Merge tag 'bitmap-for-6.16-rc1' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - dead code cleanups for cpumasks and nodemasks (me)

 - fixed-width flavors of GENMASK() and BIT() (Vincent, Lucas and me)

 - FIELD_MODIFY() helper (Luo)

 - for_each_node_with_cpus() optimization (me)

 - bitmap-str fixes (Andy)

* tag 'bitmap-for-6.16-rc1' of https://github.com/norov/linux:
  topology: make for_each_node_with_cpus() O(N)
  bitfield: Add FIELD_MODIFY() helper
  bitmap-str: Add missing header(s)
  bitmap-str: Get rid of 'extern' for function prototypes
  build_bug.h: more user friendly error messages in BUILD_BUG_ON_ZERO()
  test_bits: add tests for BIT_U*()
  test_bits: add tests for GENMASK_U*()
  drm/i915: Convert REG_GENMASK*() to fixed-width GENMASK_U*()
  bits: introduce fixed-type BIT_U*()
  bits: introduce fixed-type GENMASK_U*()
  bits: add comments and newlines to #if, #else and #endif directives
  cpumask: drop cpumask_assign_cpu()
  riscv: switch set_icache_stale_mask() to using non-atomic assign_cpu()
  cpumask: add non-atomic __assign_cpu()
  nodemask: drop nodes_shift

Author: torvalds

arch/riscv/mm/cacheflush.c

@@ -172,7 +172,7 @@ static void set_icache_stale_mask(void)
 	stale_cpu = cpumask_test_cpu(cpu, mask);
 
 	cpumask_setall(mask);
-	cpumask_assign_cpu(cpu, mask, stale_cpu);
+	__assign_cpu(cpu, mask, stale_cpu);
 	put_cpu();
 }
 #endif

drivers/gpu/drm/i915/i915_reg_defs.h

@@ -9,76 +9,19 @@
 #include <linux/bitfield.h>
 #include <linux/bits.h>
 
-/**
- * REG_BIT() - Prepare a u32 bit value
- * @__n: 0-based bit number
- *
- * Local wrapper for BIT() to force u32, with compile time checks.
- *
- * @return: Value with bit @__n set.
- */
-#define REG_BIT(__n)							\
-	((u32)(BIT(__n) +						\
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__n) &&		\
-				 ((__n) < 0 || (__n) > 31))))
-
-/**
- * REG_BIT8() - Prepare a u8 bit value
- * @__n: 0-based bit number
- *
- * Local wrapper for BIT() to force u8, with compile time checks.
- *
- * @return: Value with bit @__n set.
- */
-#define REG_BIT8(__n)                                                   \
-	((u8)(BIT(__n) +                                                \
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__n) &&         \
-				 ((__n) < 0 || (__n) > 7))))
-
-/**
- * REG_GENMASK() - Prepare a continuous u32 bitmask
- * @__high: 0-based high bit
- * @__low: 0-based low bit
- *
- * Local wrapper for GENMASK() to force u32, with compile time checks.
- *
- * @return: Continuous bitmask from @__high to @__low, inclusive.
- */
-#define REG_GENMASK(__high, __low)					\
-	((u32)(GENMASK(__high, __low) +					\
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&	\
-				 __is_constexpr(__low) &&		\
-				 ((__low) < 0 || (__high) > 31 || (__low) > (__high)))))
-
-/**
- * REG_GENMASK64() - Prepare a continuous u64 bitmask
- * @__high: 0-based high bit
- * @__low: 0-based low bit
- *
- * Local wrapper for GENMASK_ULL() to force u64, with compile time checks.
- *
- * @return: Continuous bitmask from @__high to @__low, inclusive.
+/*
+ * Wrappers over the generic fixed width BIT_U*() and GENMASK_U*()
+ * implementations, for compatibility reasons with previous implementation.
  */
-#define REG_GENMASK64(__high, __low)					\
-	((u64)(GENMASK_ULL(__high, __low) +				\
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&		\
-				 __is_constexpr(__low) &&		\
-				 ((__low) < 0 || (__high) > 63 || (__low) > (__high)))))
+#define REG_GENMASK(high, low)		GENMASK_U32(high, low)
+#define REG_GENMASK64(high, low)	GENMASK_U64(high, low)
+#define REG_GENMASK16(high, low)	GENMASK_U16(high, low)
+#define REG_GENMASK8(high, low)		GENMASK_U8(high, low)
 
