xen: introduce generic non-atomic test_*bit()

The following generic functions were introduced:
* test_bit
* generic__test_and_set_bit
* generic__test_and_clear_bit
* generic__test_and_change_bit

These functions and macros can be useful for architectures
that don't have corresponding arch-specific instructions.

Also, the patch introduces the following generics which are
used by the functions mentioned above:
* BITOP_BITS_PER_WORD
* BITOP_MASK
* BITOP_WORD
* BITOP_TYPE

The following approach was chosen for generic*() and arch*() bit
operation functions:
If the bit operation function that is going to be generic starts
with the prefix "__", then the corresponding generic/arch function
will also contain the "__" prefix. For example:
 * test_bit() will be defined using arch_test_bit() and
   generic_test_bit().
 * __test_and_set_bit() will be defined using
   arch__test_and_set_bit() and generic__test_and_set_bit().

Signed-off-by: Oleksii Kurochko <oleksii.kurochko@gmail.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Michal Orzel <michal.orzel@amd.com>

xen/arch/arm/include/asm/bitops.h

@@ -22,9 +22,6 @@
 #define __set_bit(n,p)            set_bit(n,p)
 #define __clear_bit(n,p)          clear_bit(n,p)
 
-#define BITOP_BITS_PER_WORD     32
-#define BITOP_MASK(nr)          (1UL << ((nr) % BITOP_BITS_PER_WORD))
-#define BITOP_WORD(nr)          ((nr) / BITOP_BITS_PER_WORD)
 #define BITS_PER_BYTE           8
 
 #define ADDR (*(volatile int *) addr)
@@ -76,70 +73,6 @@ bool test_and_change_bit_timeout(int nr, volatile void *p,
 bool clear_mask16_timeout(uint16_t mask, volatile void *p,
                           unsigned int max_try);
 
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_set_bit(int nr, volatile void *addr)
-{
-        unsigned int mask = BITOP_MASK(nr);
-        volatile unsigned int *p =
-                ((volatile unsigned int *)addr) + BITOP_WORD(nr);
-        unsigned int old = *p;
-
-        *p = old | mask;
-        return (old & mask) != 0;
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_clear_bit(int nr, volatile void *addr)
-{
-        unsigned int mask = BITOP_MASK(nr);
-        volatile unsigned int *p =
-                ((volatile unsigned int *)addr) + BITOP_WORD(nr);
-        unsigned int old = *p;
-
-        *p = old & ~mask;
-        return (old & mask) != 0;
-}
-
-/* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr,
-                                            volatile void *addr)
-{
-        unsigned int mask = BITOP_MASK(nr);
-        volatile unsigned int *p =
-                ((volatile unsigned int *)addr) + BITOP_WORD(nr);
-        unsigned int old = *p;
-
-        *p = old ^ mask;
-        return (old & mask) != 0;
-}
-
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static inline int test_bit(int nr, const volatile void *addr)
-{
-        const volatile unsigned int *p = (const volatile unsigned int *)addr;
-        return 1UL & (p[BITOP_WORD(nr)] >> (nr & (BITOP_BITS_PER_WORD-1)));
-}
-
 #define arch_ffs(x)  ((x) ? 1 + __builtin_ctz(x) : 0)
 #define arch_ffsl(x) ((x) ? 1 + __builtin_ctzl(x) : 0)
 #define arch_fls(x)  ((x) ? 32 - __builtin_clz(x) : 0)

xen/arch/ppc/include/asm/bitops.h

@@ -15,9 +15,6 @@
 #define __set_bit(n, p)         set_bit(n, p)
 #define __clear_bit(n, p)       clear_bit(n, p)
 
-#define BITOP_BITS_PER_WORD     32
-#define BITOP_MASK(nr)          (1U << ((nr) % BITOP_BITS_PER_WORD))
-#define BITOP_WORD(nr)          ((nr) / BITOP_BITS_PER_WORD)
 #define BITS_PER_BYTE           8
 
 /* PPC bit number conversion */
@@ -69,17 +66,6 @@ static inline void clear_bit(int nr, volatile void *addr)
     clear_bits(BITOP_MASK(nr), (volatile unsigned int *)addr + BITOP_WORD(nr));
 }
 
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static inline int test_bit(int nr, const volatile void *addr)
-{
-    const volatile unsigned int *p = addr;
-    return 1 & (p[BITOP_WORD(nr)] >> (nr & (BITOP_BITS_PER_WORD - 1)));
-}
-
 static inline unsigned int test_and_clear_bits(
     unsigned int mask,
     volatile unsigned int *p)
@@ -133,44 +119,6 @@ static inline int test_and_set_bit(unsigned int nr, volatile void *addr)
         (volatile unsigned int *)addr + BITOP_WORD(nr)) != 0;
 }
 
