,%%xmm7" :: "m" (dptr[z][d+16]));
+ asm volatile("movdqa %0,%%xmm13" :: "m" (dptr[z][d+32]));
+ asm volatile("movdqa %0,%%xmm15" :: "m" (dptr[z][d+48]));
+ asm volatile("pxor %xmm5,%xmm2");
+ asm volatile("pxor %xmm7,%xmm3");
+ asm volatile("pxor %xmm13,%xmm10");
+ asm volatile("pxor %xmm15,%xmm11");
+ asm volatile("pxor %xmm5,%xmm4");
+ asm volatile("pxor %xmm7,%xmm6");
+ asm volatile("pxor %xmm13,%xmm12");
+ asm volatile("pxor %xmm15,%xmm14");
+ }
+ asm volatile("prefetchnta %0" :: "m" (q[d]));
+ asm volatile("prefetchnta %0" :: "m" (q[d+32]));
+ /* P/Q left side optimization */
+ for ( z = start-1 ; z >= 0 ; z-- ) {
+ asm volatile("pxor %xmm5,%xmm5");
+ asm volatile("pxor %xmm7,%xmm7");
+ asm volatile("pxor %xmm13,%xmm13");
+ asm volatile("pxor %xmm15,%xmm15");
+ asm volatile("pcmpgtb %xmm4,%xmm5");
+ asm volatile("pcmpgtb %xmm6,%xmm7");
+ asm volatile("pcmpgtb %xmm12,%xmm13");
+ asm volatile("pcmpgtb %xmm14,%xmm15");
+ asm volatile("paddb %xmm4,%xmm4");
+ asm volatile("paddb %xmm6,%xmm6");
+ asm volatile("paddb %xmm12,%xmm12");
+ asm volatile("paddb %xmm14,%xmm14");
+ asm volatile("pand %xmm0,%xmm5");
+ asm volatile("pand %xmm0,%xmm7");
+ asm volatile("pand %xmm0,%xmm13");
+ asm volatile("pand %xmm0,%xmm15");
+ asm volatile("pxor %xmm5,%xmm4");
+ asm volatile("pxor %xmm7,%xmm6");
+ asm volatile("pxor %xmm13,%xmm12");
+ asm volatile("pxor %xmm15,%xmm14");
+ }
+ asm volatile("movntdq %%xmm2,%0" : "=m" (p[d]));
+ asm volatile("movntdq %%xmm3,%0" : "=m" (p[d+16]));
+ asm volatile("movntdq %%xmm10,%0" : "=m" (p[d+32]));
+ asm volatile("movntdq %%xmm11,%0" : "=m" (p[d+48]));
+ asm volatile("pxor %0,%%xmm4" : : "m" (q[d]));
+ asm volatile("pxor %0,%%xmm6" : : "m" (q[d+16]));
+ asm volatile("pxor %0,%%xmm12" : : "m" (q[d+32]));
+ asm volatile("pxor %0,%%xmm14" : : "m" (q[d+48]));
+ asm volatile("movntdq %%xmm4,%0" : "=m" (q[d]));
+ asm volatile("movntdq %%xmm6,%0" : "=m" (q[d+16]));
+ asm volatile("movntdq %%xmm12,%0" : "=m" (q[d+32]));
+ asm volatile("movntdq %%xmm14,%0" : "=m" (q[d+48]));
+ }
+ asm volatile("sfence" : : : "memory");
+ kernel_fpu_end();
+ }
+
+
const struct raid6_calls raid6_sse2x4 = {
raid6_sse24_gen_syndrome,
+ raid6_sse24_xor_syndrome,
raid6_have_sse2,
"sse2x4",
1 /* Has cache hints */
diff --git a/lib/raid6/test/test.c b/lib/raid6/test/test.c
index 5a485b7a7d3c..3bebbabdb510 100644
--- a/lib/raid6/test/test.c
+++ b/lib/raid6/test/test.c
@@ -28,11 +28,11 @@ char *dataptrs[NDISKS];
char data[NDISKS][PAGE_SIZE];
char recovi[PAGE_SIZE], recovj[PAGE_SIZE];
-static void makedata(void)
+static void makedata(int start, int stop)
{
int i, j;
- for (i = 0; i < NDISKS; i++) {
+ for (i = start; i <= stop; i++) {
for (j = 0; j < PAGE_SIZE; j++)
data[i][j] = rand();