-/**
- * REG_GENMASK8() - Prepare a continuous u8 bitmask
- * @__high: 0-based high bit
- * @__low: 0-based low bit
- *
- * Local wrapper for GENMASK() to force u8, with compile time checks.
- *
- * @return: Continuous bitmask from @__high to @__low, inclusive.
- */
-#define REG_GENMASK8(__high, __low)                                     \
-	((u8)(GENMASK(__high, __low) +                                  \
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&      \
-				 __is_constexpr(__low) &&               \
-				 ((__low) < 0 || (__high) > 7 || (__low) > (__high)))))
+#define REG_BIT(n)			BIT_U32(n)
+#define REG_BIT64(n)			BIT_U64(n)
+#define REG_BIT16(n)			BIT_U16(n)
+#define REG_BIT8(n)			BIT_U8(n)
 
 /*
  * Local integer constant expression version of is_power_of_2().
@@ -143,35 +86,6 @@
  */
 #define REG_FIELD_GET64(__mask, __val)	((u64)FIELD_GET(__mask, __val))
 
-/**
- * REG_BIT16() - Prepare a u16 bit value
- * @__n: 0-based bit number
- *
- * Local wrapper for BIT() to force u16, with compile time
- * checks.
- *
- * @return: Value with bit @__n set.
- */
-#define REG_BIT16(__n)                                                   \
-	((u16)(BIT(__n) +                                                \
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__n) &&         \
-				 ((__n) < 0 || (__n) > 15))))
-
-/**
- * REG_GENMASK16() - Prepare a continuous u8 bitmask
- * @__high: 0-based high bit
- * @__low: 0-based low bit
- *
- * Local wrapper for GENMASK() to force u16, with compile time
- * checks.
- *
- * @return: Continuous bitmask from @__high to @__low, inclusive.
- */
-#define REG_GENMASK16(__high, __low)                                     \
-	((u16)(GENMASK(__high, __low) +                                  \
-	       BUILD_BUG_ON_ZERO(__is_constexpr(__high) &&      \
-				 __is_constexpr(__low) &&               \
-				 ((__low) < 0 || (__high) > 15 || (__low) > (__high)))))
 
 /**
  * REG_FIELD_PREP16() - Prepare a u16 bitfield value

include/linux/bitfield.h

@@ -8,6 +8,7 @@
 #define _LINUX_BITFIELD_H
 
 #include <linux/build_bug.h>
+#include <linux/typecheck.h>
 #include <asm/byteorder.h>
 
 /*
@@ -38,8 +39,7 @@
  *	  FIELD_PREP(REG_FIELD_D, 0x40);
  *
  * Modify:
- *  reg &= ~REG_FIELD_C;
- *  reg |= FIELD_PREP(REG_FIELD_C, c);
+ *  FIELD_MODIFY(REG_FIELD_C, &reg, c);
  */
 
 #define __bf_shf(x) (__builtin_ffsll(x) - 1)
@@ -156,6 +156,23 @@
 		(typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask));	\
 	})
 
+/**
+ * FIELD_MODIFY() - modify a bitfield element
+ * @_mask: shifted mask defining the field's length and position
+ * @_reg_p: pointer to the memory that should be updated
+ * @_val: value to store in the bitfield
+ *
+ * FIELD_MODIFY() modifies the set of bits in @_reg_p specified by @_mask,
+ * by replacing them with the bitfield value passed in as @_val.
+ */
+#define FIELD_MODIFY(_mask, _reg_p, _val)						\
+	({										\
+		typecheck_pointer(_reg_p);						\
+		__BF_FIELD_CHECK(_mask, *(_reg_p), _val, "FIELD_MODIFY: ");		\
+		*(_reg_p) &= ~(_mask);							\
+		*(_reg_p) |= (((typeof(_mask))(_val) << __bf_shf(_mask)) & (_mask));	\
+	})
+
 extern void __compiletime_error("value doesn't fit into mask")
 __field_overflow(void);
 extern void __compiletime_error("bad bitfield mask")

