bitmap: add atomic set functions

Use atomic_or() for atomic bitmaps where several threads may set bits at
the same time. This avoids the race condition between threads loading
an element, bitwise ORing, and then storing the element.

When setting all bits in a word we can avoid atomic ops and instead just
use an smp_mb() at the end.

Most bitmap users don't need atomicity so introduce new functions.

Backports commit 9f02cfc84b85929947b32fe1674fbc6a429f332a from qemu

qemu/include/qemu/bitmap.h

@@ -27,6 +27,7 @@
  * Otherwise many inlines will generate horrible code.
  *
  * bitmap_set(dst, pos, nbits)			Set specified bit area
+ * bitmap_set_atomic(dst, pos, nbits)   Set specified bit area with atomic ops
  * bitmap_clear(dst, pos, nbits)		Clear specified bit area
  */
 
@@ -47,6 +48,7 @@
         unsigned long name[BITS_TO_LONGS(bits)]
 
 void bitmap_set(unsigned long *map, long i, long len);
+void bitmap_set_atomic(unsigned long *map, long i, long len);
 void bitmap_clear(unsigned long *map, long start, long nr);
 
 static inline unsigned long *bitmap_zero_extend(unsigned long *old,

qemu/include/qemu/bitops.h

@@ -16,6 +16,7 @@
 #include <assert.h>
 
 #include "host-utils.h"
+#include "atomic.h"
 
 #define BITS_PER_BYTE           CHAR_BIT
 #define BITS_PER_LONG           (sizeof (unsigned long) * BITS_PER_BYTE)
@@ -38,6 +39,19 @@ static inline void set_bit(long nr, unsigned long *addr)
     *p  |= mask;
 }
 
+/**
+ * set_bit_atomic - Set a bit in memory atomically
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ */
+static inline void set_bit_atomic(long nr, unsigned long *addr)
+{
+    unsigned long mask = BIT_MASK(nr);
+    unsigned long *p = addr + BIT_WORD(nr);
+
+    atomic_or(p, mask);
+}
+
 /**
  * clear_bit - Clears a bit in memory
  * @nr: Bit to clear

qemu/util/bitmap.c

@@ -11,6 +11,7 @@
 
 #include "qemu/bitops.h"
 #include "qemu/bitmap.h"
+#include "qemu/atomic.h"
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
 
@@ -34,6 +35,43 @@ void bitmap_set(unsigned long *map, long start, long nr)
     }
 }
 
+void bitmap_set_atomic(unsigned long *map, long start, long nr)
+{
+    unsigned long *p = map + BIT_WORD(start);
+    const long size = start + nr;
+    int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+    unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+    /* First word */
+    if (nr - bits_to_set > 0) {
+        atomic_or(p, mask_to_set);
+        nr -= bits_to_set;
+        bits_to_set = BITS_PER_LONG;
+        mask_to_set = ~0UL;
+        p++;
+    }
+
+    /* Full words */
+    if (bits_to_set == BITS_PER_LONG) {
+        while (nr >= BITS_PER_LONG) {
+            *p = ~0UL;
+            nr -= BITS_PER_LONG;
+            p++;
+        }
+    }
+
+    /* Last word */
+    if (nr) {
+        mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+        atomic_or(p, mask_to_set);
+    } else {
+        /* If we avoided the full barrier in atomic_or(), issue a
+         * barrier to account for the assignments in the while loop.
+         */
+        smp_mb();
+    }
+}
+
 void bitmap_clear(unsigned long *map, long start, long nr)
 {
     unsigned long *p = map + BIT_WORD(start);