Merge tag 'bitmap-6.0-rc1' of https://github.com/norov/linux

Pull bitmap updates from Yury Norov:

 - fix the duplicated comments on bitmap_to_arr64() (Qu Wenruo)

 - optimize out non-atomic bitops on compile-time constants (Alexander
   Lobakin)

 - cleanup bitmap-related headers (Yury Norov)

 - x86/olpc: fix 'logical not is only applied to the left hand side'
   (Alexander Lobakin)

 - lib/nodemask: inline wrappers around bitmap (Yury Norov)

* tag 'bitmap-6.0-rc1' of https://github.com/norov/linux: (26 commits)
  lib/nodemask: inline next_node_in() and node_random()
  powerpc: drop dependency on <asm/machdep.h> in archrandom.h
  x86/olpc: fix 'logical not is only applied to the left hand side'
  lib/cpumask: move some one-line wrappers to header file
  headers/deps: mm: align MANITAINERS and Docs with new gfp.h structure
  headers/deps: mm: Split <linux/gfp_types.h> out of <linux/gfp.h>
  headers/deps: mm: Optimize <linux/gfp.h> header dependencies
  lib/cpumask: move trivial wrappers around find_bit to the header
  lib/cpumask: change return types to unsigned where appropriate
  cpumask: change return types to bool where appropriate
  lib/bitmap: change type of bitmap_weight to unsigned long
  lib/bitmap: change return types to bool where appropriate
  arm: align find_bit declarations with generic kernel
  iommu/vt-d: avoid invalid memory access via node_online(NUMA_NO_NODE)
  lib/test_bitmap: test the tail after bitmap_to_arr64()
  lib/bitmap: fix off-by-one in bitmap_to_arr64()
  lib: test_bitmap: add compile-time optimization/evaluations assertions
  bitmap: don't assume compiler evaluates small mem*() builtins calls
  net/ice: fix initializing the bitmap in the switch code
  bitops: let optimize out non-atomic bitops on compile-time constants
  ...

5 files changed, 81 insertions, 105 deletions

diff --git a/lib/Makefile b/lib/Makefile
index 17e48da223e2..c95212141928 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -33,7 +33,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
-	 nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o \
+	 nmi_backtrace.o win_minmax.o memcat_p.o \
 	 buildid.o cpumask.o
 
 lib-$(CONFIG_PRINTK) += dump_stack.o
diff --git a/lib/bitmap.c b/lib/bitmap.c
index b18e31ea6e66..488e6c3e5acc 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -237,7 +237,7 @@ void bitmap_cut(unsigned long *dst, const unsigned long *src,
 }
 EXPORT_SYMBOL(bitmap_cut);
 
-int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 				const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k;
@@ -275,7 +275,7 @@ void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_xor);
 
-int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
 				const unsigned long *bitmap2, unsigned int bits)
 {
 	unsigned int k;
@@ -333,10 +333,9 @@ bool __bitmap_subset(const unsigned long *bitmap1,
 }
 EXPORT_SYMBOL(__bitmap_subset);
 
-int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
+unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
 {
-	unsigned int k, lim = bits/BITS_PER_LONG;
-	int w = 0;
+	unsigned int k, lim = bits/BITS_PER_LONG, w = 0;
 
 	for (k = 0; k < lim; k++)
 		w += hweight_long(bitmap[k]);
@@ -1564,7 +1563,7 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits)
 
 	/* Clear tail bits in the last element of array beyond nbits. */
 	if (nbits % 64)
-		buf[-1] &= GENMASK_ULL(nbits % 64, 0);
+		buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0);
 }
 EXPORT_SYMBOL(bitmap_to_arr64);
 #endif
diff --git a/lib/cpumask.c b/lib/cpumask.c
index b9728513a4d4..8baeb37e23d3 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -8,61 +8,6 @@
 #include <linux/numa.h>
 