@@ -91,34 +91,55 @@ int main(int argc, char *argv[])
{
const struct raid6_calls *const *algo;
const struct raid6_recov_calls *const *ra;
- int i, j;
+ int i, j, p1, p2;
int err = 0;
- makedata();
+ makedata(0, NDISKS-1);
for (ra = raid6_recov_algos; *ra; ra++) {
if ((*ra)->valid && !(*ra)->valid())
continue;
+
raid6_2data_recov = (*ra)->data2;
raid6_datap_recov = (*ra)->datap;
printf("using recovery %s\n", (*ra)->name);
for (algo = raid6_algos; *algo; algo++) {
- if (!(*algo)->valid || (*algo)->valid()) {
- raid6_call = **algo;
+ if ((*algo)->valid && !(*algo)->valid())
+ continue;
+
+ raid6_call = **algo;
+
+ /* Nuke syndromes */
+ memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE);
+
+ /* Generate assumed good syndrome */
+ raid6_call.gen_syndrome(NDISKS, PAGE_SIZE,
+ (void **)&dataptrs);
+
+ for (i = 0; i < NDISKS-1; i++)
+ for (j = i+1; j < NDISKS; j++)
+ err += test_disks(i, j);
+
+ if (!raid6_call.xor_syndrome)
+ continue;
+
+ for (p1 = 0; p1 < NDISKS-2; p1++)
+ for (p2 = p1; p2 < NDISKS-2; p2++) {
- /* Nuke syndromes */
- memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE);
+ /* Simulate rmw run */
+ raid6_call.xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
+ (void **)&dataptrs);
+ makedata(p1, p2);
+ raid6_call.xor_syndrome(NDISKS, p1, p2, PAGE_SIZE,
+ (void **)&dataptrs);
- /* Generate assumed good syndrome */
- raid6_call.gen_syndrome(NDISKS, PAGE_SIZE,
- (void **)&dataptrs);
+ for (i = 0; i < NDISKS-1; i++)
+ for (j = i+1; j < NDISKS; j++)
+ err += test_disks(i, j);
+ }
- for (i = 0; i < NDISKS-1; i++)
- for (j = i+1; j < NDISKS; j++)
- err += test_disks(i, j);
- }
}
printf("\n");
}
diff --git a/lib/raid6/tilegx.uc b/lib/raid6/tilegx.uc
index e7c29459cbcd..2dd291a11264 100644
--- a/lib/raid6/tilegx.uc
+++ b/lib/raid6/tilegx.uc
@@ -80,6 +80,7 @@ void raid6_tilegx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
const struct raid6_calls raid6_tilegx$# = {
raid6_tilegx$#_gen_syndrome,
+ NULL, /* XOR not yet implemented */
NULL,
"tilegx$#",
0
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index 1826c7407258..c98ae818eb4e 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -4,6 +4,7 @@
* Copyright 31 August 2008 James Bottomley
* Copyright (C) 2013, Intel Corporation
*/
+#include <linux/bug.h>
#include <linux/kernel.h>
#include <linux/math64.h>
#include <linux/export.h>
@@ -14,7 +15,8 @@
/**
* string_get_size - get the size in the specified units
- * @size: The size to be converted
+ * @size: The size to be converted in blocks
+ * @blk_size: Size of the block (use 1 for size in bytes)
* @units: units to use (powers of 1000 or 1024)
* @buf: buffer to format to
* @len: length of buffer
@@ -24,14 +26,14 @@
* at least 9 bytes and will always be zero terminated.
