Merge branch 'linus' into x86/urgent

Merge reason: pull in latest to fix a bug in it.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 398 insertions, 1 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 9960be04cbbe..bb1326d3839c 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -194,4 +194,10 @@ config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
 config NLATTR
         bool
 
+#
+# Generic 64-bit atomic support is selected if needed
+#
+config GENERIC_ATOMIC64
+       bool
+
 endmenu
diff --git a/lib/Makefile b/lib/Makefile
index 1f6edefebffe..8e9bcf9d3261 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -93,6 +93,10 @@ obj-$(CONFIG_NLATTR) += nlattr.o
 
 obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
 
+obj-$(CONFIG_GENERIC_CSUM) += checksum.o
+
+obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
+
 hostprogs-y     := gen_crc32table
 clean-files     := crc32table.h
 
diff --git a/lib/atomic64.c b/lib/atomic64.c
new file mode 100644
index 000000000000..c5e725562416
--- /dev/null
+++ b/lib/atomic64.c
@@ -0,0 +1,175 @@
+/*
+ * Generic implementation of 64-bit atomics using spinlocks,
+ * useful on processors that don't have 64-bit atomic instructions.
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.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/types.h>
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <asm/atomic.h>
+
+/*
+ * We use a hashed array of spinlocks to provide exclusive access
+ * to each atomic64_t variable.  Since this is expected to used on
+ * systems with small numbers of CPUs (<= 4 or so), we use a
+ * relatively small array of 16 spinlocks to avoid wasting too much
+ * memory on the spinlock array.
+ */
+#define NR_LOCKS        16
+
+/*
+ * Ensure each lock is in a separate cacheline.
+ */
+static union {
+        spinlock_t lock;
+        char pad[L1_CACHE_BYTES];
+} atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp;
+
+static inline spinlock_t *lock_addr(const atomic64_t *v)
+{
+        unsigned long addr = (unsigned long) v;
+
+        addr >>= L1_CACHE_SHIFT;
+        addr ^= (addr >> 8) ^ (addr >> 16);
+        return &atomic64_lock[addr & (NR_LOCKS - 1)].lock;
+}
+
+long long atomic64_read(const atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+void atomic64_set(atomic64_t *v, long long i)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+
+        spin_lock_irqsave(lock, flags);
+        v->counter = i;
+        spin_unlock_irqrestore(lock, flags);
+}
+
+void atomic64_add(long long a, atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+
+        spin_lock_irqsave(lock, flags);
+        v->counter += a;
+        spin_unlock_irqrestore(lock, flags);
+}
+
+long long atomic64_add_return(long long a, atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter += a;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+void atomic64_sub(long long a, atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+
+        spin_lock_irqsave(lock, flags);
+        v->counter -= a;
+        spin_unlock_irqrestore(lock, flags);
+}
+
+long long atomic64_sub_return(long long a, atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter -= a;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+long long atomic64_dec_if_positive(atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter - 1;
+        if (val >= 0)
+                v->counter = val;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter;
+        if (val == o)
+                v->counter = n;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+long long atomic64_xchg(atomic64_t *v, long long new)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter;
+        v->counter = new;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        int ret = 1;
+
+        spin_lock_irqsave(lock, flags);
+        if (v->counter != u) {
+                v->counter += a;
+                ret = 0;
+        }
+        spin_unlock_irqrestore(lock, flags);
+        return ret;
+}
+
+static int init_atomic64_lock(void)
+{
+        int i;
+
+        for (i = 0; i < NR_LOCKS; ++i)
+                spin_lock_init(&atomic64_lock[i].lock);
+        return 0;
+}
+
+pure_initcall(init_atomic64_lock);
diff --git a/lib/checksum.c b/lib/checksum.c
new file mode 100644
index 000000000000..12e5a1c91cda
--- /dev/null
+++ b/lib/checksum.c
@@ -0,0 +1,193 @@
+/*
+ *
+ * INET         An implementation of the TCP/IP protocol suite for the LINUX
+ *              operating system.  INET is implemented using the  BSD Socket
+ *              interface as the means of communication with the user level.
+ *
+ *              IP/TCP/UDP checksumming routines
+ *
+ * Authors:     Jorge Cwik, <jorge@laser.satlink.net>
+ *              Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ *              Tom May, <ftom@netcom.com>
+ *              Andreas Schwab, <schwab@issan.informatik.uni-dortmund.de>
+ *              Lots of code moved from tcp.c and ip.c; see those files
+ *              for more names.
+ *
+ * 03/02/96     Jes Sorensen, Andreas Schwab, Roman Hodek:
+ *              Fixed some nasty bugs, causing some horrible crashes.
+ *              A: At some points, the sum (%0) was used as
+ *              length-counter instead of the length counter
+ *              (%1). Thanks to Roman Hodek for pointing this out.
+ *              B: GCC seems to mess up if one uses too many
+ *              data-registers to hold input values and one tries to
+ *              specify d0 and d1 as scratch registers. Letting gcc
+ *              choose these registers itself solves the problem.