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_set_bit(int nr, volatile void *addr)
-{
-    unsigned int mask = BITOP_MASK(nr);
-    volatile unsigned int *p = (volatile unsigned int *)addr + BITOP_WORD(nr);
-    unsigned int old = *p;
-
-    *p = old | mask;
-    return (old & mask) != 0;
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_clear_bit(int nr, volatile void *addr)
-{
-    unsigned int mask = BITOP_MASK(nr);
-    volatile unsigned int *p = (volatile unsigned int *)addr + BITOP_WORD(nr);
-    unsigned int old = *p;
-
-    *p = old & ~mask;
-    return (old & mask) != 0;
-}
-
 #define arch_ffs(x)  ((x) ? 1 + __builtin_ctz(x) : 0)
 #define arch_ffsl(x) ((x) ? 1 + __builtin_ctzl(x) : 0)
 #define arch_fls(x)  ((x) ? 32 - __builtin_clz(x) : 0)

xen/arch/ppc/include/asm/page.h

@@ -2,9 +2,9 @@
 #ifndef _ASM_PPC_PAGE_H
 #define _ASM_PPC_PAGE_H
 
+#include <xen/bitops.h>
 #include <xen/types.h>
 
-#include <asm/bitops.h>
 #include <asm/byteorder.h>
 
 #define PDE_VALID     PPC_BIT(0)

xen/arch/ppc/mm-radix.c

@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-or-later */
+#include <xen/bitops.h>
 #include <xen/init.h>
 #include <xen/kernel.h>
 #include <xen/mm.h>
@@ -6,7 +7,6 @@
 #include <xen/types.h>
 #include <xen/lib.h>
 
-#include <asm/bitops.h>
 #include <asm/byteorder.h>
 #include <asm/early_printk.h>
 #include <asm/page.h>

xen/arch/x86/include/asm/bitops.h

@@ -19,9 +19,6 @@
 #define ADDR (*(volatile int *) addr)
 #define CONST_ADDR (*(const volatile int *) addr)
 
-extern void __bitop_bad_size(void);
-#define bitop_bad_size(addr) (sizeof(*(addr)) < 4)
-
 /**
  * set_bit - Atomically set a bit in memory
  * @nr: the bit to set
@@ -175,7 +172,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
 })
 
 /**
- * __test_and_set_bit - Set a bit and return its old value
+ * arch__test_and_set_bit - Set a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -183,7 +180,7 @@ static inline int test_and_set_bit(int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_set_bit(int nr, void *addr)
+static inline int arch__test_and_set_bit(int nr, volatile void *addr)
 {
     int oldbit;
 
@@ -194,10 +191,7 @@ static inline int __test_and_set_bit(int nr, void *addr)
 
     return oldbit;
 }
-#define __test_and_set_bit(nr, addr) ({                 \
-    if ( bitop_bad_size(addr) ) __bitop_bad_size();     \
-    __test_and_set_bit(nr, addr);                       \
-})
+#define arch__test_and_set_bit arch__test_and_set_bit
 
 /**
  * test_and_clear_bit - Clear a bit and return its old value
@@ -224,7 +218,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
 })
 
 /**
- * __test_and_clear_bit - Clear a bit and return its old value
+ * arch__test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to set
  * @addr: Address to count from
  *
@@ -232,7 +226,7 @@ static inline int test_and_clear_bit(int nr, volatile void *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static inline int __test_and_clear_bit(int nr, void *addr)
+static inline int arch__test_and_clear_bit(int nr, volatile void *addr)
 {
     int oldbit;
 
@@ -243,13 +237,10 @@ static inline int __test_and_clear_bit(int nr, void *addr)
 
     return oldbit;
 }
-#define __test_and_clear_bit(nr, addr) ({               \
-    if ( bitop_bad_size(addr) ) __bitop_bad_size();     \
-    __test_and_clear_bit(nr, addr);                     \
-})
+#define arch__test_and_clear_bit arch__test_and_clear_bit
 
 /* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, void *addr)
+static inline int arch__test_and_change_bit(int nr, volatile void *addr)
 {
     int oldbit;
 
@@ -260,10 +251,7 @@ static inline int __test_and_change_bit(int nr, void *addr)
 
     return oldbit;
 }
-#define __test_and_change_bit(nr, addr) ({              \
-    if ( bitop_bad_size(addr) ) __bitop_bad_size();     \
-    __test_and_change_bit(nr, addr);                    \
-})
+#define arch__test_and_change_bit arch__test_and_change_bit
 
 /**
  * test_and_change_bit - Change a bit and return its new value
@@ -307,8 +295,7 @@ static inline int variable_test_bit(int nr, const volatile void *addr)
     return oldbit;
 }
 