*
*/
-void string_get_size(u64 size, const enum string_size_units units,
+void string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
char *buf, int len)
{
static const char *const units_10[] = {
- "B", "kB", "MB", "GB", "TB", "PB", "EB"
+ "B", "kB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB"
};
static const char *const units_2[] = {
- "B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB"
+ "B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB", "ZiB", "YiB"
};
static const char *const *const units_str[] = {
[STRING_UNITS_10] = units_10,
@@ -42,31 +44,57 @@ void string_get_size(u64 size, const enum string_size_units units,
[STRING_UNITS_2] = 1024,
};
int i, j;
- u32 remainder = 0, sf_cap;
+ u32 remainder = 0, sf_cap, exp;
char tmp[8];
+ const char *unit;
tmp[0] = '\0';
i = 0;
- if (size >= divisor[units]) {
- while (size >= divisor[units]) {
- remainder = do_div(size, divisor[units]);
- i++;
- }
+ if (!size)
+ goto out;
- sf_cap = size;
- for (j = 0; sf_cap*10 < 1000; j++)
- sf_cap *= 10;
+ while (blk_size >= divisor[units]) {
+ remainder = do_div(blk_size, divisor[units]);
+ i++;
+ }
- if (j) {
- remainder *= 1000;
- remainder /= divisor[units];
- snprintf(tmp, sizeof(tmp), ".%03u", remainder);
- tmp[j+1] = '\0';
- }
+ exp = divisor[units] / (u32)blk_size;
+ if (size >= exp) {
+ remainder = do_div(size, divisor[units]);
+ remainder *= blk_size;
+ i++;
+ } else {
+ remainder *= size;
+ }
+
+ size *= blk_size;
+ size += remainder / divisor[units];
+ remainder %= divisor[units];
+
+ while (size >= divisor[units]) {
+ remainder = do_div(size, divisor[units]);
+ i++;
}
+ sf_cap = size;
+ for (j = 0; sf_cap*10 < 1000; j++)
+ sf_cap *= 10;
+
+ if (j) {
+ remainder *= 1000;
+ remainder /= divisor[units];
+ snprintf(tmp, sizeof(tmp), ".%03u", remainder);
+ tmp[j+1] = '\0';
+ }
+
+ out:
+ if (i >= ARRAY_SIZE(units_2))
+ unit = "UNK";
+ else
+ unit = units_str[units][i];
+
snprintf(buf, len, "%u%s %s", (u32)size,
- tmp, units_str[units][i]);
+ tmp, unit);
}
EXPORT_SYMBOL(string_get_size);
diff --git a/lib/test-hexdump.c b/lib/test-hexdump.c
index 9846ff7428b3..c227cc43ec0a 100644
--- a/lib/test-hexdump.c
+++ b/lib/test-hexdump.c
@@ -48,7 +48,7 @@ static void __init test_hexdump(size_t len, int rowsize, int groupsize,
char test[32 * 3 + 2 + 32 + 1];
char real[32 * 3 + 2 + 32 + 1];
char *p;
- const char **result;
+ const char * const *result;
size_t l = len;
int gs = groupsize, rs = rowsize;
unsigned int i;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 3a1e0843f9a2..da39c608a28c 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -33,6 +33,7 @@
#include <asm/page.h> /* for PAGE_SIZE */
#include <asm/sections.h> /* for dereference_function_descriptor() */
+#include <asm/byteorder.h> /* cpu_to_le16 */
#include <linux/string_helpers.h>
#include "kstrtox.h"
@@ -122,142 +123,145 @@ int skip_atoi(const char **s)
return i;
}
-/* Decimal conversion is by far the most typical, and is used
- * for /proc and /sys data. This directly impacts e.g. top performance
- * with many processes running. We optimize it for speed
- * using ideas described at <http://www.cs.uiowa.edu/~jones/bcd/divide.html>
- * (with permission from the author, Douglas W. Jones).