include/linux/bitmap-str.h

@@ -2,12 +2,14 @@
 #ifndef __LINUX_BITMAP_STR_H
 #define __LINUX_BITMAP_STR_H
 
+#include <linux/types.h>
+
 int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits);
 int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits);
-extern int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp,
-					int nmaskbits, loff_t off, size_t count);
-extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp,
-					int nmaskbits, loff_t off, size_t count);
+int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp, int nmaskbits,
+				loff_t off, size_t count);
+int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp, int nmaskbits,
+			     loff_t off, size_t count);
 int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits);
 int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits);
 int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,

include/linux/bitops.h

@@ -8,7 +8,6 @@
 
 #include <uapi/linux/kernel.h>
 
-#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 #define BITS_TO_LONGS(nr)	__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
 #define BITS_TO_U64(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
 #define BITS_TO_U32(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))

include/linux/bits.h

@@ -12,23 +12,76 @@
 #define BIT_ULL_MASK(nr)	(ULL(1) << ((nr) % BITS_PER_LONG_LONG))
 #define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
 #define BITS_PER_BYTE		8
+#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 
 /*
  * Create a contiguous bitmask starting at bit position @l and ending at
  * position @h. For example
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
 #if !defined(__ASSEMBLY__)
+
+/*
+ * Missing asm support
+ *
+ * GENMASK_U*() and BIT_U*() depend on BITS_PER_TYPE() which relies on sizeof(),
+ * something not available in asm. Nevertheless, fixed width integers is a C
+ * concept. Assembly code can rely on the long and long long versions instead.
+ */
+
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
+#include <linux/overflow.h>
+
 #define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
-#else
+
+/*
+ * Generate a mask for the specified type @t. Additional checks are made to
+ * guarantee the value returned fits in that type, relying on
+ * -Wshift-count-overflow compiler check to detect incompatible arguments.
+ * For example, all these create build errors or warnings:
+ *
+ * - GENMASK(15, 20): wrong argument order
+ * - GENMASK(72, 15): doesn't fit unsigned long
+ * - GENMASK_U32(33, 15): doesn't fit in a u32
+ */
+#define GENMASK_TYPE(t, h, l)					\
+	((t)(GENMASK_INPUT_CHECK(h, l) +			\
+	     (type_max(t) << (l) &				\
+	      type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h)))))
+
+#define GENMASK_U8(h, l)	GENMASK_TYPE(u8, h, l)
+#define GENMASK_U16(h, l)	GENMASK_TYPE(u16, h, l)
+#define GENMASK_U32(h, l)	GENMASK_TYPE(u32, h, l)
+#define GENMASK_U64(h, l)	GENMASK_TYPE(u64, h, l)
+
+/*
+ * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The
+ * following examples generate compiler warnings due to -Wshift-count-overflow:
+ *
+ * - BIT_U8(8)
+ * - BIT_U32(-1)
+ * - BIT_U32(40)
+ */
+#define BIT_INPUT_CHECK(type, nr) \
+	BUILD_BUG_ON_ZERO(const_true((nr) >= BITS_PER_TYPE(type)))
+
+#define BIT_TYPE(type, nr) ((type)(BIT_INPUT_CHECK(type, nr) + BIT_ULL(nr)))
+
+#define BIT_U8(nr)	BIT_TYPE(u8, nr)
+#define BIT_U16(nr)	BIT_TYPE(u16, nr)
+#define BIT_U32(nr)	BIT_TYPE(u32, nr)
+#define BIT_U64(nr)	BIT_TYPE(u64, nr)
+
+#else /* defined(__ASSEMBLY__) */
+
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
  * disable the input check if that is the case.
  */
 #define GENMASK_INPUT_CHECK(h, l) 0
-#endif
+
+#endif /* !defined(__ASSEMBLY__) */
 