 /**
- * cpumask_next - get the next cpu in a cpumask
- * @n: the cpu prior to the place to search (ie. return will be > @n)
- * @srcp: the cpumask pointer
- *
- * Returns >= nr_cpu_ids if no further cpus set.
- */
-unsigned int cpumask_next(int n, const struct cpumask *srcp)
-{
-	/* -1 is a legal arg here. */
-	if (n != -1)
-		cpumask_check(n);
-	return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
-}
-EXPORT_SYMBOL(cpumask_next);
-
-/**
- * cpumask_next_and - get the next cpu in *src1p & *src2p
- * @n: the cpu prior to the place to search (ie. return will be > @n)
- * @src1p: the first cpumask pointer
- * @src2p: the second cpumask pointer
- *
- * Returns >= nr_cpu_ids if no further cpus set in both.
- */
-int cpumask_next_and(int n, const struct cpumask *src1p,
-		     const struct cpumask *src2p)
-{
-	/* -1 is a legal arg here. */
-	if (n != -1)
-		cpumask_check(n);
-	return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
-		nr_cpumask_bits, n + 1);
-}
-EXPORT_SYMBOL(cpumask_next_and);
-
-/**
- * cpumask_any_but - return a "random" in a cpumask, but not this one.
- * @mask: the cpumask to search
- * @cpu: the cpu to ignore.
- *
- * Often used to find any cpu but smp_processor_id() in a mask.
- * Returns >= nr_cpu_ids if no cpus set.
- */
-int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
-{
-	unsigned int i;
-
-	cpumask_check(cpu);
-	for_each_cpu(i, mask)
-		if (i != cpu)
-			break;
-	return i;
-}
-EXPORT_SYMBOL(cpumask_any_but);
-
-/**
  * cpumask_next_wrap - helper to implement for_each_cpu_wrap
  * @n: the cpu prior to the place to search
  * @mask: the cpumask pointer
@@ -74,9 +19,9 @@ EXPORT_SYMBOL(cpumask_any_but);
  * Note: the @wrap argument is required for the start condition when
  * we cannot assume @start is set in @mask.
  */
-int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
 {
-	int next;
+	unsigned int next;
 
 again:
 	next = cpumask_next(n, mask);
@@ -125,34 +70,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 }
 EXPORT_SYMBOL(alloc_cpumask_var_node);
 
-bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
-{
-	return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
-}
-EXPORT_SYMBOL(zalloc_cpumask_var_node);
-
-/**
- * alloc_cpumask_var - allocate a struct cpumask
- * @mask: pointer to cpumask_var_t where the cpumask is returned
- * @flags: GFP_ flags
- *
- * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
- * a nop returning a constant 1 (in <linux/cpumask.h>).
- *
- * See alloc_cpumask_var_node.
- */
-bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
-{
-	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
-}
-EXPORT_SYMBOL(alloc_cpumask_var);
-
-bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
-{
-	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
-}
-EXPORT_SYMBOL(zalloc_cpumask_var);
-
 /**
  * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
  * @mask: pointer to cpumask_var_t where the cpumask is returned
@@ -206,7 +123,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  */
 unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	int cpu;
+	unsigned int cpu;
 
 	/* Wrap: we always want a cpu. */
 	i %= num_online_cpus();
@@ -244,10 +161,10 @@ static DEFINE_PER_CPU(int, distribute_cpu_mask_prev);
  *
  * Returns >= nr_cpu_ids if the intersection is empty.
  */
-int cpumask_any_and_distribute(const struct cpumask *src1p,
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
 			       const struct cpumask *src2p)
 {
-	int next, prev;
+	unsigned int next, prev;
 
 	/* NOTE: our first selection will skip 0. */
 	prev = __this_cpu_read(distribute_cpu_mask_prev);
@@ -263,9 +180,9 @@ int cpumask_any_and_distribute(const struct cpumask *src1p,
 }
 EXPORT_SYMBOL(cpumask_any_and_distribute);
 
-int cpumask_any_distribute(const struct cpumask *srcp)
+unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
-	int next, prev;
+	unsigned int next, prev;
 
 	/* NOTE: our first selection will skip 0. */
 	prev = __this_cpu_read(distribute_cpu_mask_prev);
diff --git a/lib/nodemask.c b/lib/nodemask.c
index e22647f5181b..b8a433d16b51 100644
--- a/lib/nodemask.c
+++ b/lib/nodemask.c
@@ -3,14 +3,6 @@
 #include <linux/module.h>
 #include <linux/random.h>
 