+/*
+ * Decimal conversion is by far the most typical, and is used for
+ * /proc and /sys data. This directly impacts e.g. top performance
+ * with many processes running. We optimize it for speed by emitting
+ * two characters at a time, using a 200 byte lookup table. This
+ * roughly halves the number of multiplications compared to computing
+ * the digits one at a time. Implementation strongly inspired by the
+ * previous version, which in turn used ideas described at
+ * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission
+ * from the author, Douglas W. Jones).
+ *
+ * It turns out there is precisely one 26 bit fixed-point
+ * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32
+ * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual
+ * range happens to be somewhat larger (x <= 1073741898), but that's
+ * irrelevant for our purpose.
+ *
+ * For dividing a number in the range [10^4, 10^6-1] by 100, we still
+ * need a 32x32->64 bit multiply, so we simply use the same constant.
+ *
+ * For dividing a number in the range [100, 10^4-1] by 100, there are
+ * several options. The simplest is (x * 0x147b) >> 19, which is valid
+ * for all x <= 43698.
*/
-#if BITS_PER_LONG != 32 || BITS_PER_LONG_LONG != 64
-/* Formats correctly any integer in [0, 999999999] */
+static const u16 decpair[100] = {
+#define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030)
+ _( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9),
+ _(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19),
+ _(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29),
+ _(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39),
+ _(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49),
+ _(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59),
+ _(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69),
+ _(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79),
+ _(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89),
+ _(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99),
+#undef _
+};
+
+/*
+ * This will print a single '0' even if r == 0, since we would
+ * immediately jump to out_r where two 0s would be written but only
+ * one of them accounted for in buf. This is needed by ip4_string
+ * below. All other callers pass a non-zero value of r.
+*/
static noinline_for_stack
-char *put_dec_full9(char *buf, unsigned q)
+char *put_dec_trunc8(char *buf, unsigned r)
{
- unsigned r;
+ unsigned q;
- /*
- * Possible ways to approx. divide by 10
- * (x * 0x1999999a) >> 32 x < 1073741829 (multiply must be 64-bit)
- * (x * 0xcccd) >> 19 x < 81920 (x < 262149 when 64-bit mul)
- * (x * 0x6667) >> 18 x < 43699
- * (x * 0x3334) >> 17 x < 16389
- * (x * 0x199a) >> 16 x < 16389
- * (x * 0x0ccd) >> 15 x < 16389
- * (x * 0x0667) >> 14 x < 2739
- * (x * 0x0334) >> 13 x < 1029
- * (x * 0x019a) >> 12 x < 1029
- * (x * 0x00cd) >> 11 x < 1029 shorter code than * 0x67 (on i386)
- * (x * 0x0067) >> 10 x < 179
- * (x * 0x0034) >> 9 x < 69 same
- * (x * 0x001a) >> 8 x < 69 same
- * (x * 0x000d) >> 7 x < 69 same, shortest code (on i386)
- * (x * 0x0007) >> 6 x < 19
- * See <http://www.cs.uiowa.edu/~jones/bcd/divide.html>
- */
- r = (q * (uint64_t)0x1999999a) >> 32;