-#define test_bit(nr, addr) ({                           \
-    if ( bitop_bad_size(addr) ) __bitop_bad_size();     \
+#define arch_test_bit(nr, addr) ({                      \
     __builtin_constant_p(nr) ?                          \
         constant_test_bit(nr, addr) :                   \
         variable_test_bit(nr, addr);                    \

xen/include/xen/bitops.h

@@ -4,6 +4,17 @@
 #include <xen/compiler.h>
 #include <xen/types.h>
 
+#define BITOP_BITS_PER_WORD 32
+typedef uint32_t bitop_uint_t;
+
+#define BITOP_MASK(nr)  ((bitop_uint_t)1 << ((nr) % BITOP_BITS_PER_WORD))
+
+#define BITOP_WORD(nr)  ((nr) / BITOP_BITS_PER_WORD)
+
+extern void __bitop_bad_size(void);
+
+#define bitop_bad_size(addr) (sizeof(*(addr)) < sizeof(bitop_uint_t))
+
 #include <asm/bitops.h>
 
 /*
@@ -24,6 +35,175 @@
 unsigned int __pure generic_ffsl(unsigned long x);
 unsigned int __pure generic_flsl(unsigned long x);
 
+/**
+ * generic__test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static always_inline bool
+generic__test_and_set_bit(int nr, volatile void *addr)
+{
+    bitop_uint_t mask = BITOP_MASK(nr);
+    volatile bitop_uint_t *p = (volatile bitop_uint_t *)addr + BITOP_WORD(nr);
+    bitop_uint_t old = *p;
+
+    *p = old | mask;
+    return (old & mask);
+}
+
+/**
+ * generic__test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static always_inline bool
+generic__test_and_clear_bit(int nr, volatile void *addr)
+{
+    bitop_uint_t mask = BITOP_MASK(nr);
+    volatile bitop_uint_t *p = (volatile bitop_uint_t *)addr + BITOP_WORD(nr);
+    bitop_uint_t old = *p;
+
+    *p = old & ~mask;
+    return (old & mask);
+}
+
+/**
+ * generic__test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static always_inline bool
+generic__test_and_change_bit(int nr, volatile void *addr)
+{
+    bitop_uint_t mask = BITOP_MASK(nr);
+    volatile bitop_uint_t *p = (volatile bitop_uint_t *)addr + BITOP_WORD(nr);
+    bitop_uint_t old = *p;
+
+    *p = old ^ mask;
+    return (old & mask);
+}
+
+/**
+ * generic_test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static always_inline bool generic_test_bit(int nr, const volatile void *addr)
+{
+    bitop_uint_t mask = BITOP_MASK(nr);
+    const volatile bitop_uint_t *p =
+        (const volatile bitop_uint_t *)addr + BITOP_WORD(nr);
+
+    return (*p & mask);
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static always_inline bool
+__test_and_set_bit(int nr, volatile void *addr)
+{
+#ifndef arch__test_and_set_bit
+#define arch__test_and_set_bit generic__test_and_set_bit
+#endif
+
+    return arch__test_and_set_bit(nr, addr);
+}
+#define __test_and_set_bit(nr, addr) ({             \
+    if ( bitop_bad_size(addr) ) __bitop_bad_size(); \
+    __test_and_set_bit(nr, addr);                   \
+})
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static always_inline bool
+__test_and_clear_bit(int nr, volatile void *addr)
+{
+#ifndef arch__test_and_clear_bit
+#define arch__test_and_clear_bit generic__test_and_clear_bit
+#endif
+
+    return arch__test_and_clear_bit(nr, addr);
+}
+#define __test_and_clear_bit(nr, addr) ({           \
+    if ( bitop_bad_size(addr) ) __bitop_bad_size(); \
+    __test_and_clear_bit(nr, addr);                 \
+})
+
+/**
+ * __test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static always_inline bool
+__test_and_change_bit(int nr, volatile void *addr)
+{
+#ifndef arch__test_and_change_bit
+#define arch__test_and_change_bit generic__test_and_change_bit
+#endif
+
+    return arch__test_and_change_bit(nr, addr);
+}
+#define __test_and_change_bit(nr, addr) ({              \
+    if ( bitop_bad_size(addr) ) __bitop_bad_size();     \
+    __test_and_change_bit(nr, addr);                    \
+})
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static always_inline bool test_bit(int nr, const volatile void *addr)
+{
+#ifndef arch_test_bit
+#define arch_test_bit generic_test_bit
+#endif
+
+    return arch_test_bit(nr, addr);
+}
+#define test_bit(nr, addr) ({                           \
+    if ( bitop_bad_size(addr) ) __bitop_bad_size();     \
+    test_bit(nr, addr);                                 \
+})
+
 static always_inline __pure unsigned int ffs(unsigned int x)
 {
     if ( __builtin_constant_p(x) )