 #define GENMASK(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))

include/linux/build_bug.h

@@ -4,17 +4,17 @@
 
 #include <linux/compiler.h>
 
-#ifdef __CHECKER__
-#define BUILD_BUG_ON_ZERO(e) (0)
-#else /* __CHECKER__ */
 /*
  * Force a compilation error if condition is true, but also produce a
  * result (of value 0 and type int), so the expression can be used
  * e.g. in a structure initializer (or where-ever else comma expressions
  * aren't permitted).
+ *
+ * Take an error message as an optional second argument. If omitted,
+ * default to the stringification of the tested expression.
  */
-#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); })))
-#endif /* __CHECKER__ */
+#define BUILD_BUG_ON_ZERO(e, ...) \
+	__BUILD_BUG_ON_ZERO_MSG(e, ##__VA_ARGS__, #e " is true")
 
 /* Force a compilation error if a constant expression is not a power of 2 */
 #define __BUILD_BUG_ON_NOT_POWER_OF_2(n)	\

include/linux/compiler.h

@@ -192,9 +192,9 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 })
 
 #ifdef __CHECKER__
-#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0)
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) (0)
 #else /* __CHECKER__ */
-#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
 #endif /* __CHECKER__ */
 
 /* &a[0] degrades to a pointer: a different type from an array */

include/linux/cpumask.h

@@ -625,22 +625,6 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
 	__clear_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-/**
- * cpumask_assign_cpu - assign a cpu in a cpumask
- * @cpu: cpu number (< nr_cpu_ids)
- * @dstp: the cpumask pointer
- * @bool: the value to assign
- */
-static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value)
-{
-	assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value);
-}
-
-static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value)
-{
-	__assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value);
-}
-
 /**
  * cpumask_test_cpu - test for a cpu in a cpumask
  * @cpu: cpu number (< nr_cpu_ids)
@@ -1141,6 +1125,9 @@ void init_cpu_possible(const struct cpumask *src);
 #define assign_cpu(cpu, mask, val)	\
 	assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
 
+#define __assign_cpu(cpu, mask, val)	\
+	__assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
+
 #define set_cpu_possible(cpu, possible)	assign_cpu((cpu), &__cpu_possible_mask, (possible))
 #define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_enabled_mask, (enabled))
 #define set_cpu_present(cpu, present)	assign_cpu((cpu), &__cpu_present_mask, (present))

include/linux/nodemask.h

@@ -39,9 +39,6 @@
  * int nodes_full(mask)			Is mask full (all bits sets)?
  * int nodes_weight(mask)		Hamming weight - number of set bits
  *
- * void nodes_shift_right(dst, src, n)	Shift right
- * void nodes_shift_left(dst, src, n)	Shift left
- *
  * unsigned int first_node(mask)	Number lowest set bit, or MAX_NUMNODES
  * unsigend int next_node(node, mask)	Next node past 'node', or MAX_NUMNODES
  * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first,
@@ -247,22 +244,6 @@ static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int n
 	return bitmap_weight(srcp->bits, nbits);
 }
 
-#define nodes_shift_right(dst, src, n) \
-			__nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES)
-static __always_inline void __nodes_shift_right(nodemask_t *dstp,
-					const nodemask_t *srcp, int n, int nbits)
-{
-	bitmap_shift_right(dstp->bits, srcp->bits, n, nbits);
-}
-
-#define nodes_shift_left(dst, src, n) \
-			__nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES)
-static __always_inline void __nodes_shift_left(nodemask_t *dstp,
-					const nodemask_t *srcp, int n, int nbits)
-{
-	bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
-}
-
 /* FIXME: better would be to fix all architectures to never return
           > MAX_NUMNODES, then the silly min_ts could be dropped. */
 
@@ -541,6 +522,7 @@ static __always_inline int node_random(const nodemask_t *maskp)
 
 #define for_each_node(node)	   for_each_node_state(node, N_POSSIBLE)
 #define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
+#define for_each_node_with_cpus(node)	for_each_node_state(node, N_CPU)
 
 /*
  * For nodemask scratch area.