-unsigned int __next_node_in(int node, const nodemask_t *srcp)
-{
-	unsigned int ret = __next_node(node, srcp);
-
-	if (ret == MAX_NUMNODES)
-		ret = __first_node(srcp);
-	return ret;
-}
 EXPORT_SYMBOL(__next_node_in);
 
 #ifdef CONFIG_NUMA
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index d5923a640457..98754ff9fe68 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -604,6 +604,12 @@ static void __init test_bitmap_arr64(void)
 			pr_err("bitmap_copy_arr64(nbits == %d:"
 				" tail is not safely cleared: %d\n", nbits, next_bit);
 
+		if ((nbits % 64) &&
+		    (arr[(nbits - 1) / 64] & ~GENMASK_ULL((nbits - 1) % 64, 0)))
+			pr_err("bitmap_to_arr64(nbits == %d): tail is not safely cleared: 0x%016llx (must be 0x%016llx)\n",
+			       nbits, arr[(nbits - 1) / 64],
+			       GENMASK_ULL((nbits - 1) % 64, 0));
+
 		if (nbits < EXP1_IN_BITS - 64)
 			expect_eq_uint(arr[DIV_ROUND_UP(nbits, 64)], 0xa5a5a5a5);
 	}
@@ -869,6 +875,67 @@ static void __init test_bitmap_print_buf(void)
 	}
 }
 
+static void __init test_bitmap_const_eval(void)
+{
+	DECLARE_BITMAP(bitmap, BITS_PER_LONG);
+	unsigned long initvar = BIT(2);
+	unsigned long bitopvar = 0;
+	unsigned long var = 0;
+	int res;
+
+	/*
+	 * Compilers must be able to optimize all of those to compile-time
+	 * constants on any supported optimization level (-O2, -Os) and any
+	 * architecture. Otherwise, trigger a build bug.
+	 * The whole function gets optimized out then, there's nothing to do
+	 * in runtime.
+	 */
+
+	/*
+	 * Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }`.
+	 * Clang on s390 optimizes bitops at compile-time as intended, but at
+	 * the same time stops treating @bitmap and @bitopvar as compile-time
+	 * constants after regular test_bit() is executed, thus triggering the
+	 * build bugs below. So, call const_test_bit() there directly until
+	 * the compiler is fixed.
+	 */
+	bitmap_clear(bitmap, 0, BITS_PER_LONG);
+#if defined(__s390__) && defined(__clang__)
+	if (!const_test_bit(7, bitmap))
+#else
+	if (!test_bit(7, bitmap))
+#endif
+		bitmap_set(bitmap, 5, 2);
+
+	/* Equals to `unsigned long bitopvar = BIT(20)` */
+	__change_bit(31, &bitopvar);
+	bitmap_shift_right(&bitopvar, &bitopvar, 11, BITS_PER_LONG);
+
+	/* Equals to `unsigned long var = BIT(25)` */
+	var |= BIT(25);
+	if (var & BIT(0))
+		var ^= GENMASK(9, 6);
+
+	/* __const_hweight<32|64>(GENMASK(6, 5)) == 2 */
+	res = bitmap_weight(bitmap, 20);
+	BUILD_BUG_ON(!__builtin_constant_p(res));
+	BUILD_BUG_ON(res != 2);
+
+	/* !(BIT(31) & BIT(18)) == 1 */
+	res = !test_bit(18, &bitopvar);
+	BUILD_BUG_ON(!__builtin_constant_p(res));
+	BUILD_BUG_ON(!res);
+
+	/* BIT(2) & GENMASK(14, 8) == 0 */
+	res = initvar & GENMASK(14, 8);
+	BUILD_BUG_ON(!__builtin_constant_p(res));
+	BUILD_BUG_ON(res);
+
+	/* ~BIT(25) */
+	BUILD_BUG_ON(!__builtin_constant_p(~var));
+	BUILD_BUG_ON(~var != ~BIT(25));
+}
+
 static void __init selftest(void)
 {
 	test_zero_clear();
@@ -884,6 +951,7 @@ static void __init selftest(void)
 	test_for_each_set_clump8();
 	test_bitmap_cut();
 	test_bitmap_print_buf();
+	test_bitmap_const_eval();
 }
 
 KSTM_MODULE_LOADERS(test_bitmap);