- *buf++ = (q - 10 * r) + '0'; /* 1 */
- q = (r * (uint64_t)0x1999999a) >> 32;
- *buf++ = (r - 10 * q) + '0'; /* 2 */
- r = (q * (uint64_t)0x1999999a) >> 32;
- *buf++ = (q - 10 * r) + '0'; /* 3 */
- q = (r * (uint64_t)0x1999999a) >> 32;
- *buf++ = (r - 10 * q) + '0'; /* 4 */
- r = (q * (uint64_t)0x1999999a) >> 32;
- *buf++ = (q - 10 * r) + '0'; /* 5 */
- /* Now value is under 10000, can avoid 64-bit multiply */
- q = (r * 0x199a) >> 16;
- *buf++ = (r - 10 * q) + '0'; /* 6 */
- r = (q * 0xcd) >> 11;
- *buf++ = (q - 10 * r) + '0'; /* 7 */
- q = (r * 0xcd) >> 11;
- *buf++ = (r - 10 * q) + '0'; /* 8 */
- *buf++ = q + '0'; /* 9 */
+ /* 1 <= r < 10^8 */
+ if (r < 100)
+ goto out_r;
+
+ /* 100 <= r < 10^8 */
+ q = (r * (u64)0x28f5c29) >> 32;
+ *((u16 *)buf) = decpair[r - 100*q];
+ buf += 2;
+
+ /* 1 <= q < 10^6 */
+ if (q < 100)
+ goto out_q;
+
+ /* 100 <= q < 10^6 */
+ r = (q * (u64)0x28f5c29) >> 32;
+ *((u16 *)buf) = decpair[q - 100*r];
+ buf += 2;
+
+ /* 1 <= r < 10^4 */
+ if (r < 100)
+ goto out_r;
+
+ /* 100 <= r < 10^4 */
+ q = (r * 0x147b) >> 19;
+ *((u16 *)buf) = decpair[r - 100*q];
+ buf += 2;
+out_q:
+ /* 1 <= q < 100 */
+ r = q;
+out_r:
+ /* 1 <= r < 100 */
+ *((u16 *)buf) = decpair[r];
+ buf += r < 10 ? 1 : 2;
return buf;
}
-#endif
-/* Similar to above but do not pad with zeros.
- * Code can be easily arranged to print 9 digits too, but our callers
- * always call put_dec_full9() instead when the number has 9 decimal digits.
- */
+#if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64
static noinline_for_stack
-char *put_dec_trunc8(char *buf, unsigned r)
+char *put_dec_full8(char *buf, unsigned r)
{
unsigned q;
- /* Copy of previous function's body with added early returns */
- while (r >= 10000) {
- q = r + '0';
- r = (r * (uint64_t)0x1999999a) >> 32;
- *buf++ = q - 10*r;
- }
+ /* 0 <= r < 10^8 */
+ q = (r * (u64)0x28f5c29) >> 32;
+ *((u16 *)buf) = decpair[r - 100*q];
+ buf += 2;
- q = (r * 0x199a) >> 16; /* r <= 9999 */
- *buf++ = (r - 10 * q) + '0';
- if (q == 0)
- return buf;
- r = (q * 0xcd) >> 11; /* q <= 999 */
- *buf++ = (q - 10 * r) + '0';
- if (r == 0)
- return buf;
- q = (r * 0xcd) >> 11; /* r <= 99 */
- *buf++ = (r - 10 * q) + '0';
- if (q == 0)
- return buf;
- *buf++ = q + '0'; /* q <= 9 */
- return buf;
-}
+ /* 0 <= q < 10^6 */
+ r = (q * (u64)0x28f5c29) >> 32;
+ *((u16 *)buf) = decpair[q - 100*r];
+ buf += 2;
-/* There are two algorithms to print larger numbers.
- * One is generic: divide by 1000000000 and repeatedly print
- * groups of (up to) 9 digits. It's conceptually simple,
- * but requires a (unsigned long long) / 1000000000 division.
- *
- * Second algorithm splits 64-bit unsigned long long into 16-bit chunks,
- * manipulates them cleverly and generates groups of 4 decimal digits.
- * It so happens that it does NOT require long long division.
- *
- * If long is > 32 bits, division of 64-bit values is relatively easy,
- * and we will use the first algorithm.
- * If long long is > 64 bits (strange architecture with VERY large long long),
- * second algorithm can't be used, and we again use the first one.
- *
- * Else (if long is 32 bits and long long is 64 bits) we use second one.