+ *
+ *              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.
+ */
+
+/* Revised by Kenneth Albanowski for m68knommu. Basic problem: unaligned access
+ kills, so most of the assembly has to go. */
+
+#include <linux/module.h>
+#include <net/checksum.h>
+
+#include <asm/byteorder.h>
+
+static inline unsigned short from32to16(unsigned long x)
+{
+        /* add up 16-bit and 16-bit for 16+c bit */
+        x = (x & 0xffff) + (x >> 16);
+        /* add up carry.. */
+        x = (x & 0xffff) + (x >> 16);
+        return x;
+}
+
+static unsigned int do_csum(const unsigned char *buff, int len)
+{
+        int odd, count;
+        unsigned long result = 0;
+
+        if (len <= 0)
+                goto out;
+        odd = 1 & (unsigned long) buff;
+        if (odd) {
+                result = *buff;
+                len--;
+                buff++;
+        }
+        count = len >> 1;               /* nr of 16-bit words.. */
+        if (count) {
+                if (2 & (unsigned long) buff) {
+                        result += *(unsigned short *) buff;
+                        count--;
+                        len -= 2;
+                        buff += 2;
+                }
+                count >>= 1;            /* nr of 32-bit words.. */
+                if (count) {
+                        unsigned long carry = 0;
+                        do {
+                                unsigned long w = *(unsigned long *) buff;
+                                count--;
+                                buff += 4;
+                                result += carry;
+                                result += w;
+                                carry = (w > result);
+                        } while (count);
+                        result += carry;
+                        result = (result & 0xffff) + (result >> 16);
+                }
+                if (len & 2) {
+                        result += *(unsigned short *) buff;
+                        buff += 2;
+                }
+        }
+        if (len & 1)
+                result += (*buff << 8);
+        result = from32to16(result);
+        if (odd)
+                result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
+out:
+        return result;
+}
+
+/*
+ *      This is a version of ip_compute_csum() optimized for IP headers,
+ *      which always checksum on 4 octet boundaries.
+ */
+__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+        return (__force __sum16)~do_csum(iph, ihl*4);
+}
+EXPORT_SYMBOL(ip_fast_csum);
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+__wsum csum_partial(const void *buff, int len, __wsum wsum)
+{
+        unsigned int sum = (__force unsigned int)wsum;
+        unsigned int result = do_csum(buff, len);
+
+        /* add in old sum, and carry.. */
+        result += sum;
+        if (sum > result)
+                result += 1;
+        return (__force __wsum)result;
+}
+EXPORT_SYMBOL(csum_partial);
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+__sum16 ip_compute_csum(const void *buff, int len)
+{
+        return (__force __sum16)~do_csum(buff, len);
+}
+EXPORT_SYMBOL(ip_compute_csum);
+
+/*
+ * copy from fs while checksumming, otherwise like csum_partial
+ */
+__wsum
+csum_partial_copy_from_user(const void __user *src, void *dst, int len,
+                                                __wsum sum, int *csum_err)
+{
+        int missing;
+
+        missing = __copy_from_user(dst, src, len);
+        if (missing) {
+                memset(dst + len - missing, 0, missing);
+                *csum_err = -EFAULT;
+        } else
+                *csum_err = 0;
+
+        return csum_partial(dst, len, sum);
+}
+EXPORT_SYMBOL(csum_partial_copy_from_user);
+
+/*
+ * copy from ds while checksumming, otherwise like csum_partial
+ */
+__wsum
+csum_partial_copy(const void *src, void *dst, int len, __wsum sum)
+{
+        memcpy(dst, src, len);
+        return csum_partial(dst, len, sum);
+}
+EXPORT_SYMBOL(csum_partial_copy);
+
+#ifndef csum_tcpudp_nofold
+__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+                        unsigned short len,
+                        unsigned short proto,
+                        __wsum sum)
+{
+        unsigned long long s = (__force u32)sum;
+
+        s += (__force u32)saddr;
+        s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN
+        s += proto + len;
+#else
+        s += (proto + len) << 8;
+#endif
+        s += (s >> 32);
+        return (__force __wsum)s;
+}
+EXPORT_SYMBOL(csum_tcpudp_nofold);
+#endif
diff --git a/lib/extable.c b/lib/extable.c
index 179c08745595..4cac81ec225e 100644
--- a/lib/extable.c
+++ b/lib/extable.c
@@ -39,7 +39,26 @@ void sort_extable(struct exception_table_entry *start,
         sort(start, finish - start, sizeof(struct exception_table_entry),
              cmp_ex, NULL);
 }
-#endif
+
+#ifdef CONFIG_MODULES
+/*
+ * If the exception table is sorted, any referring to the module init
+ * will be at the beginning or the end.
+ */
+void trim_init_extable(struct module *m)
+{
+        /*trim the beginning*/
+        while (m->num_exentries && within_module_init(m->extable[0].insn, m)) {
+                m->extable++;
+                m->num_exentries--;
+        }
+        /*trim the end*/
+        while (m->num_exentries &&
+                within_module_init(m->extable[m->num_exentries-1].insn, m))
+                m->num_exentries--;
+}
+#endif /* CONFIG_MODULES */
+#endif /* !ARCH_HAS_SORT_EXTABLE */
 
 #ifndef ARCH_HAS_SEARCH_EXTABLE
 /*