- */
+ /* 0 <= r < 10^4 */
+ q = (r * 0x147b) >> 19;
+ *((u16 *)buf) = decpair[r - 100*q];
+ buf += 2;
-#if BITS_PER_LONG != 32 || BITS_PER_LONG_LONG != 64
-
-/* First algorithm: generic */
+ /* 0 <= q < 100 */
+ *((u16 *)buf) = decpair[q];
+ buf += 2;
+ return buf;
+}
-static
+static noinline_for_stack
char *put_dec(char *buf, unsigned long long n)
{
- if (n >= 100*1000*1000) {
- while (n >= 1000*1000*1000)
- buf = put_dec_full9(buf, do_div(n, 1000*1000*1000));
- if (n >= 100*1000*1000)
- return put_dec_full9(buf, n);
- }
+ if (n >= 100*1000*1000)
+ buf = put_dec_full8(buf, do_div(n, 100*1000*1000));
+ /* 1 <= n <= 1.6e11 */
+ if (n >= 100*1000*1000)
+ buf = put_dec_full8(buf, do_div(n, 100*1000*1000));
+ /* 1 <= n < 1e8 */
return put_dec_trunc8(buf, n);
}
-#else
+#elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64
-/* Second algorithm: valid only for 64-bit long longs */
-
-/* See comment in put_dec_full9 for choice of constants */
-static noinline_for_stack
-void put_dec_full4(char *buf, unsigned q)
+static void
+put_dec_full4(char *buf, unsigned r)
{
- unsigned r;
- r = (q * 0xccd) >> 15;
- buf[0] = (q - 10 * r) + '0';
- q = (r * 0xcd) >> 11;
- buf[1] = (r - 10 * q) + '0';
- r = (q * 0xcd) >> 11;
- buf[2] = (q - 10 * r) + '0';
- buf[3] = r + '0';
+ unsigned q;
+
+ /* 0 <= r < 10^4 */
+ q = (r * 0x147b) >> 19;
+ *((u16 *)buf) = decpair[r - 100*q];
+ buf += 2;
+ /* 0 <= q < 100 */
+ *((u16 *)buf) = decpair[q];
}
/*
@@ -265,9 +269,9 @@ void put_dec_full4(char *buf, unsigned q)
* The approximation x/10000 == (x * 0x346DC5D7) >> 43
* holds for all x < 1,128,869,999. The largest value this
* helper will ever be asked to convert is 1,125,520,955.
- * (d1 in the put_dec code, assuming n is all-ones).
+ * (second call in the put_dec code, assuming n is all-ones).
*/
-static
+static noinline_for_stack
unsigned put_dec_helper4(char *buf, unsigned x)
{
uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43;
@@ -294,6 +298,8 @@ char *put_dec(char *buf, unsigned long long n)
d2 = (h ) & 0xffff;
d3 = (h >> 16); /* implicit "& 0xffff" */
+ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0
+ = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */
q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff);
q = put_dec_helper4(buf, q);
@@ -323,7 +329,8 @@ char *put_dec(char *buf, unsigned long long n)
*/
int num_to_str(char *buf, int size, unsigned long long num)
{
- char tmp[sizeof(num) * 3];
+ /* put_dec requires 2-byte alignment of the buffer. */
+ char tmp[sizeof(num) * 3] __aligned(2);
int idx, len;
/* put_dec() may work incorrectly for num = 0 (generate "", not "0") */
@@ -384,7 +391,8 @@ static noinline_for_stack
char *number(char *buf, char *end, unsigned long long num,
struct printf_spec spec)
{
- char tmp[3 * sizeof(num)];
+ /* put_dec requires 2-byte alignment of the buffer. */
+ char tmp[3 * sizeof(num)] __aligned(2);
char sign;
char locase;
int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10);
@@ -944,7 +952,7 @@ char *ip4_string(char *p, const u8 *addr, const char *fmt)
break;
}
for (i = 0; i < 4; i++) {
- char temp[3]; /* hold each IP quad in reverse order */
+ char temp[4] __aligned(2); /* hold each IP quad in reverse order */
int digits = put_dec_trunc8(temp, addr[index]) - temp;
if (leading_zeros) {
if (digits < 3)